From ae7eddf3239eba603b4fb95abe183808b2de0572 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Wed, 17 Jan 2024 19:54:02 +0800 Subject: [PATCH 01/18] add docs for all tutorial --- docs/tutorial/101-installation.md | 70 +++++++ docs/tutorial/102-concepts.md | 47 +++++ docs/tutorial/103-example.md | 108 ++++++++++ docs/tutorial/104-usecase.md | 324 ++++++++++++++++++++++++++++++ docs/tutorial/105-logging.md | 102 ++++++++++ docs/tutorial/201-agent.md | 176 ++++++++++++++++ docs/tutorial/202-pipeline.md | 285 ++++++++++++++++++++++++++ docs/tutorial/203-model.md | 252 +++++++++++++++++++++++ docs/tutorial/204-service.md | 134 ++++++++++++ docs/tutorial/205-memory.md | 146 ++++++++++++++ docs/tutorial/206-prompt.md | 64 ++++++ docs/tutorial/207-monitor.md | 100 +++++++++ docs/tutorial/208-distribute.md | 147 ++++++++++++++ docs/tutorial/301-community.md | 34 ++++ docs/tutorial/302-contribute.md | 69 +++++++ docs/tutorial/advance.rst | 14 ++ docs/tutorial/contribute.rst | 8 + docs/tutorial/main.md | 39 ++++ docs/tutorial/quick_start.rst | 11 + 19 files changed, 2130 insertions(+) create mode 100644 docs/tutorial/101-installation.md create mode 100644 docs/tutorial/102-concepts.md create mode 100644 docs/tutorial/103-example.md create mode 100644 docs/tutorial/104-usecase.md create mode 100644 docs/tutorial/105-logging.md create mode 100644 docs/tutorial/201-agent.md create mode 100644 docs/tutorial/202-pipeline.md create mode 100644 docs/tutorial/203-model.md create mode 100644 docs/tutorial/204-service.md create mode 100644 docs/tutorial/205-memory.md create mode 100644 docs/tutorial/206-prompt.md create mode 100644 docs/tutorial/207-monitor.md create mode 100644 docs/tutorial/208-distribute.md create mode 100644 docs/tutorial/301-community.md create mode 100644 docs/tutorial/302-contribute.md create mode 100644 docs/tutorial/advance.rst create mode 100644 docs/tutorial/contribute.rst create mode 100644 docs/tutorial/main.md create mode 100644 docs/tutorial/quick_start.rst diff --git a/docs/tutorial/101-installation.md b/docs/tutorial/101-installation.md new file mode 100644 index 000000000..8f0af849a --- /dev/null +++ b/docs/tutorial/101-installation.md @@ -0,0 +1,70 @@ +# Installation + +To install AgentScope, you need to have Python 3.9 or higher installed. We recommend setting up a new virtual environment specifically for AgentScope: + +### Create a Virtual Environment + +#### Using Conda + +If you're using Conda as your package and environment management tool, you can create a new virtual environment with Python 3.9 using the following commands: + +```bash +# Create a new virtual environment named 'agentscope' with Python 3.9 +conda create -n agentscope python=3.9 + +# Activate the virtual environment +conda activate agentscope +``` + +#### Using Virtualenv + +Alternatively, if you prefer `virtualenv`, you can install it first (if it's not already installed) and then create a new virtual environment as shown: + +```bash +# Install virtualenv if it is not already installed +pip install virtualenv + +# Create a new virtual environment named 'agentscope' with Python 3.9 +virtualenv agentscope --python=python3.9 + +# Activate the virtual environment +source agentscope/bin/activate # On Windows use `agentscope\Scripts\activate` +``` + +### Installing AgentScope + +#### Install from Source + +For users who prefer to install AgentScope directly from the source code, follow these steps to clone the repository and install the platform in editable mode: + +**_Note: This project is under active development, it's recommended to install AgentScope from source._** + +```bash +# Pull the source code from Github +git clone https://github.com/alibaba/AgentScope.git +cd AgentScope + +# For centralized multi-agent applications +pip install -e . +# For distributed multi-agent applications +pip install -e .[distribute] # On Mac use `pip install -e .\[distribute\]` +``` + +#### Install with Pip + +If you prefer to install AgentScope from Pypi, you can do so easily using `pip`: + +```bash +# For centralized multi-agent applications +pip install agentscope +# For distributed multi-agent applications +pip install agentscope[distribute] # On Mac use `pip install agentscope\[distribute\]` +``` + + + +**Note**: The `[distribute]` option installs additional dependencies required for distributed applications. Remember to activate your virtual environment before running these commands. + + + +[[Return to the top]](#installation) \ No newline at end of file diff --git a/docs/tutorial/102-concepts.md b/docs/tutorial/102-concepts.md new file mode 100644 index 000000000..a87228bfa --- /dev/null +++ b/docs/tutorial/102-concepts.md @@ -0,0 +1,47 @@ +# Fundamental Concepts + +In this tutorial, you'll have an initial understanding of the **fundamental concepts** of AgentScope. We will focus on how a multi-agent application runs based on our platform and familiarize you with the essential terms. Let's get started! + +![Concepts](https://img.alicdn.com/imgextra/i1/O1CN01ELiTw41KGKqTmWZua_!!6000000001136-2-tps-756-598.png) + +## Essential Terms and Concepts + +* **Agent** refers to an autonomous entity capable of performing actions to achieve specific objectives (probably powered by LLMs). In AgentScope, an agent takes the message as input and generates a corresponding response message. Agents can interact with each other to simulate human-like behaviors (e.g., discussion or debate) and cooperate to finish complicated tasks (e.g., generate runnable and reliable code). +* **Message** is a carrier of communication information between agents. It encapsulates information that needs to be conveyed, such as instructions, multi-modal data, or status updates. In AgentScope, a message is a subclass of Python's dict with additional features for inter-agent communication, including fields such as `name` and `content` for identification and payload delivery. +* **Memory** refers to the structures (e.g., list-like memory, database-based memory) used to store and manage `Message` that agents need to remember and store. This can include chat history, knowledge, or other data that informs the agent's future actions. +* **Service** is a collection of functionality tools (e.g., web search, code interpreter, file processing) that provide specific capabilities or processes that are independent of an agent's memory state. Services can be invoked by agents or other components and designed to be reusable across different scenarios. +* **Pipeline** refers to the interaction order or pattern of agents in a task. AgentScope provides built-in `pipelines` to streamline the process of collaboration across multiple agents, such as `SequentialPipeline` and `ForLoopPipeline`. When a `Pipeline` is executed, the `message` passes from predecessors to successors with intermediate results for the task. + + +## Code Structure + +```bash +AgentScope +├── src +│ ├── agentscope +│ | ├── agents # Core components and implementations pertaining to agents. +│ | ├── configs # Configurations that can be customized for the application's needs. +│ | ├── memory # Structures for agent memory. +│ | ├── models # Interfaces for integrating diverse model APIs. +│ | ├── pipeline # Fundamental components and implementations for running pipelines. +│ | ├── rpc # Rpc module for agent distributed deployment. +│ | ├── service # Services offering functions independent of memory and state. +│ | ├── utils # Auxiliary utilities and helper functions. +│ | ├── message.py # Definitions and implementations of messaging between agents. +| | ├── web_ui # WebUI used to show dialogs. +│ | ├── prompt.py # Prompt engineering module for model input. +│ | ├── ... .. +│ | ├── ... .. +├── scripts # Scripts for launching local Model API +├── examples # Pre-built examples of different applications. +├── docs # Documentation tool for API reference. +├── tests # Unittest modules for continuous integration. +├── LICENSE # The official licensing agreement for AgentScope usage. +└── setup.py # Setup script for installing. +├── ... .. +└── ... .. +``` + + + +[[Return to the top]](#fundamental-concepts) \ No newline at end of file diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md new file mode 100644 index 000000000..1ed8d6fcb --- /dev/null +++ b/docs/tutorial/103-example.md @@ -0,0 +1,108 @@ +# Getting Started with a Simple Example + +AgentScope is a versatile platform for building and running multi-agent applications. We provide various pre-built examples that will help you quickly understand how to create and use multi-agent for various applications. In this tutorial, you will learn to set up a **simple agent-based interaction**. + +## Step1: Prepare Model Configs + +Agent is the basic composition and communication unit in AgentScope. To initialize an model-based agent, you need to prepare your configs for avaliable models. AgentScope supports a variety of APIs for pre-trained models. Here is a table outlining the supported APIs and the type of arguments required for each: + +| Model Usage | Type Argument in AgentScope | Supported APIs | +| -------------------- | ------------------ | ------------------------------------------------------------ | +| Text generation | `openai` | Standard OpenAI chat API, FastChat and vllm | +| Image generation | `openai_dall_e` | DALL-E API for generating images | +| Embedding | `openai_embedding` | API for text embeddings | +| General usages in POST | `post_api` | Huggingface/ModelScope Inference API, and customized post API | + + +Each API has its specific configuration requirements. For example, to configure an OpenAI API, you would need to fill out the following fields in the model config in a dict, a yaml file or a json file: + +``` +model_config = { + "type": "openai", # Choose from "openai", "openai_dall_e", or "openai_embedding" + "name": "{your_config_name}", # A unique identifier for your config + "model_name": "{model_name}", # The model identifier used in the OpenAI API, such as "gpt-3.5-turbo", "gpt-4", or "text-embedding-ada-002" + "api_key": "xxx", # Your OpenAI API key. If unset, the environment variable OPENAI_API_KEY is used. + "organization": "xxx", # Your OpenAI organization ID. If unset, the environment variable OPENAI_ORGANIZATION is used. +} +``` + +For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). + +You can register your configuration by calling AgentScope's initilization method as follow. Besides, you can also load more than one config by calling init mutliple times. +```python +import agentscope + +agentscope.init(model_configs="./openai_model_configs.json") +agentscope.init(model_configs="./modelscope_model_configs.json") # use openai and modelscope at the same time + +# or you can init once by passing a list of config dict +# openai_cfg_dict = {...dict_filling...} +# modelscope_cfg_dict = {...dict_filling...} +# agentscope.init(model_configs=[openai_cfg_dict, modelscope_cfg_dict]) +``` + + +## Step2: Create Agents + +Creating agents is straightforward in AgentScope. After initializing AgentScope with your model configurations (Step 1 above), you can then define each agent with its corresponding role and specific model. + +```python +import agentscope +from agentscope.agents import DialogAgent, UserAgent + +# read model configs +agentscope.init(model_configs="./openai_model_configs.json") + +# Create a dialog agent and a user agent +dialogAgent = DialogAgent(name="assistant", model="gpt-4") +userAgent = UserAgent() +``` + +**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-agent.md) for all available agents. + +## Step3: Agent Conversation + +`Message` is the primary means of communication between agents in AgentScope. They are Python dictionaries comprising essential fields like the actual `content` of this message and the sender's `name`. Optionally, a message can include a `url` to either a local file (image, video or audio) or website. + +```python +from agentscope.message import Msg + +# Example of a simple text message from Alice +message_from_alice = Msg("Alice", "Hi!") + +# Example of a message from Bob with an attached image +message_from_bob = Msg("Bob", "What about this picture I took?", url="/path/to/picture.jpg") +``` + +To start a conversation between two agents, such as `dialogAgent` and `userAgent`, you can use the following loop. The conversation continues until the user inputs `"exit"` which terminates the interaction. + +```python +x = None +while True: + x = dialogAgent(x) + x = userAgent(x) + + # Terminate the conversation if the user types "exit" + if x.content == "exit": + print("Exiting the conversation.") + break +``` + +For a more advanced approach, AgentScope offers the option of using pipelines to manage the flow of messages between agents. The `sequentialpipeline` stands for sequential speech, where each agent receive message from last agent and generate its response accordingly. + +```python +from agentscope.pipelines.functional import ( + sequentialpipeline, +) + +# Execute the conversation loop within a pipeline structure +x = None +while x is None or x.content != "exit": + x = sequentialpipeline(dialogAgent, userAgent) +``` + +For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-pipeline.md). + + + +[[Return to the top]](#getting-started-with-a-simple-example) diff --git a/docs/tutorial/104-usecase.md b/docs/tutorial/104-usecase.md new file mode 100644 index 000000000..63270b97d --- /dev/null +++ b/docs/tutorial/104-usecase.md @@ -0,0 +1,324 @@ +# Crafting Your First Application + +img + +Before diving into the advanced topics of AgentScope, in this tutorial, we will give you a glance at building a Werewolf application with out-of-the-box components of AgentScope. + +**Werewolf** is a well-known social-deduction game, that involves an imaginary village where a few villagers are secretly werewolves, and the objective is to find out who they are before they eliminate all other players. It's a good use case to demonstrate the interaction between multiple autonomous agents, each with its own objectives and the need for communication. + +Let the adventure begin to unlock the potential of multi-agent applications with AgentScope! + +## Getting Started + +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Message`, and `pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: + +* [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) +* [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) +* [Step 3: **Initialize** AgentScope and the Agents](#step-3-initialize-agentscope-and-the-agents) +* [Step 4: Set Up the Game Logic with **Pipelines**](#step-4-set-up-the-game-logic-with-pipelines) +* [Step 5: **Run** the Application](#step-5-run-the-application) + +**Note**: all the configurations and code for this tutorial can be found in `examples/werewolf`. + +### Step 1: Prepare Model API and Set Model Configs + +As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). + +```json +[ + { + "type": "openai", + "name": "gpt-4", + "parameters": { + "api_key": "xxx", + "organization_id": "xxx", + "temperature": 0.0 + } + }, +] +``` + +### Step 2: Define the Roles of Each Agent + +In the Werewolf game, agents assume a variety of roles, each endowed with distinctive abilities and objectives. Below, we will outline the agent classes corresponding to each role: + +- Villager: Ordinary townsfolk trying to survive. +- Werewolf: Predators in disguise, aiming to outlast the villagers. +- Seer: A villager with the power to see the true nature of one player each night. +- Witch: A villager who can save or poison a player each night. + +To implement your own agent, you need to inherit `AgentBase` and implement the `reply` function, which is executed when an agent instance is called via `agent1(x)`. + +```python +from agentscope.agents import AgentBase + +class MyAgent(AgentBase): + def reply(self, x): + # Do something here + ... + return x +``` + +AgentScope provides several out-of-box Agents implements and organizes them as an *Agent Pool*. In this application, we use a built-in agent, `DictDialogAgent`. Here we give an example configuration of `DictDialogAgent` for a player assigned as the role of a werewolf: + +```json +{ + "class": "DictDialogAgent", + "args": { + "name": "Player1", + "sys_prompt": "Act as a player in a werewolf game. You are Player1 and\nthere are totally 6 players, named Player1, Player2, Player3, Player4, Player5 and Player6.\n\nPLAYER ROLES:\nIn werewolf game, players are divided into two werewolves, two villagers, one seer, and one witch. Note only werewolves know who are their teammates.\nWerewolves: They know their teammates' identities and attempt to eliminate a villager each night while trying to remain undetected.\nVillagers: They do not know who the werewolves are and must work together during the day to deduce who the werewolves might be and vote to eliminate them.\nSeer: A villager with the ability to learn the true identity of one player each night. This role is crucial for the villagers to gain information.\nWitch: A character who has a one-time ability to save a player from being eliminated at night (sometimes this is a potion of life) and a one-time ability to eliminate a player at night (a potion of death).\n\nGAME RULE:\nThe game consists of two phases: night phase and day phase. The two phases are repeated until werewolf or villager wins the game.\n1. Night Phase: During the night, the werewolves discuss and vote for a player to eliminate. Special roles also perform their actions at this time (e.g., the Seer chooses a player to learn their role, the witch chooses a decide if save the player).\n2. Day Phase: During the day, all surviving players discuss who they suspect might be a werewolf. No one reveals their role unless it serves a strategic purpose. After the discussion, a vote is taken, and the player with the most votes is \"lynched\" or eliminated from the game.\n\nVICTORY CONDITION:\nFor werewolves, they win the game if the number of werewolves is equal to or greater than the number of remaining villagers.\nFor villagers, they win if they identify and eliminate all of the werewolves in the group.\n\nCONSTRAINTS:\n1. Your response should be in the first person.\n2. This is a conversational game. You should respond only based on the conversation history and your strategy.\n\nYou are playing werewolf in this game.\n", + "model": "gpt-3.5-turbo", + "use_memory": true + } +} +``` + +In this configuration, `Player1` is designated as a `DictDialogAgent`. The parameters include a system prompt (`sys_prompt`) that can guide the agent's behavior, the model (`model`) that determines the type of language model of the agent, and a flag (`use_memory`) indicating whether the agent should remember past interactions. + +For other players, configurations can be customized based on their roles. Each role may have different prompts, models, or memory settings. You can refer to the JSON file located at `examples/werewolf/configs/agent_configs.json` within the AgentScope examples directory. + +### Step 3: Initialize AgentScope and the Agents + +Now we have defined the roles in the application and we can initialize the AgentScope environment and all agents. This process is simplified by AgentScope via a few lines, based on the configuration files we've prepared (assuming there are **2** werewolves, **2** villagers, **1** witch, and **1** seer): + +```python +import agentscope + +# read model and agent configs, and initialize agents automatically +survivors = agentscope.init( + model_configs="./configs/model_configs.json", + agent_configs="./configs/agent_configs.json", + logger_level="DEBUG", +) + +# Define the roles within the game. This list should match the order and number +# of agents specified in the 'agent_configs.json' file. +roles = ["werewolf", "werewolf", "villager", "villager", "seer", "witch"] + +# Based on their roles, assign the initialized agents to variables. +# This helps us reference them easily in the game logic. +wolves, villagers, witch, seer = survivors[:2], survivors[2:-2], survivors[-1], survivors[-2] +``` + +Through this snippet of code, we've allocated roles to our agents and associated them with the configurations that dictate their behavior in the application. + +### Step 4: Set Up the Game Logic + +In this step, you will set up the game logic and orchestrate the flow of the Werewolf game using AgentScope's helper utilities. + +#### Leverage Pipeline and MsgHub + +To simplify the construction of agent communication, AgentScope provides two helpful concepts: **Pipeline** and **MsgHub**. + +- **Pipeline**: It allows users to program communication among agents easily. + + ```python + from agentscope.pipelines import SequentialPipeline + + pipe = SequentialPipeline(agent1, agent2, agent3) + x = pipe(x) # the message x will be passed and replied by agent 1,2,3 in order + ``` + +- **MsgHub**: You may have noticed that all the above examples are one-to-one communication. To achieve a group chat, we provide another communication helper utility `msghub`. With it, the messages from participants will be broadcast to all other participants automatically. In such cases, participating agents even don't need input and output messages. All we need to do is to decide the order of speaking. Besides, `msghub` also supports dynamic control of participants. + + ```python + with msghub(participants=[agent1, agent2, agent3]) as hub: + agent1() + agent2() + + # Broadcast a message to all participants + hub.broadcast(Msg("Host", "Welcome to join the group chat!")) + + # Add or delete participants dynamically + hub.delete(agent1) + hub.add(agent4) + ``` + +#### Implement Werewolf Pipeline + +The game logic is divided into two major phases: (1) night when werewolves act, and (2) daytime when all players discuss and vote. Each phase will be handled by a section of code using pipelines to manage multi-agent communications. + +* **1.1 Night Phase: Werewolves Discuss and Vote** + +During the night phase, werewolves must discuss among themselves to decide on a target. The `msghub` function creates a message hub for the werewolves to communicate in, where every message sent by an agent is observable by all other agents within the `msghub`. + +```python +# start the game +for i in range(1, MAX_GAME_ROUND + 1): + # Night phase: werewolves discuss + hint = HostMsg(content=Prompts.to_wolves.format(n2s(wolves))) + with msghub(wolves, announcement=hint) as hub: + for _ in range(MAX_WEREWOLF_DISCUSSION_ROUND): + x = sequentialpipeline(wolves) + if x.agreement: + break +``` + +After the discussion, werewolves proceed to vote for their target, and the majority's choice is determined. The result of the vote is then broadcast to all werewolves. + +**Note**: the detailed prompts and utility functions can be found in `examples/werewolf`. + +```python + # werewolves vote + hint = HostMsg(content=Prompts.to_wolves_vote) + votes = [extract_name_and_id(wolf(hint).content)[0] for wolf in wolves] + # broadcast the result to werewolves + dead_player = [majority_vote(votes)] + hub.broadcast( + HostMsg(content=Prompts.to_wolves_res.format(dead_player[0])), + ) +``` + +* **1.2 Witch's Turn** + +If the witch is still alive, she gets the opportunity to use her powers to either save the player chosen by the werewolves or use her poison. + +```python + # Witch's turn + healing_used_tonight = False + if witch in survivors: + if healing: + # Witch decides whether to use the healing potion + hint = HostMsg( + content=Prompts.to_witch_resurrect.format_map( + {"witch_name": witch.name, "dead_name": dead_player[0]}, + ), + ) + # Witch decides whether to use the poison + if witch(hint).resurrect: + healing_used_tonight = True + dead_player.pop() + healing = False +``` + +* **1.3 Seer's Turn** + +The seer has a chance to reveal the true identity of a player. This information can be crucial for the villagers. The `observe()` function allows each agent to take note of a message without immediately replying to it. + +```python + # Seer's turn + if seer in survivors: + # Seer chooses a player to reveal their identity + hint = HostMsg( + content=Prompts.to_seer.format(seer.name, n2s(survivors)), + ) + x = seer(hint) + + player, idx = extract_name_and_id(x.content) + role = "werewolf" if roles[idx] == "werewolf" else "villager" + hint = HostMsg(content=Prompts.to_seer_result.format(player, role)) + seer.observe(hint) +``` + +* **1.4 Update Alive Players** + +Based on the actions taken during the night, the list of surviving players needs to be updated. + +```python + # Update the list of survivors and werewolves after the night's events + survivors, wolves = update_alive_players(survivors, wolves, dead_player) +``` + +* **2.1 Daytime Phase: Discussion and Voting** + +During the day, all players will discuss and then vote to eliminate a suspected werewolf. + +```python + # Daytime discussion + with msghub(survivors, announcement=hints) as hub: + # Discuss + x = sequentialpipeline(survivors) + # Vote + hint = HostMsg(content=Prompts.to_all_vote.format(n2s(survivors))) + votes = [extract_name_and_id(_(hint).content)[0] for _ in survivors] + vote_res = majority_vote(votes) + # Broadcast the voting result to all players + result = HostMsg(content=Prompts.to_all_res.format(vote_res)) + hub.broadcast(result) + # Update the list of survivors and werewolves after the vote + survivors, wolves = update_alive_players(survivors, wolves, vote_res) +``` + +* **2.2 Check for Winning Conditions** + +After each phase, the game checks if the werewolves or villagers have won. + +```python + # Check if either side has won + if check_winning(survivors, wolves, "Moderator"): + break +``` + +* **2.3 Continue to the Next Round** + +If neither werewolves nor villagers win, the game continues to the next round. + +```python + # If the game hasn't ended, prepare for the next round + hub.broadcast(HostMsg(content=Prompts.to_all_continue)) +``` + +These code blocks outline the core game loop for Werewolf using AgentScope's `msghub` and `pipeline`, which help to easily manage the operational logic of an application. + +### Step 5: Run the Application + +With the game logic and agents set up, you're ready to run the Werewolf game. By executing the `pipeline`, the game will proceed through the predefined phases, with agents interacting based on their roles and the strategies coded above: + +```bash +cd examples/werewolf +python main.py # Assuming the pipeline is implemented in main.py +``` + +As the game starts, you'll see output in the terminal, similar to the logs below, which illustrate how the game unfolds: + +```bash +Moderator: Player1 and Player2, you are werewolves. If you are alone, eliminate a player, else discuss with your teammates and reach an agreement. Response in the following format which can be loaded by json.loads(){ + "thought": "thought", + "speak": "thoughts summary to say to others", + "agreement": "whether the discussion reached an agreement or not(true/false)" +} +Player1: Player2, let's discuss who we should eliminate tonight. +Player2: I think we should eliminate Player4 tonight. They seem suspicious to me. +Player1: I think we should eliminate Player4 tonight. They seem suspicious to me. +Player2: I agree with Player2, let's eliminate Player4 tonight. They seem suspicious. +Moderator: Which player do you vote to kill? Response in the following format which can be loaded by python json.loads() +{{ + "thought": "thought" , + "speak": "player_name" +}} +Player1: Player4 +Player2: Player4 +Moderator: The player with the most votes is Player4. +Moderator: Player6, you're witch. Tonight Player4 is eliminated. Would you like to resurrect Player4? Response in the following format which can be loaded by python json.loads() +{ + "thought": "thought", + "speak": "thoughts summary to say", + "resurrect": "true/false" +} +Player6: I have considered the options, and I choose to resurrect Player4. +Moderator: Player5, you're seer. Which player in Player1, Player2, Player3, Player4, Player5 and Player6 would you like to check tonight? Response in the following json format which can be loaded by python json.loads() +{ + "thought": "thought" , + "speak": "player_name" +} +Player5: Player3 +Moderator: Okay, the role of Player3 is villager. +Moderator: The day is coming, all the players open your eyes. Last night is peaceful, no player is eliminated. +... +``` + +## Next step + +Now you've grasped how to conveniently set up a multi-agent application with AgentScope. Feel free to tailor the game to include additional roles and introduce more sophisticated strategies. For more advanced tutorials that delve deeper into more capabilities of AgentScope, such as *memory management* and *service functions* utilized by agents, please refer to the tutorials in the **Advanced Exploration** section and look up the API references. + + +## Other Example Applications + +- Example of Simple Group Conversation: [examples/Simple Conversation](https://github.com/alibaba/AgentScope/tree/main/examples/simple_chat/README.md) +- Example of Werewolves: [examples/Werewolves](https://github.com/alibaba/AgentScope/tree/main/examples/werewolves/README.md) +- Example of Distributed Agents: [examples/Distributed Agents](https://github.com/alibaba/AgentScope/tree/main/examples/distributed_agents/README.md) +- ... + + + +[[Return to the top]](#crafting-your-first-application) \ No newline at end of file diff --git a/docs/tutorial/105-logging.md b/docs/tutorial/105-logging.md new file mode 100644 index 000000000..55e50d93f --- /dev/null +++ b/docs/tutorial/105-logging.md @@ -0,0 +1,102 @@ +# Logging and WebUI + +Welcome to the tutorial on logging in multi-agent applications with AgentScope. We'll also touch on how you can visualize these logs using a simple web interface. This guide will help you track the agent's interactions and system information in a clearer and more organized way. + +## Logging + +The logging utilities consist of a custom setup for the `loguru.logger`, which is an enhancement over Python's built-in `logging` module. We provide custom features: + +- **Colored Output**: Assigns different colors to different speakers in a chat to enhance readability. +- **Redirecting Standard Error (stderr)**: Captures error messages and logs them with the `ERROR` level. +- **Custom Log Levels**: Adds a custom level called `CHAT` that is specifically designed for logging dialogue interactions. +- **Special Formatting**: Format logs with timestamps, levels, function names, and line numbers. Chat messages are formatted differently to stand out. + +### Setting Up the Logger + +We recommend setting up the logger via `agentscope.init`, and you can set the log level: + +```python +import agentscope + +LOG_LEVEL = Literal[ + "TRACE", + "DEBUG", + "CHAT", + "INFO", + "SUCCESS", + "WARNING", + "ERROR", + "CRITICAL", +] + +agentscope.init(..., logger_level="INFO") +``` + +### Logging a Chat Message + +Logging chat messages helps keep a record of the conversation between agents. Here's how you can do it: + +```python +# Log a simple string message. +logger.chat("Hello World!") + +# Log a `message` representing dialogue with a speaker and content. +logger.chat({"name": "User", "content": "Hello, how are you?"}) +logger.chat({"name": "Agent", "content": "I'm fine, thank you!"}) +``` + +### Logging a System information + +System logs are crucial for tracking the application's state and identifying issues. Here's how to log different levels of system information: + +```python +# Log general information useful for understanding the flow of the application. +logger.info("The dialogue agent has started successfully.") + +# Log a warning message indicating a potential issue that isn't immediately problematic. +logger.warning("The agent is running slower than expected.") + +# Log an error message when something has gone wrong. +logger.error("The agent encountered an unexpected error while processing a request.") +``` + +## Integrating logging with WebUI + +To visualize these logs, we provide a customized gradio component in `src/agentscope/web_ui`. + +### Quick Running +For convince, we provide the pre-built app in a wheel file, you can run the WebUI in the following command: +```shell +pip install gradio_groupchat-0.0.1-py3-none-any.whl +python app.py +``` +After the init and entering the UI port printed by `app.py`, e.g., `http://127.0.0.1:7860/`, you can choose `demo_run.log` in the top-middle `FileSelector` window (it's a demo log file provided by us). Then, the dialog and system log should be shown correctly in the bottom windows. + +![webui](https://img.alicdn.com/imgextra/i2/O1CN01hSaFue1EdL2yCEznc_!!6000000000374-2-tps-3066-1808.png) + +### For Other Customization +To customize the backend, or the frontend of the provided WebUI, you can +```shell +# generate the template codes +# for network connectivity problem, try to run +# `npm config rm proxy && npm config rm https-proxy` first +gradio cc create GroupChat --template Chatbot +# replace the generated app.py into our built-in app.py +cp -f app.py groupchat/demo +# debug and develop your web_ui +cd groupchat +# edit the app.py, or other parts you want, reference link: +# https://www.gradio.app/guides/custom-components-in-five-minutes +gradio cc dev +``` + +If you want to release the modification, you can do +```shell +gradio cc build +pip install +python app.py +``` + + + +[[Return to the top]](#logging-and-webui) \ No newline at end of file diff --git a/docs/tutorial/201-agent.md b/docs/tutorial/201-agent.md new file mode 100644 index 000000000..03c371baf --- /dev/null +++ b/docs/tutorial/201-agent.md @@ -0,0 +1,176 @@ +# Customizing Your Own Agent + +This tutorial helps you to understand the `Agent` in mode depth and navigate through the process of crafting your own custom agent with AgentScope. We start by introducing the fundamental abstraction called `AgentBase`, which serves as the base class to maintain the general behaviors of all agents. Then, we will go through the *AgentPool*, an ensemble of pre-built, specialized agents, each designed with a specific purpose in mind. Finally, we will demonstrate how to customize your own agent, ensuring it fits the needs of your project. + +## Understanding `AgentBase` + +The `AgentBase` class is the architectural cornerstone for all agent constructs within the AgentScope. As the superclass of all custom agents, it provides a comprehensive template consisting of essential attributes and methods that underpin the core functionalities of any conversational agent. + +Each AgentBase derivative is composed of several key characteristics: + +* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/205-memory.md). + +* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). + +* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/206-prompt.md). + +In addition to these attributes, `AgentBase` endows agents with pivotal methods such as `observe` and `reply`: + +* `observe()`: Through this method, an agent can take note of `message` without immediately replying, allowing it to update its memory based on the observed `message`. +* `reply()`: This is the primary method that developers must implement. It defines the agent's behavior in response to an incoming `message`, encapsulating the logic that results in the agent's output. + +Besides, for unified interfaces and type hints, we introduce another base class `Operator`, which indicates performing some operation on input data by the `__call__` function. And we make `AgentBase` a subclass of `Operator`. + + +```python +class AgentBase(Operator): + # ... [code omitted for brevity] + + def __init__( + self, + name: str, + config: Optional[dict] = None, + sys_prompt: Optional[str] = None, + model: Optional[Union[Callable[..., Any], str]] = None, + use_memory: bool = True, + memory_config: Optional[dict] = None, + ) -> None: + + # ... [code omitted for brevity] + def observe(self, x: Union[dict, Sequence[dict]]) -> None: + # An optional method for updating the agent's internal state based on + # messages it has observed. This method can be used to enrich the + # agent's understanding and memory without producing an immediate + # response. + self.memory.add(x) + + def reply(self, x: dict = None) -> dict: + # The core method to be implemented by custom agents. It defines the + # logic for processing an input message and generating a suitable + # response. + raise NotImplementedError( + f"Agent [{type(self).__name__}] is missing the required " + f'"reply" function.', + ) + + # ... [code omitted for brevity] +``` + +## Exploring the AgentPool + +The *AgentPool* within AgentScope is a curated ensemble of ready-to-use, specialized agents. Each of these agents is tailored for a distinct role and comes equipped with default behaviors that address specific tasks. The *AgentPool* is designed to expedite the development process by providing various templates of `Agent `. + +Below is a table summarizing the functionality of some of the key agents available in the Agent Pool: + +| Agent Type | Description | Typical Use Cases | +| -------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | +| `AgentBase` | Serves as the superclass for all agents, providing essential attributes and methods. | The foundation for building any custom agent. | +| `RpcAgentBase` | Executes remote procedure calls in distributed mode. | The foundation for building any custom agent in distributed mode. | +| `DialogAgent` | Manages dialogues by understanding context and generating coherent responses. | Customer service bots, virtual assistants. | +| `UserAgent` | Interacts with the user to collect input, generating messages that may include URLs or additional specifics based on required keys. | Collecting user input for agents | +| *More to Come* | AgentScope is continuously expanding its pool with more specialized agents for diverse applications. | | + +## Customizing Agents from the AgentPool + +Customizing an agent from AgentPool enables you to tailor its functionality to meet the unique demands of your multi-agent application. You have the flexibility to modify existing agents with minimal effort by **adjusting configurations** and prompts or, for more extensive customization, you can engage in secondary development. + +Below, we provide usages of how to configure various agents from the AgentPool: + +### `DialogAgent` + +- **Reply Method**: The `reply` method is where the main logic for processing input `message` and generating responses. + +```python +def reply(self, x: dict = None) -> dict: + # Additional processing steps can occur here + + if x is not None: + self.memory.add(x) # Update the memory with the input + + # Generate a prompt for the language model using the system prompt and memory + prompt = self.engine.join(self.sys_prompt, self.memory.get_memory()) + + # Invoke the language model with the prepared prompt + response = self.model(prompt, parse_func=json.loads, fault_handler=lambda x: {"speak": x}) + + # Format the response and create a message object + msg = Msg(self.name, response.get("speak", None) or response, **response) + + # Record the message to memory and return it + self.memory.add(msg) + return msg +``` + +- **Usages:** To tailor a `DialogAgent` for a customer service bot: + +```python +from agentscope.agents import DialogAgent + +# Configuration for the DialogAgent +dialog_agent_config = { + "name": "ServiceBot", + "model": "gpt-3.5", # Specify the model used for dialogue generation + "sys_prompt": "Act as AI assistant to interact with the others. Try to " + "reponse on one line.\n", # Custom prompt for the agent + # Other configurations specific to the DialogAgent +} + +# Create and configure the DialogAgent +service_bot = DialogAgent(**dialog_agent_config) +``` + +### `UserAgent` + +- **Reply Method**: This method processes user input by prompting for content and if needed, additional keys and a URL. The gathered data is stored in a `message` object in the agent's memory for logging or later use and returns the message as a response. + +```python +def reply( + self, + x: dict = None, + required_keys: Optional[Union[list[str], str]] = None, +) -> dict: + # Check if there is initial data to be added to memory + if x is not None: + self.memory.add(x) + + content = input(f"{self.name}: ") # Prompt the user for input + kwargs = {} + + # Prompt for additional information based on the required keys + if required_keys is not None: + if isinstance(required_keys, str): + required_keys = [required_keys] + for key in required_keys: + kwargs[key] = input(f"{key}: ") + + # Optionally prompt for a URL if required + url = None + if self.require_url: + url = input("URL: ") + + # Create a message object with the collected input and additional details + msg = Msg(self.name, content=content, url=url, **kwargs) + + # Add the message object to memory + self.memory.add(msg) + return msg +``` + +- **Usages:** To configure a `UserAgent` for collecting user input and URLs (of file, image, video, audio , or website): + +```python +from agentscope.agents import UserAgent + +# Configuration for UserAgent +user_agent_config = { + "name": "User", + "require_url": True, # If true, the agent will require a URL +} + +# Create and configure the UserAgent +user_proxy_agent = UserAgent(**user_agent_config) +``` + + + +[[Return to the top]](#customizing-your-own-agent) \ No newline at end of file diff --git a/docs/tutorial/202-pipeline.md b/docs/tutorial/202-pipeline.md new file mode 100644 index 000000000..cf776ea24 --- /dev/null +++ b/docs/tutorial/202-pipeline.md @@ -0,0 +1,285 @@ +# Agent Interactions: Dive deeper into Pipelines and Message Hub + +**Pipeline & MsgHub** (message hub) are one or a sequence of steps describing how the structured `Message` passes between multi-agents, which streamlines the process of collaboration across agents. + +`Pipeline` allows users to program communication among agents easily, and `MsgHub` enables message sharing among agents like a group chat. + +## Pipelines + +`Pipeline` in AgentScope serves as conduits through which messages pass among agents. In AgentScope, an `Agent` is a subclass of an `Operator` that performs some operation on input data. Pipelines extend this concept by encapsulating multiple agents, and also act as an `Operator`. + +Here is the base class for all pipeline types: + +```python +class PipelineBase(Operator): + """Base interface of all pipelines.""" + # ... [code omitted for brevity] + @abstractmethod + def __call__(self, x: Optional[dict] = None) -> dict: + """Define the actions taken by this pipeline. + + Args: + x (Optional[`dict`], optional): + Dialog history and some environmental information + + Returns: + `dict`: The pipeline's response to the input. + """ +``` + +### Category + +AgentScope provides two main types of pipelines based on their implementation strategy: + +* **Operator-Type Pipelines** + + * These pipelines are object-oriented and inherit from the `PipelineBase`. They are operators themselves and can be combined with other operators to create complex interaction patterns. + + ```python + # Instantiate and invoke + pipeline = ClsPipeline(agent1, agent2, agent3) + x = pipeline(x) + ``` + +* **Functional Pipelines** + + * Functional pipelines provide similar control flow mechanisms as the class-based pipelines but are implemented as standalone functions. These are useful for scenarios where a class-based setup may not be necessary or preferred. + + ```python + # Just invoke + x = funcpipeline(x, agent1, agent2, agent3) + ``` + +Pipelines are categorized based on their functionality, much like programming language constructs. The table below outlines the different pipelines available in AgentScope: + +| Operator-Type Pipeline | Functional Pipeline | Description | +| -------------------- | -------------------- | ------------------------------------------------------------ | +| `SequentialPipeline` | `sequentialpipeline` | Executes a sequence of operators in order, passing the output of one as the input to the next. | +| `IfElsePipeline` | `ifelsepipeline` | Implements conditional logic, executing one operator if a condition is true and another if it is false. | +| `SwitchPipeline` | `switchpipeline` | Facilitates multi-branch selection, executing an operator from a mapped set based on the evaluation of a condition. | +| `ForLoopPipeline` | `forlooppipeline` | Repeatedly executes an operator for a set number of iterations or until a specified break condition is met. | +| `WhileLoopPipeline` | `whilelooppipeline` | Continuously executes an operator as long as a given condition remains true. | +| - | `placeholder` | Acts as a placeholder in branches that do not require any operations in flow control like if-else/switch | + +### Usage + +This section illustrates how pipelines can simplify the implementation of logic in multi-agent applications by comparing the usage of pipelines versus approaches without pipelines. + +**Note：** Please note that in the examples provided below, we use the term `agent` to represent any instance that can act as an `_Operator`. This is for ease of understanding and to illustrate how pipelines orchestrate interactions between different operations. You can replace `agent` with any `_Operator`, thus allowing for a mix of `agent` and `pipeline` in practice. + +#### `SequentialPipeline` + +* Without pipeline: + + ``` + x = agent1(x) + x = agent2(x) + x = agent3(x) + ``` + +- Using pipeline: + + ```python + from agentscope.pipelines import SequentialPipeline + + pipe = SequentialPipeline([agent1, agent2, agent3]) + x = pipe(x) + ``` + +- Using functional pipeline: + + ```python + from agentscope.pipelines import sequentialpipeline + + x = sequentialpipeline(x, [agent1, agent2, agent3]) + ``` + +#### `IfElsePipeline` + +* Without pipeline: + + ```python + if condition(x): + x = agent1(x) + else: + x = agent2(x) + ``` + +- Using pipeline: + + ```python + from agentscope.pipelines import IfElsePipeline + + pipe = IfElsePipeline(condition, agent1, agent2) + x = pipe(x) + ``` + +- Using functional pipeline: + + ```python + from agentscope.functional import ifelsepipeline + + x = ifelsepipeline(x, condition, agent1, agent2) + ``` + +#### `SwitchPipeline` + +* Without pipeline: + + ```python + switch_result = condition(x) + if switch_result == case1: + x = agent1(x) + elif switch_result == case2: + x = agent2(x) + else: + x = default_agent(x) + ``` + +- Using pipeline: + + ```python + from agentscope.pipelines import SwitchPipeline + + case_operators = {case1: agent1, case2: agent2} + pipe = SwitchPipeline(condition, case_operators, default_agent) + x = pipe(x) + ``` + +- Using functional pipeline: + + ```python + from agentscope.functional import switchpipeline + + case_operators = {case1: agent1, case2: agent2} + x = switchpipeline(x, condition, case_operators, default_agent) + ``` + +#### `ForLoopPipeline` + +* Without pipeline: + + ```python + for i in range(max_iterations): + x = agent(x) + if break_condition(x): + break + ``` + +* Using pipeline: + + ```python + from agentscope.pipelines import ForLoopPipeline + + pipe = ForLoopPipeline(agent, max_iterations, break_condition) + x = pipe(x) + ``` + +* Using functional pipeline: + + ```python + from agentscope.functional import forlooppipeline + + x = forlooppipeline(x, agent, max_iterations, break_condition) + ``` + +#### `WhileLoopPipeline` + + * Without pipeline: + + ```python + while condition(x): + x = agent(x) + ``` + + * Using pipeline: + + ```python + from agentscope.pipelines import WhileLoopPipeline + + pipe = WhileLoopPipeline(agent, condition) + x = pipe(x) + ``` + + - Using functional pipeline: + + ```python + from agentscope.functional import whilelooppipeline + + x = whilelooppipeline(x, agent, condition) + ``` + +## MsgHub + +`MsgHub` is designed to manage dialogue among a group of agents, allowing for the sharing of messages. Through `MsgHub`, agents can broadcast messages to all other agents in the group with `broadcast`. + +Here is the core class for a `MsgHub`: + +```python +class MsgHubManager: + """MsgHub manager class for sharing dialog among a group of agents.""" + # ... [code omitted for brevity] + + def broadcast(self, msg: Union[dict, list[dict]]) -> None: + """Broadcast the message to all participants.""" + for agent in self.participants: + agent.observe(msg) + + def add(self, new_participant: Union[Sequence[AgentBase], AgentBase]) -> None: + """Add new participant into this hub""" + # ... [code omitted for brevity] + + def delete(self, participant: Union[Sequence[AgentBase], AgentBase]) -> None: + """Delete agents from participant.""" + # ... [code omitted for brevity] +``` + +### Usage + +#### Creating a MsgHub + +To create a `MsgHub`, instantiate a `MsgHubManager` by calling the `msghub` helper function with a list of participating agents. Additionally, you can supply an optional initial announcement that, if provided, will be broadcast to all participants upon initialization. + +```python +from agentscope.msg_hub import msghub + +# Initialize MsgHub with participating agents +hub_manager = msghub( + participants=[agent1, agent2, agent3], announcement=initial_announcement +) +``` + +#### Broadcast message in MsgHub + +The `MsgHubManager` can be used with a context manager to handle the setup and teardown of the message hub environment: + +```python +with msghub( + participants=[agent1, agent2, agent3], announcement=initial_announcement +) as hub: + # Agents can now broadcast and receive messages within this block + agent1() + agent2() + + # Or manually broadcast a message + hub.broadcast(some_message) + +``` + +Upon exiting the context block, the `MsgHubManager` ensures that each agent's audience is cleared, preventing any unintended message sharing outside of the hub context. + +#### Adding and Deleting Participants + +You can dynamically add or remove agents from the `MsgHub`: + +```python +# Add a new participant +hub.add(new_agent) + +# Remove an existing participant +hub.delete(existing_agent) +``` + + + +[[Return to the top]](#agent-interactions:-Dive-deeper-into-pipelines-and-message-hub) \ No newline at end of file diff --git a/docs/tutorial/203-model.md b/docs/tutorial/203-model.md new file mode 100644 index 000000000..e60ee9268 --- /dev/null +++ b/docs/tutorial/203-model.md @@ -0,0 +1,252 @@ +# Using Different Model Sources with Model API + +AgentScope allows for the integration of multi-modal models from various sources. The core step is the initialization process, where once initialized with a certain config, all agent instances globally select the appropriate model APIs based on the model name specified (e.g., `model='gpt-4'`): + +```python +import agentscope + +agentscope.init(model_configs=PATH_TO_MODEL_CONFIG) +``` + +where the model configs could be a list of dict: + +```json +[ + { + "type": "openai", + "name": "gpt-4", + "parameters": { + "api_key": "xxx", + "organization_id": "xxx", + "temperature": 0.0 + } + }, + { + "type": "openai_dall_e", + "name": "dall-e-3", + "parameters": { + "api_key": "xxx", + "organization_id": "xxx", + "size": "1024x1024" + } + } + // Additional models can be configured here +] +``` + +This allows users to configure the model once, enabling shared use across all agents within the multi-agent application. Here is a table outlining the supported APIs and the type of arguments required for each: + +| Model Usage | Type Argument in AgentScope | Supported APIs | +| -------------------- | ------------------ | ------------------------------------------------------------ | +| Text generation | `openai` | Standard OpenAI chat API, FastChat and vllm | +| Image generation | `openai_dall_e` | DALL-E API for generating images | +| Embedding | `openai_embedding` | API for text embeddings | +| General usages in POST | `post_api` | Huggingface/ModelScope Inference API, and customized post API | + +## Standard OpenAI API + +Our configuration is fully compatible with the Standard OpenAI API. For specific parameter configuration and usage guides, we recommend visiting their official website: [https://platform.openai.com/docs/api-reference/introduction](https://platform.openai.com/docs/api-reference/introduction). + +## Self-host Model API + +In AgentScope, in addition to OpenAI API, we also support open-source models with post-request API. In this document, we will introduce how to fast set up local model API serving with different inference engines. + +### Flask-based Model API Serving + +[Flask](https://github.com/pallets/flask) is a lightweight web application framework. It is easy to build a local model API serving with Flask. + +Here we provide two Flask examples with Transformers and ModelScope libraries, respectively. You can build your own model API serving with a few modifications. + +#### With Transformers Library + +##### Install Libraries and Set up Serving + +Install Flask and Transformers by following the command. + +```bash +pip install Flask, transformers +``` + +Taking model `meta-llama/Llama-2-7b-chat-hf` and port `8000` as an example, set up the model API serving by running the following command. +```bash +python flask_transformers/setup_hf_service.py + --model_name_or_path meta-llama/Llama-2-7b-chat-hf + --device "cuda:0" # or "cpu" + --port 8000 +``` + +You can replace `meta-llama/Llama-2-7b-chat-hf` with any model card in the huggingface model hub. + +##### How to use in AgentScope + +In AgentScope, you can load the model with the following model configs: `./flask_transformers/model_config.json`. + +```json +{ + "type": "post_api", + "name": "flask_llama2-7b-chat", + "api_url": "http://127.0.0.1:8000/llm/", + "json_args": { + "max_length": 4096, + "temperature": 0.5 + } +} +``` + +##### Note + +In this model serving, the messages from post requests should be in **STRING** format. You can use [templates for chat model](https://huggingface.co/docs/transformers/main/chat_templating) from *transformers* with a little modification based on `./flask_transformers/setup_hf_service.py`. + + +#### With ModelScope Library + +##### Install Libraries and Set up Serving + +Install Flask and modelscope by following the command. + +```bash +pip install Flask, modelscope +``` + +Taking model `modelscope/Llama-2-7b-ms` and port `8000` as an example, to set up the model API serving, run the following command. + +```bash +python flask_modelscope/setup_ms_service.py + --model_name_or_path modelscope/Llama-2-7b-ms + --device "cuda:0" # or "cpu" + --port 8000 +``` + +You can replace `modelscope/Llama-2-7b-ms` with any model card in modelscope model hub. + + +##### How to use AgentScope + +In AgentScope, you can load the model with the following model configs: `flask_modelscope/model_config.json`. + +```json +{ + "type": "post_api", + "name": "flask_llama2-7b-ms", + "api_url": "http://127.0.0.1:8000/llm/", + "json_args": { + "max_length": 4096, + "temperature": 0.5 + } +} +``` + +##### Note + +Similar to the example of transformers, the messages from post requests should be in **STRING format**. + + +### FastChat + +[FastChat](https://github.com/lm-sys/FastChat) is an open platform that provides a quick setup for model serving with OpenAI-compatible RESTful APIs. + +#### Install Libraries and Set up Serving + +To install FastChat, run + +```bash +pip install "fastchat[model_worker,webui]" +``` + +Taking model `meta-llama/Llama-2-7b-chat-hf` and port `8000` as an example, to set up model API serving, run the following command to set up model serving. + +```bash +bash fastchat_script/fastchat_setup.sh -m meta-llama/Llama-2-7b-chat-hf -p 8000 +``` + +#### Supported Models +Refer to [supported model list](https://github.com/lm-sys/FastChat/blob/main/docs/model_support.md#supported-models) of FastChat. + +#### How to use in AgentScope +Now you can load the model in AgentScope by the following model config: `fastchat_script/model_config.json`. +```json +{ + "type": "openai", + "name": "meta-llama/Llama-2-7b-chat-hf", + "api_key": "EMPTY", + "client_args": { + "base_url": "http://127.0.0.1:8000/v1/" + }, + "generate_args": { + "temperature": 0.5 + } +} +``` + +### vllm + +[vllm](https://github.com/vllm-project/vllm) is a high-throughput inference and serving engine for LLMs. + +#### Install Libraries and Set up Serving +To install vllm, run + +```bash +pip install vllm +``` + +Taking model `meta-llama/Llama-2-7b-chat-hf` and port `8000` as an example, to set up model API serving, run + +```bash +bash vllm_script/vllm_setup.sh -m meta-llama/Llama-2-7b-chat-hf -p 8000 +``` + +#### Supported models + +Please refer to the [supported models list](https://docs.vllm.ai/en/latest/models/supported_models.html) of vllm. + +#### How to use in AgentScope +Now you can load the model in AgentScope by the following model config: `vllm_script/model_config.json`. + +```json +{ + "type": "openai", + "name": "meta-llama/Llama-2-7b-chat-hf", + "api_key": "EMPTY", + "client_args": { + "base_url": "http://127.0.0.1:8000/v1/" + }, + "generate_args": { + "temperature": 0.5 + } +} +``` + + +## Model Inference API + +Both [Huggingface](https://huggingface.co/docs/api-inference/index) and [ModelScope](https://www.modelscope.cn) provide model inference API, which can be used with AgentScope post API model wrapper. +Taking `gpt2` in HuggingFace inference API as an example, you can use the following model config in AgentScope. + +```bash +{ + "type": "post_api", + "name": 'gpt2', + "headers": { + "Authorization": "Bearer {YOUR_API_TOKEN}" + } + "api_url": "https://api-inference.huggingface.co/models/gpt2" +} +``` + +## In-memory Models without API + +It is entirely possible to use models without setting up an API service. Here's an example of how to initialize an agent with a local model instance: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained(MODEL_NAME) +tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) +model.eval() +# Do remember to re-implement the `reply` method to tokenize `message`! +agent = YourAgent(name='agent', model=model, tokenizer=tokenizer) +``` + + + +[[Return to the top]](#using-different-model-sources-with-model-api) \ No newline at end of file diff --git a/docs/tutorial/204-service.md b/docs/tutorial/204-service.md new file mode 100644 index 000000000..7a185871a --- /dev/null +++ b/docs/tutorial/204-service.md @@ -0,0 +1,134 @@ +# Enhancing Agent Capabilities with Service Functions + +**Service functions**, often referred to simply as **Service**, constitute a versatile suite of utility tools that can be used to enhance the functionality of agents. A service is designed to perform a specific task like web search, code interpretation, or file processing. Services can be invoked by agents and other components for reuse across different scenarios. + +## ServiceResponse + +The design behind `Service` distinguishes them from typical Python functions. In scenarios where execution is failed, service functions do not raise exceptions within the program. Instead, they return a `ServiceResponse` (a sub-class of dict). + +```python +def demo_service() -> ServiceResponse: + #do some specifc actions + # ...... + res = ServiceResponse({status=status, content=content}) + return res + + +class ServiceResponse(dict): + """Used to wrap the execution results of the services""" + # ... [code omitted for brevity] + + def __init__( + self, + status: ServiceExecStatus, + content: Any, + ): + self.status = status + self.content = content +``` + +This object encapsulates `status` of the execution (`SUCCESS` or `ERROR`), which can indicate success or failure, and the `content`, which can either be the output of a successful execution or the error stack from a failure. + +Here's why this design is beneficial: + +- **Error Handling**: `Service` and `ServiceResponse` allows agents to flexibly handle errors. An agent can check the status of the response and decide on the next steps, whether to retry the operation, use fallback logic, or analyze the error stack and choose an appropriate strategy to make improvements. +- **Consistency**: Service functions provide a consistent interface for both successful outcomes and errors. This consistency simplifies the interaction model for agents that use these services. + +## Overview of Service Functions + +Below is a table outlining various service functions categorized by their primary domain. These services offer a range of capabilities to agents. + +| Service Scenario | Service Function Name | Description | +| --------------- | --------------------- | ------------------------------------------------------------ | +| Code | `execute_python_code` | Execute a string of Python code, optionally inside a Docker container. | +| Retrieval | `retrieve_from_list` | Retrieve specific items from a list based on given criteria. | +| SQL Query | `query_mysql` | Execute a SQL query against a MySQL database and return results. | +| | `query_sqlite` | Execute a SQL query against a SQLite database and return results. | +| | `query_mongodb` | Perform a query or operation against a MongoDB collection. | +| Text Processing | `summarization` | Summarize a block of text to highlight the main points with LLM. | +| Web Search | `web_search` | Perform a web search using a specified search engine (currently supports Google and Bing). | +| File | `create_file` | Create a new file at a specified path with optional initial content. | +| | `delete_file` | Delete a file specified by the file path. | +| | `move_file` | Move or rename a file from one path to another. | +| | `create_directory` | Create a new directory at a specified path. | +| | `delete_directory` | Delete a directory and all of its contents. | +| | `move_directory` | Move or rename a directory from one path to another. | +| | `read_text_file` | Read and return the contents of a text file. | +| | `write_text_file` | Write text content to a file at a specified path. | +| | `read_json_file` | Read and parse the contents of a JSON file. | +| | `write_json_file` | Serialize a Python object to JSON and write it to a file. | +| *More to Come* | | Additional service functions are being developed and will be added to enhance the capabilities of AgentScope further. | + +For details about each Service Function, please consult the API references, where the docstrings provide comprehensive information about the parameters, expected input formats, return types, and any additional options that can modify the behavior of the Service Function. + +## Usage + +In AgentScope, each Service Function comes with a meticulously crafted docstring and demonstrative test functions that provide detailed instructions on how to utilize it. To enhance the capabilities of your agents with these services, you can craft prompts for LLM to generate parameters for Service: + +By composing appropriate prompts that align with the information detailed in the Service Functions' docstrings, you can guide an LLM to generate responses that match the required parameters of a `Service`. + +```python +import json +import inspect +from agentscope.service import ServiceResponse +from agentscope.agents import AgentBase + + +def create_file(file_path: str, content: str = "") -> ServiceResponse: + """ + Create a file and write content to it. + + Args: + file_path (str): The path where the file will be created. + content (str): Content to write into the file. + + Returns: + ServiceResponse: where the boolean indicates success, and the + str contains an error message if any, including the error type. + """ + # ... [code omitted for brevity] + + +class YourAgent(AgentBase): + # ... [code omitted for brevity] + + def reply(self, x: dict = None) -> dict: + # ... [code omitted for brevity] + + # Construct the prompt for the agent to provide parameters in JSON + # format + prompt = ( + f"To complete the user request\n```{x['content']}```\n" + "Please provide the necessary parameters in JSON format for the " + "function:\n" + f"Function: {create_file.__name__}\n" + "Description: Create a file and write content to it.\n" + ) + + # Add details about the function parameters + sig = inspect.signature(create_file) + parameters = sig.parameters.items() + params_prompt = "\n".join( + f"- {name} ({param.annotation.__name__}): " + f"{'(default: ' + json.dumps(param.default) + ')'if param.default is not inspect.Parameter.empty else ''}" + for name, param in parameters + ) + prompt += params_prompt + + # Get the model response + model_response = self.model(prompt) + + # Parse the model response and call the create_file function + # Additional extraction functions might be necessary + try: + kwargs = json.loads(model_response.content) + create_file(**kwargs) + except: + # Error handling + pass + + # ... [code omitted for brevity] +``` + + +[[Return to the top]](#enhancing-agent-capabilities-with-service-functions) \ No newline at end of file diff --git a/docs/tutorial/205-memory.md b/docs/tutorial/205-memory.md new file mode 100644 index 000000000..0ea5aa586 --- /dev/null +++ b/docs/tutorial/205-memory.md @@ -0,0 +1,146 @@ +# Memory and Message Management + +**Message** represents individual pieces of information or interactions flowing between/within agents. **Memory** refers to the storage and retrieval of historical information and serves as the storage and management system for the messages. This allows the agent to remember past interactions, maintain context, and provide more coherent and relevant responses. + +## Understanding `MessageBase` and its subclasses + +### `MessageBase` + +`MessageBase` is designed to organize attributes of a message, like the agent's name, the content, and associated media URLs. It provides a structure that can be extended to create specific types of messages. + +```python +class MessageBase(dict): + def __init__( + self, + name: str, + content: Any, + url: Optional[Union[Sequence[str], str]] = None, + timestamp: Optional[str] = None, + **kwargs: Any, + ) -> None: + self.id = uuid4().hex + self.timestamp = timestamp or _get_timestamp() + self.name = name + self.content = content + self.url = url + self.update(kwargs) + + def to_str(self) -> str: + raise NotImplementedError + + def serialize(self) -> str: + raise NotImplementedError + + # ... [code omitted for brevity] +``` + +Here are the key attributes managed by the `MessageBase` class: + +- **`name`**: This attribute denotes the originator of the message. It's a critical piece of metadata, useful in scenarios where distinguishing between different speakers is necessary. +- **`content`**: The substance of the message itself. It can include text, structured data, or any other form of content that is relevant to the interaction and requires processing by the agent. +- **`url`**: An optional attribute that allows the message to be linked to external resources. These can be direct links to files, multi-modal data, or web pages. +- **`timestamp`**: A timestamp indicating when the message was created. +- **`id`**: Each message is assigned a unique identifier (ID) upon creation. + +### `Msg` + +The `Msg` ("Message") subclass extends `MessageBase` and represents a standard `message`. `Msg` provides concrete definitions for the `to_str` and `serialize` methods to enable string representation and serialization suitable for the agent's operational context. + +```python +class Msg(MessageBase): + # ... [code omitted for brevity] + + def to_str(self) -> str: + return f"{self.name}: {self.content}" + + def serialize(self) -> str: + return json.dumps({"__type": "Msg", **self}) + +# `Msg` logs +>> Someone: I should ... +``` + +### `Tht` + +The `Tht` ("Thought") subclass is a specialized form of `MessageBase` used for encapsulating processes of an agent's internal thought. The thought is not sent outwardly but is instead used internally by the agent. As with `Msg`, specific implementations of `Tht` will define `to_str` and `serialize` methods to handle the unique requirements of representing and serializing an agent's thoughts. + +```python +class Tht(MessageBase): + # ... [code omitted for brevity] + + def to_str(self) -> str: + return f"{self.name} thought: {self.content}" + + def serialize(self) -> str: + return json.dumps({"__type": "Tht", **self}) + +>> Someone thought: I should ... +``` + +## Understanding `MemoryBase` and its subclasses + +### `MemoryBase` + +`MemoryBase` is an abstract class that handles an agent's memory in a structured way. It defines operations for storing, retrieving, deleting, and manipulating `message`'s content. + +```python +class MemoryBase(ABC): + # ... [code omitted for brevity] + + def get_memory( + self, + return_type: PromptType = PromptType.LIST, + recent_n: Optional[int] = None, + filter_func: Optional[Callable[[int, dict], bool]] = None, + ) -> Union[list, str]: + raise NotImplementedError + + def add(self, memories: Union[list[dict], dict]) -> None: + raise NotImplementedError + + def delete(self, index: Union[Iterable, int]) -> None: + raise NotImplementedError + + def load( + self, + memories: Union[str, dict, list], + overwrite: bool = False, + ) -> None: + raise NotImplementedError + + def export( + self, + to_mem: bool = False, + file_path: Optional[str] = None, + ) -> Optional[list]: + raise NotImplementedError + + def clear(self) -> None: + raise NotImplementedError + + def size(self) -> int: + raise NotImplementedError +``` + +Here are the key methods of `MemoryBase`: + +- **`get_memory`**: This method is responsible for retrieving stored messages from the agent's memory. It can return these messages in different formats as specified by the `return_type`. The method can also retrieve a specific number of recent messages if `recent_n` is provided, and it can apply a filtering function (`filter_func`) to select messages based on custom criteria. +- **`add`**: This method is used to add a new `message` to the agent's memory. It can accept a single message or a list of messages. Each message is typically an instance of `MessageBase` or its subclasses. +- **`delete`**: This method enables the removal of messages from memory by their index (or indices if an iterable is provided). +- **`load`**: This method allows for the bulk loading of messages into the agent's memory from an external source. The `overwrite` parameter determines whether to clear the existing memory before loading the new set of messages. +- **`export`**: This method facilitates exporting the stored `message` from the agent's memory either to an external file (specified by `file_path`) or directly into the working memory of the program (if `to_mem` is set to `True`). +- **`clear`**: This method purges all `message` from the agent's memory, essentially resetting it. +- **`size`**: This method returns the number of messages currently stored in the agent's memory. + +### `TemporaryMemory` + +The `TemporaryMemory` class is a concrete implementation of `MemoryBase`, providing a memory store that exists during the runtime of an agent, which is used as the default memory type of agents. Besides all the behaviors from `MemoryBase`, the `TemporaryMemory` additionally provides methods for retrieval: + +- **`retrieve_by_embedding`**: Retrieves `messages` that are most similar to a query, based on their embeddings. It uses a provided metric to determine the relevance and can return the top `k` most relevant messages. +- **`get_embeddings`**: Return the embeddings for all messages in memory. If a message does not have an embedding and an embedding model is provided, it will generate and store the embedding for the message. + +For more details about the usage of `Memory` and `Message`, please refer to the API references. + + + +[[Return to the top]](#memory-and-message-management) \ No newline at end of file diff --git a/docs/tutorial/206-prompt.md b/docs/tutorial/206-prompt.md new file mode 100644 index 000000000..e678c5e38 --- /dev/null +++ b/docs/tutorial/206-prompt.md @@ -0,0 +1,64 @@ +# Prompt Engine + +**Prompt** is a crucial component in interacting with language models, especially when seeking to generate specific types of outputs or guide the model toward desired behaviors. This tutorial will guide you through the use of the `PromptEngine` class, which simplifies the process of crafting prompts for LLMs. + +## Understanding the `PromptEngine` Class + +The `PromptEngine` class provides a structured way to combine different components of a prompt, such as instructions, hints, dialogue history, and user inputs, into a format that is suitable for the underlying language model. + +### Key Features of PromptEngine: + +- **Model Compatibility**: It works with any `ModelWrapperBase` subclass. +- **Shrink Policy**: It offers two policies for handling prompts that exceed the maximum length: `ShrinkPolicy.TRUNCATE` to simply truncate the prompt, and `ShrinkPolicy.SUMMARIZE` to summarize part of the dialog history to save space. +- **Prompt Type**: It supports both string and list-style prompts, aligning with the model's preferred input format. + +### Initialization + +When creating an instance of `PromptEngine`, you can specify the target model and, optionally, the shrinking policy, the maximum length of the prompt, the prompt type, and a summarization model (could be the same as the target model). + +```python +model = OpenAIWrapper(...) +engine = PromptEngine(model) +``` + +### Joining Prompt Components + +The `join` method of `PromptEngine` provides a unified interface to handle an arbitrary number of components for constructing the final prompt. + +#### String Type Prompt + +If the model expects a string-type prompt, components are joined with a newline character: + +```python +system_prompt = "You're a helpful assistant." +memory = ... +hint_prompt = "Please respond in JSON format." + +prompt = engine.join(system_prompt, memory, hint_prompt) +``` + +#### List Type Prompt + +For models that work with list-type prompts, components are converted to Message objects: + +```python +system_prompt = "You're a helpful assistant." +user_messages = [{"name": "user", "content": "What's the weather like today?"}] + +prompt = engine.join(system_prompt, user_messages) +``` + +### Formatting Prompts + +The `PromptEngine` supports dynamic prompts using the `format_map` parameter, allowing you to inject variables into the prompt components: + +```python +variables = {"location": "London"} +hint_prompt = "Find the weather in {location}." + +prompt = engine.join(system_prompt, user_input, hint_prompt, format_map=variables) +``` + + + +[[Return to the top]](#prompt-engine) \ No newline at end of file diff --git a/docs/tutorial/207-monitor.md b/docs/tutorial/207-monitor.md new file mode 100644 index 000000000..5ec57a0b9 --- /dev/null +++ b/docs/tutorial/207-monitor.md @@ -0,0 +1,100 @@ +# Monitor + +In multi-agent applications, particularly those that rely on external model APIs, it's crucial to monitor the usage and cost to prevent overutilization and ensure compliance with rate limits. The `MonitorBase` class and its implementation, `DictMonitor`, provide a way to track and regulate the usage of such APIs in your applications. In this tutorial, you'll learn how to use them to monitor API calls. + +## Understanding the `MonitorBase` Class + +The `MonitorBase` class serves as an interface for setting up a monitoring system that tracks various metrics, especially focusing on API usage. It defines methods that enable registration, checking, updating, and management of metrics related to API calls. + +Here are the key methods of `MonitorBase`: + +- **`register`**: Initializes a metric for tracking, such as the number of API calls made, with an optional quota to enforce limits. +- **`exists`**: Checks whether a metric is already being tracked. +- **`add`**: Increments the metric by a specified value, used to count each API call made. +- **`update`**: Updates multiple metrics at once, useful for batching updates. +- **`clear`**: Resets a metric to zero, which can be useful when the quota period resets. +- **`remove`**: Removes a metric from monitoring. +- **`get_value`**: Retrieves the current count for a particular metric. +- **`get_unit`**: Fetches the unit associated with the metric (e.g., "calls"). +- **`get_quota`**: Obtains the maximum number of allowed API calls. +- **`set_quota`**: Adjusts the quota for a metric, if the terms of API usage change. +- **`get_metric`**: Returns detailed information about a specific metric. +- **`get_metrics`**: Retrieves information about all tracked metrics, with optional filtering based on metric names. + +## Using the `DictMonitor` Class + +The `DictMonitor` class is a subclass of the `MonitorBase` class, which is implemented in an in-memory dictionary. + +### Initializing DictMonitor + +Create an instance of `DictMonitor` to begin monitoring: + +```python +monitor = DictMonitor() +``` + +### Registering API Usage Metrics + +Register a new metric to start monitoring the number of tokens: + +```python +monitor.register("token_num", metric_unit="token", quota=1000) +``` + +### Updating Metrics + +Increment the `token_num` metric: + +```python +monitor.add("token_num", 20) +``` + +### Handling Quotas + +If the number of API calls exceeds the quota, a `QuotaExceededError` will be thrown: + +```python +try: + monitor.add("api_calls", amount) +except QuotaExceededError as e: + # Handle the exceeded quota, e.g., by pausing API calls + print(e.message) +``` + +### Retrieving Metrics + +Get the current number of tokens used: + +```python +api_usage = monitor.get_value("token_num") +``` + +### Resetting and Removing Metrics + +Reset the number of token count at the start of a new period: + +```python +monitor.clear("token_num") +``` + +Remove the metric if it's no longer needed: + +```python +monitor.remove("token_num") +``` + +## Using Singleton Access + +`MonitorFactory` provides a singleton instance of a `MonitorBase` to ensure consistent access throughout your application. + +### Acquiring the Singleton Monitor Instance + +Get the singleton instance of the monitor: + +```python +monitor = MonitorFactory.get_monitor() +``` + + + +[[Return to the top]](#monitoring-and-logging) \ No newline at end of file diff --git a/docs/tutorial/208-distribute.md b/docs/tutorial/208-distribute.md new file mode 100644 index 000000000..fa1a28321 --- /dev/null +++ b/docs/tutorial/208-distribute.md @@ -0,0 +1,147 @@ +# Make Your Applications Distributed + +AgentScope is designed to be fully distributed, agent instances in one application can be deployed on different machines and run in parallel. This tutorial will introduce the features of AgentScope distributed and the distributed deployment method. + +## Features + +### Every agent is an "Actor" + +[The actor model](https://en.wikipedia.org/wiki/Actor_model) is a popular concept in concurrent programming and adopted by AgentScope. Every agent is an actor and interacts with other agents through messages. The flow of messages implies the execution order of the agent. Each agent has a `reply` method that consumes a message and generates another message, and the generated message can be sent to other agents. For example, the figure below shows the workflow of multiple agents. `A` to `F` are all agents, and the arrows represent messages. + +```mermaid +graph LR; +A-->B +A-->C +B-->D +C-->D +E-->F +D-->F +``` + +Among them, `B` and `C` can start execution simultaneously after receiving the message from `A`, and `E` can run immediately without waiting for `A`, `B`, `C,` and `D`. +By implementing each agent as an actor, an agent will automatically wait for its input `Message` before starting to execute the reply method, and multiple agents can also automatically execute `reply` at the same time if their input messages are ready, which avoids complex parallel control and makes things simple. + +### Write centrally, run distributedly + +In AgentScope, agents can be started as separate processes on the same or different machines. However, application developers do not need to pay attention to where these agents are running; you only need to write application code in the main process using the procedural programming paradigm. AgentScope will help you convert the task into a distributed version. The following is a piece of application code: `A`, `B`, and `C` are running on different machines. + +``` +x = A() +y = B(x) +z = C(x) +``` + +Although this code appears to be executed completely sequentially, AgentScope will **automatically detect potential parallelism** in your code as shown in the flow graph below, which means `C` will not wait for `B` to complete before starting execution. + +```mermaid +graph LR; +A-->B +A-->C +``` + +## Easy Distributed Deployment + +Please follow the steps below to deploy your application distributedly. + +### Write your agents + +To use distributed functionality, your agent class needs to inherit from `RpcAgentBase`. +`RpcAgentBase` requires several additional parameters compared to `AgentBase` during initialization. + +- `host`: the hostname or IP address of the machine where the agent runs, defaults to `localhost`. +- `port`: the port of this agent's RPC server, defaults to `80`. +- `launch_server`: whether to launch an RPC server locally, defaults to `True`. +- `local_mode`: set to `True` if all agents run on the same machine, defaults to `True`. + +But don't worry, `RpcAgentBase` shares the same interface as `AgentBase`, you only need to implement the `reply` method. You can even copy the `reply` method of an `AgentBase` subclass and use it in `RpcAgentBase`. + +### Run in multi-process mode + +AgentScope supports deployment in multi-process mode, where each agent is a sub-process of the application's main process, and all agents run on the same machine. +Its usage is very similar to single-process mode. The only difference lies in the initialization phase. + +Suppose you have classes `A` and `B`, both of which inherit from `RpcAgentBase`. +You can run the application in multi-process mode by passing in an additional parameter `port`, the other parts are completely the same as the single-process mode. + +```python +# import packages + +a = A( + name="A", + ..., + port=12001, # port is required, other fields like host, launch_server and local_mode use the default value +) +b = B( + name="B", + ..., + port=12002, # port is required +) + +x = None +while x is None or x.content != 'exit': + x = a(x) + x = b(x) +``` + +### Run on multiple machines + +AgentScope also supports to run agents on multiple machines. In this case, you need to start agents separately. For example, you can use the following code to start agent `A` on the machine with IP address `ip_a`. + +```python +# import packages + +server_a = RpcAgentServerLauncher( + name="A", + ..., + host=ip_a, + port=12001, + local_mode=False, +) +server_a.launch() +server_a.wait_until_terminate() +``` + +Similarly, you can start agent `B` on the machine with IP address `ip_b`. +Please make sure that the two machines can access each other using the IP addresses. + +```python +# import packages + +server_b = RpcAgentServerLauncher( + name="B", + ..., + host=ip_b, + port=12001, + local_mode=False, +) +server_b.launch() +server_b.wait_until_terminate() +``` + +Then, you can run the application's main process on any machine that can access `ip_a` and `ip_b`. + +```python +# import packages + +a = A( + name="A", + ..., + host=ip_a, + port=12001, + launch_server=False, +) +b = B( + name="B", + ..., + host=ip_b, + port=12002, + launch_server=False, +) + +x = None +while x is None or x.content != 'exit': + x = a(x) + x = b(x) +``` + +[[Return to the top]](#make-your-applications-distributed) \ No newline at end of file diff --git a/docs/tutorial/301-community.md b/docs/tutorial/301-community.md new file mode 100644 index 000000000..c4cae8faf --- /dev/null +++ b/docs/tutorial/301-community.md @@ -0,0 +1,34 @@ +# Joining The AgentScope Community + +Becoming a part of the AgentScope community allows you to connect with other users and developers. You can share insights, ask questions, and keep up-to-date with the latest developments and interesting multi-agent applications. Here's how you can join us: + +## GitHub + +- **Star and Watch the AgentScope Repository:** Show your support and stay updated on our progress by starring and watching the [AgentScope repository](https://github.com/alibaba/AgentScope). +- **Submit Issues and Pull Requests:** If you encounter any problems or have suggestions, submit an issue to the relevant repository. We also welcome pull requests for bug fixes, improvements, or new features. + +## Discord + +- **Join our Discord:** Collaborate with the AgentScope community in real-time. Engage in discussions, seek assistance, and share your experiences and insights on [Discord](https://discord.gg/Fwg5hZ2S). + +## DingTalk (钉钉) + +- **Connect on DingTalk:** We are also available on DingTalk. Join our group to chat, and stay informed about AgentScope-related news and updates. + + Scan the QR code below on DingTalk to join: + + AgentScope-logo + + Our DingTalk group invitation: [AgentScope DingTalk Group](https://qr.dingtalk.com/action/joingroup?code=v1,k1,20IUyRX5XZQ2vWjKDsjvI9dhcXjGZi3bq1pFfDZINCM=&_dt_no_comment=1&origin=11) + +## Wechat +Scan the QR code below on Wechat to join: AgentScope-wechat + +--- + +We welcome everyone interested in AgentScope to join our community and contribute to the growth of the platform! + + + +[[Return to the top]](#joining-the-agentscope-community) + diff --git a/docs/tutorial/302-contribute.md b/docs/tutorial/302-contribute.md new file mode 100644 index 000000000..b33762323 --- /dev/null +++ b/docs/tutorial/302-contribute.md @@ -0,0 +1,69 @@ +# Contributing to AgentScope + +Our community thrives on the diverse ideas and contributions of its members. Whether you're fixing a bug, adding a new feature, improving the documentation, or adding examples, your help is welcome. Here's how you can contribute: + +## Report Bugs and Ask For New Features? + +Did you find a bug or have a feature request? Please first check the issue tracker to see if it has already been reported. If not, feel free to open a new issue. Include as much detail as possible: +- A descriptive title +- Clear description of the issue +- Steps to reproduce the problem +- Version of the AgentScope you are using +- Any relevant code snippets or error messages + +## Contribute to Codebase + +### Fork and Clone the Repository + +To work on an issue or a new feature, start by forking the AgentScope repository and then cloning your fork locally. + +```bash +git clone https://github.com/your-username/AgentScope.git +cd AgentScope +``` + +### Create a New Branch + +Create a new branch for your work. This helps keep proposed changes organized and separate from the `main` branch. + +```bash +git checkout -b your-feature-branch-name +``` + +### Making Changes + +With your new branch checked out, you can now make your changes to the code. Remember to keep your changes as focused as possible. If you're addressing multiple issues or features, it's better to create separate branches and pull requests for each. + +We provide a developer version with additional `pre-commit` hooks to perform format checks compared to the official version: + +```bash +# Install the developer version +pip install -e .[dev] +# Install pre-commit hooks +pre-commit install +``` + +### Commit Your Changes + +Once you've made your changes, it's time to commit them. Write clear and concise commit messages that explain your changes. + +```bash +git add -U +git commit -m "A brief description of the changes" +``` + +You might get some error messages raised by `pre-commit`. Please resolve them according to the error code and commit again. + +### Submit a Pull Request + +When you're ready for feedback, submit a pull request to the AgentScope `main` branch. In your pull request description, explain the changes you've made and any other relevant context. + +We will review your pull request. This process might involve some discussion, additional changes on your part, or both. + +### Code Review + +Wait for us to review your pull request. We may suggest some changes or improvements. Keep an eye on your GitHub notifications and be responsive to any feedback. + + + +[[Return to the top]](#contributing-to-agentScope) \ No newline at end of file diff --git a/docs/tutorial/advance.rst b/docs/tutorial/advance.rst new file mode 100644 index 000000000..fdabbee99 --- /dev/null +++ b/docs/tutorial/advance.rst @@ -0,0 +1,14 @@ +Advanced Exploration +=============== + +.. toctree:: + :maxdepth: 2 + + 201-agent.md + 202-pipeline.md + 203-model.md + 204-service.md + 205-memory.md + 206-prompt.md + 207-monitor.md + 208-distribute.md diff --git a/docs/tutorial/contribute.rst b/docs/tutorial/contribute.rst new file mode 100644 index 000000000..20a9bdfaa --- /dev/null +++ b/docs/tutorial/contribute.rst @@ -0,0 +1,8 @@ +Get Involved +=============== + +.. toctree:: + :maxdepth: 2 + + 301-community.md + 302-contribute.md \ No newline at end of file diff --git a/docs/tutorial/main.md b/docs/tutorial/main.md new file mode 100644 index 000000000..af03c2130 --- /dev/null +++ b/docs/tutorial/main.md @@ -0,0 +1,39 @@ +# Welcome to AgentScope Tutorial Hub + +AgentScope is an innovative multi-agent platform designed to empower developers to build multi-agent applications with ease, reliability, and high performance. It features three high-level capabilities: + +- **Easy-to-Use**: Programming in pure Python with various prebuilt components for immediate use, suitable for developers or users with different levels of customization requirements. + +- **High Robustness**: Supporting customized fault-tolerance controls and retry mechanisms to enhance application stability. + +- **Actor-Based Distribution**: Enabling developers to build distributed multi-agent applications in a centralized programming manner for streamlined development. + +## Tutorial Navigator + +### Getting Started + +- [Installation Guide](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/101-installation.md) +- [Fundamental Concepts](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md) +- [Getting Started with a Simple Example](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/103-example.md) +- [Crafting Your First Application](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/104-usecase.md) +- [Logging and WebUI](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/105-logging.md) + +### Advanced Exploration + +- [Customizing Your Own Agent](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/201-agent.md) +- [Agent Interactions: Dive deeper into Pipelines and Message Hub](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-pipeline.md) +- [Using Different Model Sources with Model API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md) +- [Enhancing Agent Capabilities with Service Functions](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/204-service.md) +- [Memory and Message Management](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/205-memory.md) +- [Prompt Engine](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/206-prompt.md) +- [Monitoring](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/207-monitor.md) +- [Distributed Deployment](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/208-distribute.md) + +### Getting Involved + +* [Joining The AgentScope Community](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/301-community.md) +* [Contributing to AgentScope](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/302-contribute.md) + +### API References + +Please refer to [[API References]](https://alibaba.github.io/agentscope/) for details. \ No newline at end of file diff --git a/docs/tutorial/quick_start.rst b/docs/tutorial/quick_start.rst new file mode 100644 index 000000000..71814dccf --- /dev/null +++ b/docs/tutorial/quick_start.rst @@ -0,0 +1,11 @@ +Getting Started +=============== + +.. toctree:: + :maxdepth: 2 + + 101-installation.md + 102-concepts.md + 103-example.md + 104-usecase.md + 105-logging.md \ No newline at end of file From df0931d9bcd53134c5f7a8aa318db8cb12f33789 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Wed, 17 Jan 2024 20:22:01 +0800 Subject: [PATCH 02/18] minor fix --- docs/tutorial/103-example.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md index 1ed8d6fcb..e80da0980 100644 --- a/docs/tutorial/103-example.md +++ b/docs/tutorial/103-example.md @@ -58,7 +58,7 @@ dialogAgent = DialogAgent(name="assistant", model="gpt-4") userAgent = UserAgent() ``` -**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-agent.md) for all available agents. +**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/201-agent.md) for all available agents. ## Step3: Agent Conversation From ab751efed23c78290b95e56183c15432aaf55ffe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 10:47:20 +0800 Subject: [PATCH 03/18] minor fix according to zhijianma's comments --- docs/tutorial/101-installation.md | 24 ++++++++++++------------ docs/tutorial/102-concepts.md | 2 +- docs/tutorial/103-example.md | 14 +++++++------- 3 files changed, 20 insertions(+), 20 deletions(-) diff --git a/docs/tutorial/101-installation.md b/docs/tutorial/101-installation.md index 8f0af849a..6b05879a0 100644 --- a/docs/tutorial/101-installation.md +++ b/docs/tutorial/101-installation.md @@ -33,6 +33,18 @@ source agentscope/bin/activate # On Windows use `agentscope\Scripts\activate` ### Installing AgentScope +#### Install with Pip + +If you prefer to install AgentScope from Pypi, you can do so easily using `pip`: + +```bash +# For centralized multi-agent applications +pip install agentscope +# For distributed multi-agent applications +pip install agentscope[distribute] # On Mac use `pip install agentscope\[distribute\]` +``` + + #### Install from Source For users who prefer to install AgentScope directly from the source code, follow these steps to clone the repository and install the platform in editable mode: @@ -50,18 +62,6 @@ pip install -e . pip install -e .[distribute] # On Mac use `pip install -e .\[distribute\]` ``` -#### Install with Pip - -If you prefer to install AgentScope from Pypi, you can do so easily using `pip`: - -```bash -# For centralized multi-agent applications -pip install agentscope -# For distributed multi-agent applications -pip install agentscope[distribute] # On Mac use `pip install agentscope\[distribute\]` -``` - - **Note**: The `[distribute]` option installs additional dependencies required for distributed applications. Remember to activate your virtual environment before running these commands. diff --git a/docs/tutorial/102-concepts.md b/docs/tutorial/102-concepts.md index a87228bfa..45579aa73 100644 --- a/docs/tutorial/102-concepts.md +++ b/docs/tutorial/102-concepts.md @@ -7,7 +7,7 @@ In this tutorial, you'll have an initial understanding of the **fundamental conc ## Essential Terms and Concepts * **Agent** refers to an autonomous entity capable of performing actions to achieve specific objectives (probably powered by LLMs). In AgentScope, an agent takes the message as input and generates a corresponding response message. Agents can interact with each other to simulate human-like behaviors (e.g., discussion or debate) and cooperate to finish complicated tasks (e.g., generate runnable and reliable code). -* **Message** is a carrier of communication information between agents. It encapsulates information that needs to be conveyed, such as instructions, multi-modal data, or status updates. In AgentScope, a message is a subclass of Python's dict with additional features for inter-agent communication, including fields such as `name` and `content` for identification and payload delivery. +* **Message** is a carrier of communication information among agents. It encapsulates information that needs to be conveyed, such as instructions, multi-modal data, or status updates. In AgentScope, a message is a subclass of Python's dict with additional features for inter-agent communication, including fields such as `name` and `content` for identification and payload delivery. * **Memory** refers to the structures (e.g., list-like memory, database-based memory) used to store and manage `Message` that agents need to remember and store. This can include chat history, knowledge, or other data that informs the agent's future actions. * **Service** is a collection of functionality tools (e.g., web search, code interpreter, file processing) that provide specific capabilities or processes that are independent of an agent's memory state. Services can be invoked by agents or other components and designed to be reusable across different scenarios. * **Pipeline** refers to the interaction order or pattern of agents in a task. AgentScope provides built-in `pipelines` to streamline the process of collaboration across multiple agents, such as `SequentialPipeline` and `ForLoopPipeline`. When a `Pipeline` is executed, the `message` passes from predecessors to successors with intermediate results for the task. diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md index e80da0980..f4ad609dd 100644 --- a/docs/tutorial/103-example.md +++ b/docs/tutorial/103-example.md @@ -6,12 +6,12 @@ AgentScope is a versatile platform for building and running multi-agent applicat Agent is the basic composition and communication unit in AgentScope. To initialize an model-based agent, you need to prepare your configs for avaliable models. AgentScope supports a variety of APIs for pre-trained models. Here is a table outlining the supported APIs and the type of arguments required for each: -| Model Usage | Type Argument in AgentScope | Supported APIs | -| -------------------- | ------------------ | ------------------------------------------------------------ | -| Text generation | `openai` | Standard OpenAI chat API, FastChat and vllm | -| Image generation | `openai_dall_e` | DALL-E API for generating images | -| Embedding | `openai_embedding` | API for text embeddings | -| General usages in POST | `post_api` | Huggingface/ModelScope Inference API, and customized post API | +| Model Usage | Type Argument in AgentScope | Supported APIs | +| -------------------- | ------------------ |-----------------------------------------------------------------------------| +| Text generation | `openai` | Standard *OpenAI* chat API, FastChat and vllm | +| Image generation | `openai_dall_e` | *DALL-E* API for generating images | +| Embedding | `openai_embedding` | API for text embeddings | +| General usages in POST | `post_api` | *Huggingface* and *ModelScope* Inference API, and other customized post API | Each API has its specific configuration requirements. For example, to configure an OpenAI API, you would need to fill out the following fields in the model config in a dict, a yaml file or a json file: @@ -33,7 +33,7 @@ You can register your configuration by calling AgentScope's initilization method import agentscope agentscope.init(model_configs="./openai_model_configs.json") -agentscope.init(model_configs="./modelscope_model_configs.json") # use openai and modelscope at the same time +agentscope.init(model_configs="./modelscope_model_configs.json") # init again to use openai and modelscope at the same time # or you can init once by passing a list of config dict # openai_cfg_dict = {...dict_filling...} From 1927d1ae7b1984f5676a3eae7619865a695c1559 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 11:27:12 +0800 Subject: [PATCH 04/18] minor fix according to zhijianma's comments --- docs/tutorial/102-concepts.md | 4 ++-- docs/tutorial/103-example.md | 15 ++++++--------- docs/tutorial/104-usecase.md | 4 ++-- docs/tutorial/105-logging.md | 2 +- docs/tutorial/201-agent.md | 16 ++++++++-------- docs/tutorial/202-pipeline.md | 2 +- docs/tutorial/203-model.md | 2 +- docs/tutorial/205-memory.md | 12 ++++++------ docs/tutorial/208-distribute.md | 2 +- src/agentscope/prompt.py | 4 ++-- src/agentscope/utils/tools.py | 2 +- 11 files changed, 31 insertions(+), 34 deletions(-) diff --git a/docs/tutorial/102-concepts.md b/docs/tutorial/102-concepts.md index 45579aa73..71e80e47a 100644 --- a/docs/tutorial/102-concepts.md +++ b/docs/tutorial/102-concepts.md @@ -8,9 +8,9 @@ In this tutorial, you'll have an initial understanding of the **fundamental conc * **Agent** refers to an autonomous entity capable of performing actions to achieve specific objectives (probably powered by LLMs). In AgentScope, an agent takes the message as input and generates a corresponding response message. Agents can interact with each other to simulate human-like behaviors (e.g., discussion or debate) and cooperate to finish complicated tasks (e.g., generate runnable and reliable code). * **Message** is a carrier of communication information among agents. It encapsulates information that needs to be conveyed, such as instructions, multi-modal data, or status updates. In AgentScope, a message is a subclass of Python's dict with additional features for inter-agent communication, including fields such as `name` and `content` for identification and payload delivery. -* **Memory** refers to the structures (e.g., list-like memory, database-based memory) used to store and manage `Message` that agents need to remember and store. This can include chat history, knowledge, or other data that informs the agent's future actions. +* **Memory** refers to the structures (e.g., list-like memory, database-based memory) used to store and manage `Msg` (Message) that agents need to remember and store. This can include chat history, knowledge, or other data that informs the agent's future actions. * **Service** is a collection of functionality tools (e.g., web search, code interpreter, file processing) that provide specific capabilities or processes that are independent of an agent's memory state. Services can be invoked by agents or other components and designed to be reusable across different scenarios. -* **Pipeline** refers to the interaction order or pattern of agents in a task. AgentScope provides built-in `pipelines` to streamline the process of collaboration across multiple agents, such as `SequentialPipeline` and `ForLoopPipeline`. When a `Pipeline` is executed, the `message` passes from predecessors to successors with intermediate results for the task. +* **Pipeline** refers to the interaction order or pattern of agents in a task. AgentScope provides built-in `pipelines` to streamline the process of collaboration across multiple agents, such as `SequentialPipeline` and `ForLoopPipeline`. When a `Pipeline` is executed, the *message* passes from predecessors to successors with intermediate results for the task. ## Code Structure diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md index f4ad609dd..7cbc93ed3 100644 --- a/docs/tutorial/103-example.md +++ b/docs/tutorial/103-example.md @@ -4,7 +4,7 @@ AgentScope is a versatile platform for building and running multi-agent applicat ## Step1: Prepare Model Configs -Agent is the basic composition and communication unit in AgentScope. To initialize an model-based agent, you need to prepare your configs for avaliable models. AgentScope supports a variety of APIs for pre-trained models. Here is a table outlining the supported APIs and the type of arguments required for each: +Agent is the basic composition and communication unit in AgentScope. To initialize a model-based agent, you need to prepare your configs for avaliable models. AgentScope supports a variety of APIs for pre-trained models. Here is a table outlining the supported APIs and the type of arguments required for each: | Model Usage | Type Argument in AgentScope | Supported APIs | | -------------------- | ------------------ |-----------------------------------------------------------------------------| @@ -32,13 +32,10 @@ You can register your configuration by calling AgentScope's initilization method ```python import agentscope -agentscope.init(model_configs="./openai_model_configs.json") -agentscope.init(model_configs="./modelscope_model_configs.json") # init again to use openai and modelscope at the same time - -# or you can init once by passing a list of config dict -# openai_cfg_dict = {...dict_filling...} -# modelscope_cfg_dict = {...dict_filling...} -# agentscope.init(model_configs=[openai_cfg_dict, modelscope_cfg_dict]) +# init once by passing a list of config dict +openai_cfg_dict = {...dict_filling...} +modelscope_cfg_dict = {...dict_filling...} +agentscope.init(model_configs=[openai_cfg_dict, modelscope_cfg_dict]) ``` @@ -62,7 +59,7 @@ userAgent = UserAgent() ## Step3: Agent Conversation -`Message` is the primary means of communication between agents in AgentScope. They are Python dictionaries comprising essential fields like the actual `content` of this message and the sender's `name`. Optionally, a message can include a `url` to either a local file (image, video or audio) or website. +"Message" is the primary means of communication between agents in AgentScope. They are Python dictionaries comprising essential fields like the actual `content` of this message and the sender's `name`. Optionally, a message can include a `url` to either a local file (image, video or audio) or website. ```python from agentscope.message import Msg diff --git a/docs/tutorial/104-usecase.md b/docs/tutorial/104-usecase.md index 63270b97d..b59e2cba5 100644 --- a/docs/tutorial/104-usecase.md +++ b/docs/tutorial/104-usecase.md @@ -1,6 +1,6 @@ # Crafting Your First Application -img +img Before diving into the advanced topics of AgentScope, in this tutorial, we will give you a glance at building a Werewolf application with out-of-the-box components of AgentScope. @@ -10,7 +10,7 @@ Let the adventure begin to unlock the potential of multi-agent applications with ## Getting Started -Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Message`, and `pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: * [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) * [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) diff --git a/docs/tutorial/105-logging.md b/docs/tutorial/105-logging.md index 55e50d93f..ab7ba369f 100644 --- a/docs/tutorial/105-logging.md +++ b/docs/tutorial/105-logging.md @@ -40,7 +40,7 @@ Logging chat messages helps keep a record of the conversation between agents. He # Log a simple string message. logger.chat("Hello World!") -# Log a `message` representing dialogue with a speaker and content. +# Log a `msg` representing dialogue with a speaker and content. logger.chat({"name": "User", "content": "Hello, how are you?"}) logger.chat({"name": "Agent", "content": "I'm fine, thank you!"}) ``` diff --git a/docs/tutorial/201-agent.md b/docs/tutorial/201-agent.md index 03c371baf..d525e8ddc 100644 --- a/docs/tutorial/201-agent.md +++ b/docs/tutorial/201-agent.md @@ -16,8 +16,8 @@ Each AgentBase derivative is composed of several key characteristics: In addition to these attributes, `AgentBase` endows agents with pivotal methods such as `observe` and `reply`: -* `observe()`: Through this method, an agent can take note of `message` without immediately replying, allowing it to update its memory based on the observed `message`. -* `reply()`: This is the primary method that developers must implement. It defines the agent's behavior in response to an incoming `message`, encapsulating the logic that results in the agent's output. +* `observe()`: Through this method, an agent can take note of *message* without immediately replying, allowing it to update its memory based on the observed *message*. +* `reply()`: This is the primary method that developers must implement. It defines the agent's behavior in response to an incoming *message*, encapsulating the logic that results in the agent's output. Besides, for unified interfaces and type hints, we introduce another base class `Operator`, which indicates performing some operation on input data by the `__call__` function. And we make `AgentBase` a subclass of `Operator`. @@ -40,13 +40,13 @@ class AgentBase(Operator): def observe(self, x: Union[dict, Sequence[dict]]) -> None: # An optional method for updating the agent's internal state based on # messages it has observed. This method can be used to enrich the - # agent's understanding and memory without producing an immediate + # agent's understanding and memory without producing an immediate # response. self.memory.add(x) - + def reply(self, x: dict = None) -> dict: # The core method to be implemented by custom agents. It defines the - # logic for processing an input message and generating a suitable + # logic for processing an input message and generating a suitable # response. raise NotImplementedError( f"Agent [{type(self).__name__}] is missing the required " @@ -72,13 +72,13 @@ Below is a table summarizing the functionality of some of the key agents availab ## Customizing Agents from the AgentPool -Customizing an agent from AgentPool enables you to tailor its functionality to meet the unique demands of your multi-agent application. You have the flexibility to modify existing agents with minimal effort by **adjusting configurations** and prompts or, for more extensive customization, you can engage in secondary development. +Customizing an agent from AgentPool enables you to tailor its functionality to meet the unique demands of your multi-agent application. You have the flexibility to modify existing agents with minimal effort by **adjusting configurations** and prompts or, for more extensive customization, you can engage in secondary development. Below, we provide usages of how to configure various agents from the AgentPool: ### `DialogAgent` -- **Reply Method**: The `reply` method is where the main logic for processing input `message` and generating responses. +- **Reply Method**: The `reply` method is where the main logic for processing input *message* and generating responses. ```python def reply(self, x: dict = None) -> dict: @@ -121,7 +121,7 @@ service_bot = DialogAgent(**dialog_agent_config) ### `UserAgent` -- **Reply Method**: This method processes user input by prompting for content and if needed, additional keys and a URL. The gathered data is stored in a `message` object in the agent's memory for logging or later use and returns the message as a response. +- **Reply Method**: This method processes user input by prompting for content and if needed, additional keys and a URL. The gathered data is stored in a *message* object in the agent's memory for logging or later use and returns the message as a response. ```python def reply( diff --git a/docs/tutorial/202-pipeline.md b/docs/tutorial/202-pipeline.md index cf776ea24..1a3d7c342 100644 --- a/docs/tutorial/202-pipeline.md +++ b/docs/tutorial/202-pipeline.md @@ -1,6 +1,6 @@ # Agent Interactions: Dive deeper into Pipelines and Message Hub -**Pipeline & MsgHub** (message hub) are one or a sequence of steps describing how the structured `Message` passes between multi-agents, which streamlines the process of collaboration across agents. +**Pipeline & MsgHub** (message hub) are one or a sequence of steps describing how the structured `Msg` passes between multi-agents, which streamlines the process of collaboration across agents. `Pipeline` allows users to program communication among agents easily, and `MsgHub` enables message sharing among agents like a group chat. diff --git a/docs/tutorial/203-model.md b/docs/tutorial/203-model.md index e60ee9268..9d9d31cc3 100644 --- a/docs/tutorial/203-model.md +++ b/docs/tutorial/203-model.md @@ -243,7 +243,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained(MODEL_NAME) tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) model.eval() -# Do remember to re-implement the `reply` method to tokenize `message`! +# Do remember to re-implement the `reply` method to tokenize *message*! agent = YourAgent(name='agent', model=model, tokenizer=tokenizer) ``` diff --git a/docs/tutorial/205-memory.md b/docs/tutorial/205-memory.md index 0ea5aa586..cdeba4f7e 100644 --- a/docs/tutorial/205-memory.md +++ b/docs/tutorial/205-memory.md @@ -44,7 +44,7 @@ Here are the key attributes managed by the `MessageBase` class: ### `Msg` -The `Msg` ("Message") subclass extends `MessageBase` and represents a standard `message`. `Msg` provides concrete definitions for the `to_str` and `serialize` methods to enable string representation and serialization suitable for the agent's operational context. +The `Msg` ("Message") subclass extends `MessageBase` and represents a standard *message*. `Msg` provides concrete definitions for the `to_str` and `serialize` methods to enable string representation and serialization suitable for the agent's operational context. ```python class Msg(MessageBase): @@ -81,7 +81,7 @@ class Tht(MessageBase): ### `MemoryBase` -`MemoryBase` is an abstract class that handles an agent's memory in a structured way. It defines operations for storing, retrieving, deleting, and manipulating `message`'s content. +`MemoryBase` is an abstract class that handles an agent's memory in a structured way. It defines operations for storing, retrieving, deleting, and manipulating *message*'s content. ```python class MemoryBase(ABC): @@ -125,11 +125,11 @@ class MemoryBase(ABC): Here are the key methods of `MemoryBase`: - **`get_memory`**: This method is responsible for retrieving stored messages from the agent's memory. It can return these messages in different formats as specified by the `return_type`. The method can also retrieve a specific number of recent messages if `recent_n` is provided, and it can apply a filtering function (`filter_func`) to select messages based on custom criteria. -- **`add`**: This method is used to add a new `message` to the agent's memory. It can accept a single message or a list of messages. Each message is typically an instance of `MessageBase` or its subclasses. +- **`add`**: This method is used to add a new *message* to the agent's memory. It can accept a single message or a list of messages. Each message is typically an instance of `MessageBase` or its subclasses. - **`delete`**: This method enables the removal of messages from memory by their index (or indices if an iterable is provided). - **`load`**: This method allows for the bulk loading of messages into the agent's memory from an external source. The `overwrite` parameter determines whether to clear the existing memory before loading the new set of messages. -- **`export`**: This method facilitates exporting the stored `message` from the agent's memory either to an external file (specified by `file_path`) or directly into the working memory of the program (if `to_mem` is set to `True`). -- **`clear`**: This method purges all `message` from the agent's memory, essentially resetting it. +- **`export`**: This method facilitates exporting the stored *message* from the agent's memory either to an external file (specified by `file_path`) or directly into the working memory of the program (if `to_mem` is set to `True`). +- **`clear`**: This method purges all *message* from the agent's memory, essentially resetting it. - **`size`**: This method returns the number of messages currently stored in the agent's memory. ### `TemporaryMemory` @@ -139,7 +139,7 @@ The `TemporaryMemory` class is a concrete implementation of `MemoryBase`, provid - **`retrieve_by_embedding`**: Retrieves `messages` that are most similar to a query, based on their embeddings. It uses a provided metric to determine the relevance and can return the top `k` most relevant messages. - **`get_embeddings`**: Return the embeddings for all messages in memory. If a message does not have an embedding and an embedding model is provided, it will generate and store the embedding for the message. -For more details about the usage of `Memory` and `Message`, please refer to the API references. +For more details about the usage of `Memory` and `Msg`, please refer to the API references. diff --git a/docs/tutorial/208-distribute.md b/docs/tutorial/208-distribute.md index fa1a28321..f494a1665 100644 --- a/docs/tutorial/208-distribute.md +++ b/docs/tutorial/208-distribute.md @@ -19,7 +19,7 @@ D-->F ``` Among them, `B` and `C` can start execution simultaneously after receiving the message from `A`, and `E` can run immediately without waiting for `A`, `B`, `C,` and `D`. -By implementing each agent as an actor, an agent will automatically wait for its input `Message` before starting to execute the reply method, and multiple agents can also automatically execute `reply` at the same time if their input messages are ready, which avoids complex parallel control and makes things simple. +By implementing each agent as an actor, an agent will automatically wait for its input `Msg` before starting to execute the reply method, and multiple agents can also automatically execute `reply` at the same time if their input messages are ready, which avoids complex parallel control and makes things simple. ### Write centrally, run distributedly diff --git a/src/agentscope/prompt.py b/src/agentscope/prompt.py index 736b94dc0..99dd86e5a 100644 --- a/src/agentscope/prompt.py +++ b/src/agentscope/prompt.py @@ -105,7 +105,7 @@ def join( accept any number and type of arguments. If prompt type is `PromptType.STRING`, the arguments will be joined by `"\\\\n"`. If prompt type is `PromptType.LIST`, the string arguments will be - converted to `Message` from `system`. + converted to `Msg` from `system`. """ # TODO: achieve the summarize function if self.prompt_type == PromptType.STRING: @@ -134,7 +134,7 @@ def join_to_str(self, *args: Any, format_map: Union[dict, None]) -> str: return prompt_str def join_to_list(self, *args: Any, format_map: Union[dict, None]) -> list: - """Join prompt components to a list of `Message` objects.""" + """Join prompt components to a list of `Msg` objects.""" prompt = [] for item in args: if isinstance(item, list): diff --git a/src/agentscope/utils/tools.py b/src/agentscope/utils/tools.py index a8186d0e1..e3177ce99 100644 --- a/src/agentscope/utils/tools.py +++ b/src/agentscope/utils/tools.py @@ -38,7 +38,7 @@ def _get_timestamp(format_: str = "%Y-%m-%d %H:%M:%S") -> str: def to_openai_dict(item: dict) -> dict: - """Convert `Message` to `dict` for OpenAI API.""" + """Convert `Msg` to `dict` for OpenAI API.""" clean_dict = {} if "name" in item: From 37ffc858760c0887ffbe831d8b51c291da54e348 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 11:34:06 +0800 Subject: [PATCH 05/18] linter applied --- docs/tutorial/201-agent.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/tutorial/201-agent.md b/docs/tutorial/201-agent.md index d525e8ddc..77d17bd1d 100644 --- a/docs/tutorial/201-agent.md +++ b/docs/tutorial/201-agent.md @@ -40,13 +40,13 @@ class AgentBase(Operator): def observe(self, x: Union[dict, Sequence[dict]]) -> None: # An optional method for updating the agent's internal state based on # messages it has observed. This method can be used to enrich the - # agent's understanding and memory without producing an immediate + # agent's understanding and memory without producing an immediate # response. self.memory.add(x) - + def reply(self, x: dict = None) -> dict: # The core method to be implemented by custom agents. It defines the - # logic for processing an input message and generating a suitable + # logic for processing an input message and generating a suitable # response. raise NotImplementedError( f"Agent [{type(self).__name__}] is missing the required " @@ -72,7 +72,7 @@ Below is a table summarizing the functionality of some of the key agents availab ## Customizing Agents from the AgentPool -Customizing an agent from AgentPool enables you to tailor its functionality to meet the unique demands of your multi-agent application. You have the flexibility to modify existing agents with minimal effort by **adjusting configurations** and prompts or, for more extensive customization, you can engage in secondary development. +Customizing an agent from AgentPool enables you to tailor its functionality to meet the unique demands of your multi-agent application. You have the flexibility to modify existing agents with minimal effort by **adjusting configurations** and prompts or, for more extensive customization, you can engage in secondary development. Below, we provide usages of how to configure various agents from the AgentPool: From a0a0e4d9af58142679068afae5a5ae7e482f7e98 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 12:00:31 +0800 Subject: [PATCH 06/18] fix according to xuchen's comments --- docs/sphinx_doc/source/index.rst | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/docs/sphinx_doc/source/index.rst b/docs/sphinx_doc/source/index.rst index 1b404003c..81b560322 100644 --- a/docs/sphinx_doc/source/index.rst +++ b/docs/sphinx_doc/source/index.rst @@ -8,6 +8,21 @@ AgentScope Documentation ====================================== + +.. include:: tutorial/main.md + :parser: myst_parser.sphinx_ + +.. toctree:: + :maxdepth: 1 + :glob: + :hidden: + :caption: AgentScope Tutorial + + tutorial/quick_start.rst + tutorial/advance.rst + tutorial/contribute.rst + + .. toctree:: :maxdepth: 2 :glob: @@ -23,16 +38,6 @@ AgentScope Documentation agentscope.utils agentscope.web_ui agentscope - -.. include:: tutorial/main.md - :parser: myst_parser.sphinx_ - -.. toctree:: - :maxdepth: 1 - :glob: - :hidden: - :caption: AgentScope Tutorial - Indices and tables ================== From f5d9391736eff32aa70c559c35b2a6cd48e36041 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 12:07:31 +0800 Subject: [PATCH 07/18] fix according to xuchen's comments --- docs/sphinx_doc/source/index.rst | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/sphinx_doc/source/index.rst b/docs/sphinx_doc/source/index.rst index 81b560322..ffcdd6791 100644 --- a/docs/sphinx_doc/source/index.rst +++ b/docs/sphinx_doc/source/index.rst @@ -9,7 +9,7 @@ AgentScope Documentation ====================================== -.. include:: tutorial/main.md +.. include:: ../../tutorial/main.md :parser: myst_parser.sphinx_ .. toctree:: @@ -18,9 +18,9 @@ AgentScope Documentation :hidden: :caption: AgentScope Tutorial - tutorial/quick_start.rst - tutorial/advance.rst - tutorial/contribute.rst + ../../tutorial/quick_start.rst + ../../tutorial/advance.rst + ../../tutorial/contribute.rst .. toctree:: From 340f24d9c34f345c0bb37c28b482a9abfda43f57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Thu, 18 Jan 2024 18:28:40 +0800 Subject: [PATCH 08/18] fix according to zhijianma's comments --- docs/tutorial/103-example.md | 2 +- docs/tutorial/104-usecase.md | 6 +++--- docs/tutorial/105-logging.md | 4 ++-- docs/tutorial/202-pipeline.md | 17 ++++++++++++++++- docs/tutorial/206-prompt.md | 14 ++++++++------ docs/tutorial/207-monitor.md | 2 +- 6 files changed, 31 insertions(+), 14 deletions(-) diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md index 7cbc93ed3..025a4e3b8 100644 --- a/docs/tutorial/103-example.md +++ b/docs/tutorial/103-example.md @@ -1,6 +1,6 @@ # Getting Started with a Simple Example -AgentScope is a versatile platform for building and running multi-agent applications. We provide various pre-built examples that will help you quickly understand how to create and use multi-agent for various applications. In this tutorial, you will learn to set up a **simple agent-based interaction**. +AgentScope is a versatile platform for building and running multi-agent applications. We provide various pre-built examples that will help you quickly understand how to create and use multi-agent for various applications. In this tutorial, you will learn how to set up a **simple agent-based interaction**. ## Step1: Prepare Model Configs diff --git a/docs/tutorial/104-usecase.md b/docs/tutorial/104-usecase.md index b59e2cba5..edcfa0c44 100644 --- a/docs/tutorial/104-usecase.md +++ b/docs/tutorial/104-usecase.md @@ -4,13 +4,13 @@ Before diving into the advanced topics of AgentScope, in this tutorial, we will give you a glance at building a Werewolf application with out-of-the-box components of AgentScope. -**Werewolf** is a well-known social-deduction game, that involves an imaginary village where a few villagers are secretly werewolves, and the objective is to find out who they are before they eliminate all other players. It's a good use case to demonstrate the interaction between multiple autonomous agents, each with its own objectives and the need for communication. +**Werewolf** is a well-known social-deduction game, that involves an imaginary village where a few villagers are secretly werewolves, and the objective is to identify who they are before they eliminate all other players. It's a good use case to demonstrate the interaction between multiple autonomous agents, each with its own objectives and the need for communication. Let the adventure begin to unlock the potential of multi-agent applications with AgentScope! ## Getting Started -Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: * [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) * [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) @@ -59,7 +59,7 @@ class MyAgent(AgentBase): return x ``` -AgentScope provides several out-of-box Agents implements and organizes them as an *Agent Pool*. In this application, we use a built-in agent, `DictDialogAgent`. Here we give an example configuration of `DictDialogAgent` for a player assigned as the role of a werewolf: +AgentScope provides several out-of-the-box Agents implements and organizes them as an *Agent Pool*. In this application, we use a built-in agent, `DictDialogAgent`. Here we give an example configuration of `DictDialogAgent` for a player assigned as the role of a werewolf: ```json { diff --git a/docs/tutorial/105-logging.md b/docs/tutorial/105-logging.md index ab7ba369f..cc87749bd 100644 --- a/docs/tutorial/105-logging.md +++ b/docs/tutorial/105-logging.md @@ -19,9 +19,9 @@ We recommend setting up the logger via `agentscope.init`, and you can set the lo import agentscope LOG_LEVEL = Literal[ + "CHAT", "TRACE", "DEBUG", - "CHAT", "INFO", "SUCCESS", "WARNING", @@ -70,7 +70,7 @@ For convince, we provide the pre-built app in a wheel file, you can run the WebU pip install gradio_groupchat-0.0.1-py3-none-any.whl python app.py ``` -After the init and entering the UI port printed by `app.py`, e.g., `http://127.0.0.1:7860/`, you can choose `demo_run.log` in the top-middle `FileSelector` window (it's a demo log file provided by us). Then, the dialog and system log should be shown correctly in the bottom windows. +After the init and entering the UI port printed by `app.py`, e.g., `http://127.0.0.1:7860/`, you can choose `run.log.demo` in the top-middle `FileSelector` window (it's a demo log file provided by us). Then, the dialog and system log should be shown correctly in the bottom windows. ![webui](https://img.alicdn.com/imgextra/i2/O1CN01hSaFue1EdL2yCEznc_!!6000000000374-2-tps-3066-1808.png) diff --git a/docs/tutorial/202-pipeline.md b/docs/tutorial/202-pipeline.md index 1a3d7c342..2bf9a44fa 100644 --- a/docs/tutorial/202-pipeline.md +++ b/docs/tutorial/202-pipeline.md @@ -209,6 +209,21 @@ This section illustrates how pipelines can simplify the implementation of logic x = whilelooppipeline(x, agent, condition) ``` +### Pipeline Combination +It's worth noting that AgentScope supports the combination of pipelines to create complex interactions. For example, we can create a pipeline that executes a sequence of agents in order, and then executes another pipeline that executes a sequence of agents in condition. +```python +from agentscope.pipelines import SequentialPipeline, ParallelPipeline +# Create a pipeline that executes agents in order +pipe1 = SequentialPipeline([agent1, agent2, agent3]) +# Create a pipeline that executes agents in parallel +pipe2 = IfElsePipeline(condition, agent4, agent5) +# Create a pipeline that executes pipe1 and pipe2 in order +pipe3 = SequentialPipeline([pipe1, pipe2]) +# Invoke the pipeline +x = pipe3(x) +``` + + ## MsgHub `MsgHub` is designed to manage dialogue among a group of agents, allowing for the sharing of messages. Through `MsgHub`, agents can broadcast messages to all other agents in the group with `broadcast`. @@ -282,4 +297,4 @@ hub.delete(existing_agent) -[[Return to the top]](#agent-interactions:-Dive-deeper-into-pipelines-and-message-hub) \ No newline at end of file +[[Return to the top]](#agent-interactions-dive-deeper-into-pipelines-and-message-hub) \ No newline at end of file diff --git a/docs/tutorial/206-prompt.md b/docs/tutorial/206-prompt.md index e678c5e38..56df050ef 100644 --- a/docs/tutorial/206-prompt.md +++ b/docs/tutorial/206-prompt.md @@ -25,32 +25,34 @@ engine = PromptEngine(model) The `join` method of `PromptEngine` provides a unified interface to handle an arbitrary number of components for constructing the final prompt. -#### String Type Prompt +#### Output String Type Prompt If the model expects a string-type prompt, components are joined with a newline character: ```python system_prompt = "You're a helpful assistant." -memory = ... +memory = ... # can be dict, list, or string hint_prompt = "Please respond in JSON format." prompt = engine.join(system_prompt, memory, hint_prompt) +# the result will be [ "You're a helpful assistant.", {"name": "user", "content": "What's the weather like today?"}] ``` -#### List Type Prompt +#### Output List Type Prompt -For models that work with list-type prompts, components are converted to Message objects: +For models that work with list-type prompts,e.g., OpenAI and Huggingface chat models, the components can be converted to Message objects, whose type is list of dict: ```python system_prompt = "You're a helpful assistant." user_messages = [{"name": "user", "content": "What's the weather like today?"}] prompt = engine.join(system_prompt, user_messages) +# the result should be: [{"role": "assistant", "content": "You're a helpful assistant."}, {"name": "user", "content": "What's the weather like today?"}] ``` -### Formatting Prompts +#### Formatting Prompts in Dynamic Way -The `PromptEngine` supports dynamic prompts using the `format_map` parameter, allowing you to inject variables into the prompt components: +The `PromptEngine` supports dynamic prompts using the `format_map` parameter, allowing you to flexibly inject various variables into the prompt components for different scenarios: ```python variables = {"location": "London"} diff --git a/docs/tutorial/207-monitor.md b/docs/tutorial/207-monitor.md index 5ec57a0b9..79f496af3 100644 --- a/docs/tutorial/207-monitor.md +++ b/docs/tutorial/207-monitor.md @@ -66,7 +66,7 @@ except QuotaExceededError as e: Get the current number of tokens used: ```python -api_usage = monitor.get_value("token_num") +token_num_used = monitor.get_value("token_num") ``` ### Resetting and Removing Metrics From 35e8a4cff139ee9d0f00893326b709c782870129 Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 11:17:16 +0800 Subject: [PATCH 09/18] fix pipeline tutorial --- docs/sphinx_doc/source/index.rst | 2 ++ docs/sphinx_doc/source/tutorial/main.md | 3 -- docs/tutorial/202-pipeline.md | 47 ++++++++++++------------- src/agentscope/pipelines/functional.py | 1 + 4 files changed, 26 insertions(+), 27 deletions(-) delete mode 100644 docs/sphinx_doc/source/tutorial/main.md diff --git a/docs/sphinx_doc/source/index.rst b/docs/sphinx_doc/source/index.rst index ffcdd6791..2ca7c496b 100644 --- a/docs/sphinx_doc/source/index.rst +++ b/docs/sphinx_doc/source/index.rst @@ -26,6 +26,7 @@ AgentScope Documentation .. toctree:: :maxdepth: 2 :glob: + :hidden: :caption: AgentScope API Reference agentscope.agents @@ -38,6 +39,7 @@ AgentScope Documentation agentscope.utils agentscope.web_ui agentscope + Indices and tables ================== diff --git a/docs/sphinx_doc/source/tutorial/main.md b/docs/sphinx_doc/source/tutorial/main.md deleted file mode 100644 index f0338300d..000000000 --- a/docs/sphinx_doc/source/tutorial/main.md +++ /dev/null @@ -1,3 +0,0 @@ -# AgentScope Tutorial - -Comming Soon diff --git a/docs/tutorial/202-pipeline.md b/docs/tutorial/202-pipeline.md index 2bf9a44fa..ebe23cd4d 100644 --- a/docs/tutorial/202-pipeline.md +++ b/docs/tutorial/202-pipeline.md @@ -12,7 +12,7 @@ Here is the base class for all pipeline types: ```python class PipelineBase(Operator): - """Base interface of all pipelines.""" + """Base interface of all pipelines.""" # ... [code omitted for brevity] @abstractmethod def __call__(self, x: Optional[dict] = None) -> dict: @@ -47,7 +47,7 @@ AgentScope provides two main types of pipelines based on their implementation st ```python # Just invoke - x = funcpipeline(x, agent1, agent2, agent3) + x = funcpipeline(agent1, agent2, agent3, x) ``` Pipelines are categorized based on their functionality, much like programming language constructs. The table below outlines the different pipelines available in AgentScope: @@ -65,19 +65,19 @@ Pipelines are categorized based on their functionality, much like programming la This section illustrates how pipelines can simplify the implementation of logic in multi-agent applications by comparing the usage of pipelines versus approaches without pipelines. -**Note：** Please note that in the examples provided below, we use the term `agent` to represent any instance that can act as an `_Operator`. This is for ease of understanding and to illustrate how pipelines orchestrate interactions between different operations. You can replace `agent` with any `_Operator`, thus allowing for a mix of `agent` and `pipeline` in practice. +**Note：** Please note that in the examples provided below, we use the term `agent` to represent any instance that can act as an `Operator`. This is for ease of understanding and to illustrate how pipelines orchestrate interactions between different operations. You can replace `agent` with any `Operator`, thus allowing for a mix of `agent` and `pipeline` in practice. #### `SequentialPipeline` * Without pipeline: - ``` + ```python x = agent1(x) x = agent2(x) x = agent3(x) ``` -- Using pipeline: +* Using pipeline: ```python from agentscope.pipelines import SequentialPipeline @@ -86,12 +86,12 @@ This section illustrates how pipelines can simplify the implementation of logic x = pipe(x) ``` -- Using functional pipeline: +* Using functional pipeline: ```python from agentscope.pipelines import sequentialpipeline - x = sequentialpipeline(x, [agent1, agent2, agent3]) + x = sequentialpipeline([agent1, agent2, agent3], x) ``` #### `IfElsePipeline` @@ -105,7 +105,7 @@ This section illustrates how pipelines can simplify the implementation of logic x = agent2(x) ``` -- Using pipeline: +* Using pipeline: ```python from agentscope.pipelines import IfElsePipeline @@ -114,12 +114,12 @@ This section illustrates how pipelines can simplify the implementation of logic x = pipe(x) ``` -- Using functional pipeline: +* Using functional pipeline: ```python from agentscope.functional import ifelsepipeline - x = ifelsepipeline(x, condition, agent1, agent2) + x = ifelsepipeline(condition, agent1, agent2, x) ``` #### `SwitchPipeline` @@ -136,7 +136,7 @@ This section illustrates how pipelines can simplify the implementation of logic x = default_agent(x) ``` -- Using pipeline: +* Using pipeline: ```python from agentscope.pipelines import SwitchPipeline @@ -146,13 +146,13 @@ This section illustrates how pipelines can simplify the implementation of logic x = pipe(x) ``` -- Using functional pipeline: +* Using functional pipeline: ```python from agentscope.functional import switchpipeline case_operators = {case1: agent1, case2: agent2} - x = switchpipeline(x, condition, case_operators, default_agent) + x = switchpipeline(condition, case_operators, default_agent, x) ``` #### `ForLoopPipeline` @@ -180,19 +180,19 @@ This section illustrates how pipelines can simplify the implementation of logic ```python from agentscope.functional import forlooppipeline - x = forlooppipeline(x, agent, max_iterations, break_condition) + x = forlooppipeline(agent, max_iterations, break_condition, x) ``` #### `WhileLoopPipeline` - * Without pipeline: +* Without pipeline: ```python while condition(x): x = agent(x) ``` - * Using pipeline: +* Using pipeline: ```python from agentscope.pipelines import WhileLoopPipeline @@ -201,16 +201,18 @@ This section illustrates how pipelines can simplify the implementation of logic x = pipe(x) ``` - - Using functional pipeline: +* Using functional pipeline: ```python from agentscope.functional import whilelooppipeline - x = whilelooppipeline(x, agent, condition) + x = whilelooppipeline(agent, condition, x) ``` ### Pipeline Combination + It's worth noting that AgentScope supports the combination of pipelines to create complex interactions. For example, we can create a pipeline that executes a sequence of agents in order, and then executes another pipeline that executes a sequence of agents in condition. + ```python from agentscope.pipelines import SequentialPipeline, ParallelPipeline # Create a pipeline that executes agents in order @@ -223,7 +225,6 @@ pipe3 = SequentialPipeline([pipe1, pipe2]) x = pipe3(x) ``` - ## MsgHub `MsgHub` is designed to manage dialogue among a group of agents, allowing for the sharing of messages. Through `MsgHub`, agents can broadcast messages to all other agents in the group with `broadcast`. @@ -241,11 +242,11 @@ class MsgHubManager: agent.observe(msg) def add(self, new_participant: Union[Sequence[AgentBase], AgentBase]) -> None: - """Add new participant into this hub""" + """Add new participant into this hub""" # ... [code omitted for brevity] def delete(self, participant: Union[Sequence[AgentBase], AgentBase]) -> None: - """Delete agents from participant.""" + """Delete agents from participant.""" # ... [code omitted for brevity] ``` @@ -295,6 +296,4 @@ hub.add(new_agent) hub.delete(existing_agent) ``` - - -[[Return to the top]](#agent-interactions-dive-deeper-into-pipelines-and-message-hub) \ No newline at end of file +[[Return to the top]](#agent-interactions-dive-deeper-into-pipelines-and-message-hub) diff --git a/src/agentscope/pipelines/functional.py b/src/agentscope/pipelines/functional.py index 06f470326..042d1b6c4 100644 --- a/src/agentscope/pipelines/functional.py +++ b/src/agentscope/pipelines/functional.py @@ -5,6 +5,7 @@ from typing import Mapping from ..agents.operator import Operator +# A single Operator or a Sequence of Operators Operators = Union[Operator, Sequence[Operator]] From 35bea957d0838acddb95267d8e5b07f1d558d4bb Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 11:49:14 +0800 Subject: [PATCH 10/18] update doc workflow --- .github/workflows/sphinx_docs.yml | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/workflows/sphinx_docs.yml b/.github/workflows/sphinx_docs.yml index 117c22efd..1caa2a3c2 100644 --- a/.github/workflows/sphinx_docs.yml +++ b/.github/workflows/sphinx_docs.yml @@ -1,6 +1,10 @@ name: Deploy Sphinx documentation to Pages on: + pull_request: + types: [opened, synchronize] + paths: + - 'docs/**/*' release: types: [published] @@ -12,7 +16,8 @@ jobs: OS: ${{ matrix.os }} PYTHON: '3.9' steps: - - uses: actions/checkout@master + - name: Checkout repository + uses: actions/checkout@master - name: Setup Python ${{ matrix.python-version }} uses: actions/setup-python@master with: @@ -25,6 +30,7 @@ jobs: publish: false requirements_path: ./docs/sphinx_doc/requirements.txt - uses: peaceiris/actions-gh-pages@v3 + if: github.event_name == 'release' with: github_token: ${{ secrets.GITHUB_TOKEN }} publish_dir: ${{ steps.deployment.outputs.artifact }} \ No newline at end of file From e5099cc9ca954607fb578c2b29bb6a94b7aa2665 Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 11:59:00 +0800 Subject: [PATCH 11/18] update doc workflow --- .github/workflows/sphinx_docs.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.github/workflows/sphinx_docs.yml b/.github/workflows/sphinx_docs.yml index 1caa2a3c2..130733140 100644 --- a/.github/workflows/sphinx_docs.yml +++ b/.github/workflows/sphinx_docs.yml @@ -23,12 +23,18 @@ jobs: with: python_version: ${{ matrix.python-version }} - id: deployment + name: Build Documentation uses: sphinx-notes/pages@v3 with: documentation_path: ./docs/sphinx_doc/source python_version: ${{ matrix.python-version }} publish: false requirements_path: ./docs/sphinx_doc/requirements.txt + - name: Upload Documentation + uses: actions/upload-artifact@v3 + with: + name: SphinxDoc + path: docs/sphinx_doc/build/html/ - uses: peaceiris/actions-gh-pages@v3 if: github.event_name == 'release' with: From 6573911fdbf5c6e1a1af0496db0edfe9ac733f8a Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 12:03:57 +0800 Subject: [PATCH 12/18] fix artifact path --- .github/workflows/sphinx_docs.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sphinx_docs.yml b/.github/workflows/sphinx_docs.yml index 130733140..6e533b9db 100644 --- a/.github/workflows/sphinx_docs.yml +++ b/.github/workflows/sphinx_docs.yml @@ -34,7 +34,7 @@ jobs: uses: actions/upload-artifact@v3 with: name: SphinxDoc - path: docs/sphinx_doc/build/html/ + path: ${{ steps.deployment.outputs.artifact }} - uses: peaceiris/actions-gh-pages@v3 if: github.event_name == 'release' with: From 0da0c7ed2666b6f5bc2e46ff79ea627ec964d6a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Fri, 19 Jan 2024 13:56:36 +0800 Subject: [PATCH 13/18] fix according to dawei's comments --- docs/tutorial/102-concepts.md | 4 ++-- docs/tutorial/103-example.md | 8 +++----- 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/docs/tutorial/102-concepts.md b/docs/tutorial/102-concepts.md index 71e80e47a..8b98182cc 100644 --- a/docs/tutorial/102-concepts.md +++ b/docs/tutorial/102-concepts.md @@ -24,11 +24,11 @@ AgentScope │ | ├── memory # Structures for agent memory. │ | ├── models # Interfaces for integrating diverse model APIs. │ | ├── pipeline # Fundamental components and implementations for running pipelines. -│ | ├── rpc # Rpc module for agent distributed deployment. +│ | ├── rpc # Rpc module for agent distributed deployment. │ | ├── service # Services offering functions independent of memory and state. │ | ├── utils # Auxiliary utilities and helper functions. │ | ├── message.py # Definitions and implementations of messaging between agents. -| | ├── web_ui # WebUI used to show dialogs. +| | ├── web_ui # WebUI used to show dialogs. │ | ├── prompt.py # Prompt engineering module for model input. │ | ├── ... .. │ | ├── ... .. diff --git a/docs/tutorial/103-example.md b/docs/tutorial/103-example.md index 025a4e3b8..088f01989 100644 --- a/docs/tutorial/103-example.md +++ b/docs/tutorial/103-example.md @@ -71,7 +71,7 @@ message_from_alice = Msg("Alice", "Hi!") message_from_bob = Msg("Bob", "What about this picture I took?", url="/path/to/picture.jpg") ``` -To start a conversation between two agents, such as `dialogAgent` and `userAgent`, you can use the following loop. The conversation continues until the user inputs `"exit"` which terminates the interaction. +To start a conversation between two agents, such as `dialog_agent` and `user_agent`, you can use the following loop. The conversation continues until the user inputs `"exit"` which terminates the interaction. ```python x = None @@ -88,14 +88,12 @@ while True: For a more advanced approach, AgentScope offers the option of using pipelines to manage the flow of messages between agents. The `sequentialpipeline` stands for sequential speech, where each agent receive message from last agent and generate its response accordingly. ```python -from agentscope.pipelines.functional import ( - sequentialpipeline, -) +from agentscope.pipelines.functional import sequentialpipeline # Execute the conversation loop within a pipeline structure x = None while x is None or x.content != "exit": - x = sequentialpipeline(dialogAgent, userAgent) + x = sequentialpipeline([dialog_agent, user_agent]) ``` For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-pipeline.md). From 87f6518543bc5ff5025633197c99b28d957dcac0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Fri, 19 Jan 2024 13:59:11 +0800 Subject: [PATCH 14/18] fix according to xuchen's comments --- docs/sphinx_doc/source/index.rst | 8 ++++---- docs/{ => sphinx_doc/source}/tutorial/101-installation.md | 0 docs/{ => sphinx_doc/source}/tutorial/102-concepts.md | 0 docs/{ => sphinx_doc/source}/tutorial/103-example.md | 0 docs/{ => sphinx_doc/source}/tutorial/104-usecase.md | 0 docs/{ => sphinx_doc/source}/tutorial/105-logging.md | 0 docs/{ => sphinx_doc/source}/tutorial/201-agent.md | 0 docs/{ => sphinx_doc/source}/tutorial/202-pipeline.md | 0 docs/{ => sphinx_doc/source}/tutorial/203-model.md | 0 docs/{ => sphinx_doc/source}/tutorial/204-service.md | 0 docs/{ => sphinx_doc/source}/tutorial/205-memory.md | 0 docs/{ => sphinx_doc/source}/tutorial/206-prompt.md | 0 docs/{ => sphinx_doc/source}/tutorial/207-monitor.md | 0 docs/{ => sphinx_doc/source}/tutorial/208-distribute.md | 0 docs/{ => sphinx_doc/source}/tutorial/301-community.md | 0 docs/{ => sphinx_doc/source}/tutorial/302-contribute.md | 0 docs/{ => sphinx_doc/source}/tutorial/advance.rst | 0 docs/{ => sphinx_doc/source}/tutorial/contribute.rst | 0 docs/{ => sphinx_doc/source}/tutorial/main.md | 0 docs/{ => sphinx_doc/source}/tutorial/quick_start.rst | 0 20 files changed, 4 insertions(+), 4 deletions(-) rename docs/{ => sphinx_doc/source}/tutorial/101-installation.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/102-concepts.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/103-example.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/104-usecase.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/105-logging.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/201-agent.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/202-pipeline.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/203-model.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/204-service.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/205-memory.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/206-prompt.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/207-monitor.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/208-distribute.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/301-community.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/302-contribute.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/advance.rst (100%) rename docs/{ => sphinx_doc/source}/tutorial/contribute.rst (100%) rename docs/{ => sphinx_doc/source}/tutorial/main.md (100%) rename docs/{ => sphinx_doc/source}/tutorial/quick_start.rst (100%) diff --git a/docs/sphinx_doc/source/index.rst b/docs/sphinx_doc/source/index.rst index 2ca7c496b..6a98ce3a8 100644 --- a/docs/sphinx_doc/source/index.rst +++ b/docs/sphinx_doc/source/index.rst @@ -9,7 +9,7 @@ AgentScope Documentation ====================================== -.. include:: ../../tutorial/main.md +.. include:: tutorial/main.md :parser: myst_parser.sphinx_ .. toctree:: @@ -18,9 +18,9 @@ AgentScope Documentation :hidden: :caption: AgentScope Tutorial - ../../tutorial/quick_start.rst - ../../tutorial/advance.rst - ../../tutorial/contribute.rst + tutorial/quick_start.rst + tutorial/advance.rst + tutorial/contribute.rst .. toctree:: diff --git a/docs/tutorial/101-installation.md b/docs/sphinx_doc/source/tutorial/101-installation.md similarity index 100% rename from docs/tutorial/101-installation.md rename to docs/sphinx_doc/source/tutorial/101-installation.md diff --git a/docs/tutorial/102-concepts.md b/docs/sphinx_doc/source/tutorial/102-concepts.md similarity index 100% rename from docs/tutorial/102-concepts.md rename to docs/sphinx_doc/source/tutorial/102-concepts.md diff --git a/docs/tutorial/103-example.md b/docs/sphinx_doc/source/tutorial/103-example.md similarity index 100% rename from docs/tutorial/103-example.md rename to docs/sphinx_doc/source/tutorial/103-example.md diff --git a/docs/tutorial/104-usecase.md b/docs/sphinx_doc/source/tutorial/104-usecase.md similarity index 100% rename from docs/tutorial/104-usecase.md rename to docs/sphinx_doc/source/tutorial/104-usecase.md diff --git a/docs/tutorial/105-logging.md b/docs/sphinx_doc/source/tutorial/105-logging.md similarity index 100% rename from docs/tutorial/105-logging.md rename to docs/sphinx_doc/source/tutorial/105-logging.md diff --git a/docs/tutorial/201-agent.md b/docs/sphinx_doc/source/tutorial/201-agent.md similarity index 100% rename from docs/tutorial/201-agent.md rename to docs/sphinx_doc/source/tutorial/201-agent.md diff --git a/docs/tutorial/202-pipeline.md b/docs/sphinx_doc/source/tutorial/202-pipeline.md similarity index 100% rename from docs/tutorial/202-pipeline.md rename to docs/sphinx_doc/source/tutorial/202-pipeline.md diff --git a/docs/tutorial/203-model.md b/docs/sphinx_doc/source/tutorial/203-model.md similarity index 100% rename from docs/tutorial/203-model.md rename to docs/sphinx_doc/source/tutorial/203-model.md diff --git a/docs/tutorial/204-service.md b/docs/sphinx_doc/source/tutorial/204-service.md similarity index 100% rename from docs/tutorial/204-service.md rename to docs/sphinx_doc/source/tutorial/204-service.md diff --git a/docs/tutorial/205-memory.md b/docs/sphinx_doc/source/tutorial/205-memory.md similarity index 100% rename from docs/tutorial/205-memory.md rename to docs/sphinx_doc/source/tutorial/205-memory.md diff --git a/docs/tutorial/206-prompt.md b/docs/sphinx_doc/source/tutorial/206-prompt.md similarity index 100% rename from docs/tutorial/206-prompt.md rename to docs/sphinx_doc/source/tutorial/206-prompt.md diff --git a/docs/tutorial/207-monitor.md b/docs/sphinx_doc/source/tutorial/207-monitor.md similarity index 100% rename from docs/tutorial/207-monitor.md rename to docs/sphinx_doc/source/tutorial/207-monitor.md diff --git a/docs/tutorial/208-distribute.md b/docs/sphinx_doc/source/tutorial/208-distribute.md similarity index 100% rename from docs/tutorial/208-distribute.md rename to docs/sphinx_doc/source/tutorial/208-distribute.md diff --git a/docs/tutorial/301-community.md b/docs/sphinx_doc/source/tutorial/301-community.md similarity index 100% rename from docs/tutorial/301-community.md rename to docs/sphinx_doc/source/tutorial/301-community.md diff --git a/docs/tutorial/302-contribute.md b/docs/sphinx_doc/source/tutorial/302-contribute.md similarity index 100% rename from docs/tutorial/302-contribute.md rename to docs/sphinx_doc/source/tutorial/302-contribute.md diff --git a/docs/tutorial/advance.rst b/docs/sphinx_doc/source/tutorial/advance.rst similarity index 100% rename from docs/tutorial/advance.rst rename to docs/sphinx_doc/source/tutorial/advance.rst diff --git a/docs/tutorial/contribute.rst b/docs/sphinx_doc/source/tutorial/contribute.rst similarity index 100% rename from docs/tutorial/contribute.rst rename to docs/sphinx_doc/source/tutorial/contribute.rst diff --git a/docs/tutorial/main.md b/docs/sphinx_doc/source/tutorial/main.md similarity index 100% rename from docs/tutorial/main.md rename to docs/sphinx_doc/source/tutorial/main.md diff --git a/docs/tutorial/quick_start.rst b/docs/sphinx_doc/source/tutorial/quick_start.rst similarity index 100% rename from docs/tutorial/quick_start.rst rename to docs/sphinx_doc/source/tutorial/quick_start.rst From 3e1ee851178eaaaf4691eac830ba66eafdf738b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Fri, 19 Jan 2024 16:07:27 +0800 Subject: [PATCH 15/18] fix according to xuchen's comments [hyperlinks] --- docs/sphinx_doc/source/conf.py | 5 +++ docs/sphinx_doc/source/index.rst | 3 +- .../sphinx_doc/source/tutorial/103-example.md | 6 ++-- .../sphinx_doc/source/tutorial/104-usecase.md | 4 +-- docs/sphinx_doc/source/tutorial/201-agent.md | 6 ++-- .../source/tutorial/208-distribute.md | 4 +-- docs/sphinx_doc/source/tutorial/main.md | 34 ++++++++----------- 7 files changed, 31 insertions(+), 31 deletions(-) diff --git a/docs/sphinx_doc/source/conf.py b/docs/sphinx_doc/source/conf.py index 221d8ff67..003a56492 100644 --- a/docs/sphinx_doc/source/conf.py +++ b/docs/sphinx_doc/source/conf.py @@ -35,8 +35,13 @@ "sphinx.ext.napoleon", "sphinxcontrib.mermaid", "myst_parser", + "sphinx.ext.autosectionlabel", ] +# Prefix document path to section labels, otherwise autogenerated labels would +# look like 'heading' rather than 'path/to/file:heading' +autosectionlabel_prefix_document = True + # Add any paths that contain templates here, relative to this directory. templates_path = ["_templates"] diff --git a/docs/sphinx_doc/source/index.rst b/docs/sphinx_doc/source/index.rst index 6a98ce3a8..feb525bfd 100644 --- a/docs/sphinx_doc/source/index.rst +++ b/docs/sphinx_doc/source/index.rst @@ -24,9 +24,8 @@ AgentScope Documentation .. toctree:: - :maxdepth: 2 + :maxdepth: 1 :glob: - :hidden: :caption: AgentScope API Reference agentscope.agents diff --git a/docs/sphinx_doc/source/tutorial/103-example.md b/docs/sphinx_doc/source/tutorial/103-example.md index 088f01989..a5f514f46 100644 --- a/docs/sphinx_doc/source/tutorial/103-example.md +++ b/docs/sphinx_doc/source/tutorial/103-example.md @@ -26,7 +26,7 @@ model_config = { } ``` -For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). +For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://alibaba.github.io/AgentScope/tutorial/203-model.md). You can register your configuration by calling AgentScope's initilization method as follow. Besides, you can also load more than one config by calling init mutliple times. ```python @@ -55,7 +55,7 @@ dialogAgent = DialogAgent(name="assistant", model="gpt-4") userAgent = UserAgent() ``` -**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/201-agent.md) for all available agents. +**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://alibaba.github.io/AgentScope/tutorial/201-agent.md) for all available agents. ## Step3: Agent Conversation @@ -96,7 +96,7 @@ while x is None or x.content != "exit": x = sequentialpipeline([dialog_agent, user_agent]) ``` -For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-pipeline.md). +For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://alibaba.github.io/AgentScope/tutorial/202-pipeline.md). diff --git a/docs/sphinx_doc/source/tutorial/104-usecase.md b/docs/sphinx_doc/source/tutorial/104-usecase.md index edcfa0c44..c1608df7b 100644 --- a/docs/sphinx_doc/source/tutorial/104-usecase.md +++ b/docs/sphinx_doc/source/tutorial/104-usecase.md @@ -10,7 +10,7 @@ Let the adventure begin to unlock the potential of multi-agent applications with ## Getting Started -Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md). The overview of this tutorial is shown below: +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://alibaba.github.io/AgentScope/tutorial/102-concepts.md). The overview of this tutorial is shown below: * [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) * [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) @@ -22,7 +22,7 @@ Firstly, ensure that you have installed and configured AgentScope properly. Besi ### Step 1: Prepare Model API and Set Model Configs -As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). +As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://alibaba.github.io/AgentScope/tutorial/203-model.md). ```json [ diff --git a/docs/sphinx_doc/source/tutorial/201-agent.md b/docs/sphinx_doc/source/tutorial/201-agent.md index 77d17bd1d..58c9b5658 100644 --- a/docs/sphinx_doc/source/tutorial/201-agent.md +++ b/docs/sphinx_doc/source/tutorial/201-agent.md @@ -8,11 +8,11 @@ The `AgentBase` class is the architectural cornerstone for all agent constructs Each AgentBase derivative is composed of several key characteristics: -* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/205-memory.md). +* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://alibaba.github.io/AgentScope/tutorial/205-memory.md). -* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md). +* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API]https://alibaba.github.io/AgentScope/tutorial/203-model.md). -* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/206-prompt.md). +* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://alibaba.github.io/AgentScope/tutorial/206-prompt.md). In addition to these attributes, `AgentBase` endows agents with pivotal methods such as `observe` and `reply`: diff --git a/docs/sphinx_doc/source/tutorial/208-distribute.md b/docs/sphinx_doc/source/tutorial/208-distribute.md index f494a1665..66ca7bcb5 100644 --- a/docs/sphinx_doc/source/tutorial/208-distribute.md +++ b/docs/sphinx_doc/source/tutorial/208-distribute.md @@ -8,7 +8,7 @@ AgentScope is designed to be fully distributed, agent instances in one applicati [The actor model](https://en.wikipedia.org/wiki/Actor_model) is a popular concept in concurrent programming and adopted by AgentScope. Every agent is an actor and interacts with other agents through messages. The flow of messages implies the execution order of the agent. Each agent has a `reply` method that consumes a message and generates another message, and the generated message can be sent to other agents. For example, the figure below shows the workflow of multiple agents. `A` to `F` are all agents, and the arrows represent messages. -```mermaid +```{mermaid} graph LR; A-->B A-->C @@ -33,7 +33,7 @@ z = C(x) Although this code appears to be executed completely sequentially, AgentScope will **automatically detect potential parallelism** in your code as shown in the flow graph below, which means `C` will not wait for `B` to complete before starting execution. -```mermaid +```{mermaid} graph LR; A-->B A-->C diff --git a/docs/sphinx_doc/source/tutorial/main.md b/docs/sphinx_doc/source/tutorial/main.md index af03c2130..bbb8fa546 100644 --- a/docs/sphinx_doc/source/tutorial/main.md +++ b/docs/sphinx_doc/source/tutorial/main.md @@ -12,28 +12,24 @@ AgentScope is an innovative multi-agent platform designed to empower developers ### Getting Started -- [Installation Guide](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/101-installation.md) -- [Fundamental Concepts](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/102-concepts.md) -- [Getting Started with a Simple Example](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/103-example.md) -- [Crafting Your First Application](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/104-usecase.md) -- [Logging and WebUI](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/105-logging.md) +- [Installation Guide](tutorial/101-installation.md) +- [Fundamental Concepts](tutorial/102-concepts.md) +- [Getting Started with a Simple Example](tutorial/103-example.md) +- [Crafting Your First Application](tutorial/104-usecase.md) +- [Logging and WebUI](tutorial/105-logging.md) ### Advanced Exploration -- [Customizing Your Own Agent](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/201-agent.md) -- [Agent Interactions: Dive deeper into Pipelines and Message Hub](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/202-pipeline.md) -- [Using Different Model Sources with Model API](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/203-model.md) -- [Enhancing Agent Capabilities with Service Functions](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/204-service.md) -- [Memory and Message Management](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/205-memory.md) -- [Prompt Engine](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/206-prompt.md) -- [Monitoring](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/207-monitor.md) -- [Distributed Deployment](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/208-distribute.md) +- [Customizing Your Own Agent](tutorial/201-agent.md) +- [Agent Interactions: Dive deeper into Pipelines and Message Hub](tutorial/202-pipeline.md) +- [Using Different Model Sources with Model API](tutorial/203-model.md) +- [Enhancing Agent Capabilities with Service Functions](tutorial/204-service.md) +- [Memory and Message Management](tutorial/205-memory.md) +- [Prompt Engine](tutorial/206-prompt.md) +- [Monitoring](tutorial/207-monitor.md) +- [Distributed Deployment](tutorial/208-distribute.md) ### Getting Involved -* [Joining The AgentScope Community](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/301-community.md) -* [Contributing to AgentScope](https://github.com/alibaba/AgentScope/tree/main/docs/tutorial/302-contribute.md) - -### API References - -Please refer to [[API References]](https://alibaba.github.io/agentscope/) for details. \ No newline at end of file +* [Joining The AgentScope Community](tutorial/301-community.md) +* [Contributing to AgentScope](tutorial/302-contribute.md) \ No newline at end of file From c41496a061b9f516d782b318c237f019f82858bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=81=93=E8=BE=95?= Date: Fri, 19 Jan 2024 16:21:47 +0800 Subject: [PATCH 16/18] fix according to xuchen's comments [hyperlinks] --- docs/sphinx_doc/source/tutorial/103-example.md | 6 +++--- docs/sphinx_doc/source/tutorial/104-usecase.md | 4 ++-- docs/sphinx_doc/source/tutorial/201-agent.md | 6 +++--- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/docs/sphinx_doc/source/tutorial/103-example.md b/docs/sphinx_doc/source/tutorial/103-example.md index a5f514f46..02995edc2 100644 --- a/docs/sphinx_doc/source/tutorial/103-example.md +++ b/docs/sphinx_doc/source/tutorial/103-example.md @@ -26,7 +26,7 @@ model_config = { } ``` -For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://alibaba.github.io/AgentScope/tutorial/203-model.md). +For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://alibaba.github.io/AgentScope/tutorial/203-model.html). You can register your configuration by calling AgentScope's initilization method as follow. Besides, you can also load more than one config by calling init mutliple times. ```python @@ -55,7 +55,7 @@ dialogAgent = DialogAgent(name="assistant", model="gpt-4") userAgent = UserAgent() ``` -**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://alibaba.github.io/AgentScope/tutorial/201-agent.md) for all available agents. +**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://alibaba.github.io/AgentScope/tutorial/201-agent.html) for all available agents. ## Step3: Agent Conversation @@ -96,7 +96,7 @@ while x is None or x.content != "exit": x = sequentialpipeline([dialog_agent, user_agent]) ``` -For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://alibaba.github.io/AgentScope/tutorial/202-pipeline.md). +For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://alibaba.github.io/AgentScope/tutorial/202-pipeline.html). diff --git a/docs/sphinx_doc/source/tutorial/104-usecase.md b/docs/sphinx_doc/source/tutorial/104-usecase.md index c1608df7b..edd35ea7b 100644 --- a/docs/sphinx_doc/source/tutorial/104-usecase.md +++ b/docs/sphinx_doc/source/tutorial/104-usecase.md @@ -10,7 +10,7 @@ Let the adventure begin to unlock the potential of multi-agent applications with ## Getting Started -Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://alibaba.github.io/AgentScope/tutorial/102-concepts.md). The overview of this tutorial is shown below: +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://alibaba.github.io/AgentScope/tutorial/102-concepts.html). The overview of this tutorial is shown below: * [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) * [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) @@ -22,7 +22,7 @@ Firstly, ensure that you have installed and configured AgentScope properly. Besi ### Step 1: Prepare Model API and Set Model Configs -As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://alibaba.github.io/AgentScope/tutorial/203-model.md). +As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://alibaba.github.io/AgentScope/tutorial/203-model.html). ```json [ diff --git a/docs/sphinx_doc/source/tutorial/201-agent.md b/docs/sphinx_doc/source/tutorial/201-agent.md index 58c9b5658..e1cfb7a95 100644 --- a/docs/sphinx_doc/source/tutorial/201-agent.md +++ b/docs/sphinx_doc/source/tutorial/201-agent.md @@ -8,11 +8,11 @@ The `AgentBase` class is the architectural cornerstone for all agent constructs Each AgentBase derivative is composed of several key characteristics: -* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://alibaba.github.io/AgentScope/tutorial/205-memory.md). +* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://alibaba.github.io/AgentScope/tutorial/205-memory.html). -* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API]https://alibaba.github.io/AgentScope/tutorial/203-model.md). +* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API]https://alibaba.github.io/AgentScope/tutorial/203-model.html). -* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://alibaba.github.io/AgentScope/tutorial/206-prompt.md). +* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://alibaba.github.io/AgentScope/tutorial/206-prompt.html). In addition to these attributes, `AgentBase` endows agents with pivotal methods such as `observe` and `reply`: From 2854d9a98348cfea0a030f27e8ea41adde48214a Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 17:43:28 +0800 Subject: [PATCH 17/18] fix sphinx link --- .../source/tutorial/101-installation.md | 8 ++-- .../source/tutorial/102-concepts.md | 7 ++- .../sphinx_doc/source/tutorial/103-example.md | 19 ++++---- .../sphinx_doc/source/tutorial/104-usecase.md | 43 +++++++++++-------- .../sphinx_doc/source/tutorial/105-logging.md | 12 ++++-- docs/sphinx_doc/source/tutorial/201-agent.md | 25 ++++++----- .../source/tutorial/202-pipeline.md | 2 + docs/sphinx_doc/source/tutorial/203-model.md | 20 +++++---- .../sphinx_doc/source/tutorial/204-service.md | 13 +++--- docs/sphinx_doc/source/tutorial/205-memory.md | 14 +++--- docs/sphinx_doc/source/tutorial/206-prompt.md | 8 ++-- .../sphinx_doc/source/tutorial/207-monitor.md | 6 +-- .../source/tutorial/208-distribute.md | 4 +- .../source/tutorial/301-community.md | 6 +-- .../source/tutorial/302-contribute.md | 7 +-- docs/sphinx_doc/source/tutorial/advance.rst | 2 +- docs/sphinx_doc/source/tutorial/main.md | 30 ++++++------- 17 files changed, 120 insertions(+), 106 deletions(-) diff --git a/docs/sphinx_doc/source/tutorial/101-installation.md b/docs/sphinx_doc/source/tutorial/101-installation.md index 6b05879a0..fdde47b4f 100644 --- a/docs/sphinx_doc/source/tutorial/101-installation.md +++ b/docs/sphinx_doc/source/tutorial/101-installation.md @@ -1,3 +1,5 @@ +(101-installation)= + # Installation To install AgentScope, you need to have Python 3.9 or higher installed. We recommend setting up a new virtual environment specifically for AgentScope: @@ -44,7 +46,6 @@ pip install agentscope pip install agentscope[distribute] # On Mac use `pip install agentscope\[distribute\]` ``` - #### Install from Source For users who prefer to install AgentScope directly from the source code, follow these steps to clone the repository and install the platform in editable mode: @@ -62,9 +63,6 @@ pip install -e . pip install -e .[distribute] # On Mac use `pip install -e .\[distribute\]` ``` - **Note**: The `[distribute]` option installs additional dependencies required for distributed applications. Remember to activate your virtual environment before running these commands. - - -[[Return to the top]](#installation) \ No newline at end of file +[[Return to the top]](#installation) diff --git a/docs/sphinx_doc/source/tutorial/102-concepts.md b/docs/sphinx_doc/source/tutorial/102-concepts.md index 8b98182cc..a83da431e 100644 --- a/docs/sphinx_doc/source/tutorial/102-concepts.md +++ b/docs/sphinx_doc/source/tutorial/102-concepts.md @@ -1,3 +1,5 @@ +(102-concepts)= + # Fundamental Concepts In this tutorial, you'll have an initial understanding of the **fundamental concepts** of AgentScope. We will focus on how a multi-agent application runs based on our platform and familiarize you with the essential terms. Let's get started! @@ -12,7 +14,6 @@ In this tutorial, you'll have an initial understanding of the **fundamental conc * **Service** is a collection of functionality tools (e.g., web search, code interpreter, file processing) that provide specific capabilities or processes that are independent of an agent's memory state. Services can be invoked by agents or other components and designed to be reusable across different scenarios. * **Pipeline** refers to the interaction order or pattern of agents in a task. AgentScope provides built-in `pipelines` to streamline the process of collaboration across multiple agents, such as `SequentialPipeline` and `ForLoopPipeline`. When a `Pipeline` is executed, the *message* passes from predecessors to successors with intermediate results for the task. - ## Code Structure ```bash @@ -42,6 +43,4 @@ AgentScope └── ... .. ``` - - -[[Return to the top]](#fundamental-concepts) \ No newline at end of file +[[Return to the top]](#fundamental-concepts) diff --git a/docs/sphinx_doc/source/tutorial/103-example.md b/docs/sphinx_doc/source/tutorial/103-example.md index 02995edc2..e81fa29c2 100644 --- a/docs/sphinx_doc/source/tutorial/103-example.md +++ b/docs/sphinx_doc/source/tutorial/103-example.md @@ -1,3 +1,5 @@ +(103-example)= + # Getting Started with a Simple Example AgentScope is a versatile platform for building and running multi-agent applications. We provide various pre-built examples that will help you quickly understand how to create and use multi-agent for various applications. In this tutorial, you will learn how to set up a **simple agent-based interaction**. @@ -13,10 +15,9 @@ Agent is the basic composition and communication unit in AgentScope. To initiali | Embedding | `openai_embedding` | API for text embeddings | | General usages in POST | `post_api` | *Huggingface* and *ModelScope* Inference API, and other customized post API | - Each API has its specific configuration requirements. For example, to configure an OpenAI API, you would need to fill out the following fields in the model config in a dict, a yaml file or a json file: -``` +```python model_config = { "type": "openai", # Choose from "openai", "openai_dall_e", or "openai_embedding" "name": "{your_config_name}", # A unique identifier for your config @@ -26,9 +27,10 @@ model_config = { } ``` -For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](https://alibaba.github.io/AgentScope/tutorial/203-model.html). +For open-source models, we support integration with various model interfaces such as HuggingFace, ModelScope, FastChat, and vllm. You can find scripts on deploying these services in the `scripts` directory, and we defer the detailed instructions to [[Using Different Model Sources with Model API]](203-model). You can register your configuration by calling AgentScope's initilization method as follow. Besides, you can also load more than one config by calling init mutliple times. + ```python import agentscope @@ -38,7 +40,6 @@ modelscope_cfg_dict = {...dict_filling...} agentscope.init(model_configs=[openai_cfg_dict, modelscope_cfg_dict]) ``` - ## Step2: Create Agents Creating agents is straightforward in AgentScope. After initializing AgentScope with your model configurations (Step 1 above), you can then define each agent with its corresponding role and specific model. @@ -55,7 +56,7 @@ dialogAgent = DialogAgent(name="assistant", model="gpt-4") userAgent = UserAgent() ``` -**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](https://alibaba.github.io/AgentScope/tutorial/201-agent.html) for all available agents. +**NOTE**: Please refer to [[Customizing Your Custom Agent with Agent Pool]](201-agent) for all available agents. ## Step3: Agent Conversation @@ -81,7 +82,7 @@ while True: # Terminate the conversation if the user types "exit" if x.content == "exit": - print("Exiting the conversation.") + print("Exiting the conversation.") break ``` @@ -93,11 +94,9 @@ from agentscope.pipelines.functional import sequentialpipeline # Execute the conversation loop within a pipeline structure x = None while x is None or x.content != "exit": - x = sequentialpipeline([dialog_agent, user_agent]) + x = sequentialpipeline([dialog_agent, user_agent]) ``` -For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](https://alibaba.github.io/AgentScope/tutorial/202-pipeline.html). - - +For more details about how to utilize pipelines for complex agent interactions, please refer to [[Agent Interactions: Dive deeper into Pipelines and Message Hub]](202-pipeline). [[Return to the top]](#getting-started-with-a-simple-example) diff --git a/docs/sphinx_doc/source/tutorial/104-usecase.md b/docs/sphinx_doc/source/tutorial/104-usecase.md index edd35ea7b..a034d8bcc 100644 --- a/docs/sphinx_doc/source/tutorial/104-usecase.md +++ b/docs/sphinx_doc/source/tutorial/104-usecase.md @@ -1,3 +1,5 @@ +(104-usecase)= + # Crafting Your First Application img @@ -10,19 +12,25 @@ Let the adventure begin to unlock the potential of multi-agent applications with ## Getting Started -Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](https://alibaba.github.io/AgentScope/tutorial/102-concepts.html). The overview of this tutorial is shown below: +Firstly, ensure that you have installed and configured AgentScope properly. Besides, we will involve the basic concepts of `Model API`, `Agent`, `Msg`, and `Pipeline,` as described in [Tutorial-Concept](102-concepts). The overview of this tutorial is shown below: -* [Step 1: Prepare **Model API** and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) -* [Step 2: Define the Roles of Each **Agent**](#step-2-define-the-roles-of-each-agent) -* [Step 3: **Initialize** AgentScope and the Agents](#step-3-initialize-agentscope-and-the-agents) -* [Step 4: Set Up the Game Logic with **Pipelines**](#step-4-set-up-the-game-logic-with-pipelines) -* [Step 5: **Run** the Application](#step-5-run-the-application) +- [Crafting Your First Application](#crafting-your-first-application) + - [Getting Started](#getting-started) + - [Step 1: Prepare Model API and Set Model Configs](#step-1-prepare-model-api-and-set-model-configs) + - [Step 2: Define the Roles of Each Agent](#step-2-define-the-roles-of-each-agent) + - [Step 3: Initialize AgentScope and the Agents](#step-3-initialize-agentscope-and-the-agents) + - [Step 4: Set Up the Game Logic](#step-4-set-up-the-game-logic) + - [Leverage Pipeline and MsgHub](#leverage-pipeline-and-msghub) + - [Implement Werewolf Pipeline](#implement-werewolf-pipeline) + - [Step 5: Run the Application](#step-5-run-the-application) + - [Next step](#next-step) + - [Other Example Applications](#other-example-applications) **Note**: all the configurations and code for this tutorial can be found in `examples/werewolf`. ### Step 1: Prepare Model API and Set Model Configs -As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](https://alibaba.github.io/AgentScope/tutorial/203-model.html). +As we discussed in the last tutorial, you need to prepare your model configurations into a JSON file for standard OpenAI chat API, FastChat, and vllm. More details and advanced usages such as configuring local models with POST API are presented in [Tutorial-Model-API](203-model). ```json [ @@ -138,7 +146,7 @@ To simplify the construction of agent communication, AgentScope provides two hel The game logic is divided into two major phases: (1) night when werewolves act, and (2) daytime when all players discuss and vote. Each phase will be handled by a section of code using pipelines to manage multi-agent communications. -* **1.1 Night Phase: Werewolves Discuss and Vote** +- **1.1 Night Phase: Werewolves Discuss and Vote** During the night phase, werewolves must discuss among themselves to decide on a target. The `msghub` function creates a message hub for the werewolves to communicate in, where every message sent by an agent is observable by all other agents within the `msghub`. @@ -169,7 +177,7 @@ After the discussion, werewolves proceed to vote for their target, and the major ) ``` -* **1.2 Witch's Turn** +- **1.2 Witch's Turn** If the witch is still alive, she gets the opportunity to use her powers to either save the player chosen by the werewolves or use her poison. @@ -178,7 +186,7 @@ If the witch is still alive, she gets the opportunity to use her powers to eithe healing_used_tonight = False if witch in survivors: if healing: - # Witch decides whether to use the healing potion + # Witch decides whether to use the healing potion hint = HostMsg( content=Prompts.to_witch_resurrect.format_map( {"witch_name": witch.name, "dead_name": dead_player[0]}, @@ -191,7 +199,7 @@ If the witch is still alive, she gets the opportunity to use her powers to eithe healing = False ``` -* **1.3 Seer's Turn** +- **1.3 Seer's Turn** The seer has a chance to reveal the true identity of a player. This information can be crucial for the villagers. The `observe()` function allows each agent to take note of a message without immediately replying to it. @@ -210,7 +218,7 @@ The seer has a chance to reveal the true identity of a player. This information seer.observe(hint) ``` -* **1.4 Update Alive Players** +- **1.4 Update Alive Players** Based on the actions taken during the night, the list of surviving players needs to be updated. @@ -219,7 +227,7 @@ Based on the actions taken during the night, the list of surviving players needs survivors, wolves = update_alive_players(survivors, wolves, dead_player) ``` -* **2.1 Daytime Phase: Discussion and Voting** +- **2.1 Daytime Phase: Discussion and Voting** During the day, all players will discuss and then vote to eliminate a suspected werewolf. @@ -239,7 +247,7 @@ During the day, all players will discuss and then vote to eliminate a suspected survivors, wolves = update_alive_players(survivors, wolves, vote_res) ``` -* **2.2 Check for Winning Conditions** +- **2.2 Check for Winning Conditions** After each phase, the game checks if the werewolves or villagers have won. @@ -249,7 +257,7 @@ After each phase, the game checks if the werewolves or villagers have won. break ``` -* **2.3 Continue to the Next Round** +- **2.3 Continue to the Next Round** If neither werewolves nor villagers win, the game continues to the next round. @@ -311,7 +319,6 @@ Moderator: The day is coming, all the players open your eyes. Last night is peac Now you've grasped how to conveniently set up a multi-agent application with AgentScope. Feel free to tailor the game to include additional roles and introduce more sophisticated strategies. For more advanced tutorials that delve deeper into more capabilities of AgentScope, such as *memory management* and *service functions* utilized by agents, please refer to the tutorials in the **Advanced Exploration** section and look up the API references. - ## Other Example Applications - Example of Simple Group Conversation: [examples/Simple Conversation](https://github.com/alibaba/AgentScope/tree/main/examples/simple_chat/README.md) @@ -319,6 +326,4 @@ Now you've grasped how to conveniently set up a multi-agent application with Age - Example of Distributed Agents: [examples/Distributed Agents](https://github.com/alibaba/AgentScope/tree/main/examples/distributed_agents/README.md) - ... - - -[[Return to the top]](#crafting-your-first-application) \ No newline at end of file +[[Return to the top]](#crafting-your-first-application) diff --git a/docs/sphinx_doc/source/tutorial/105-logging.md b/docs/sphinx_doc/source/tutorial/105-logging.md index cc87749bd..42e05b5ff 100644 --- a/docs/sphinx_doc/source/tutorial/105-logging.md +++ b/docs/sphinx_doc/source/tutorial/105-logging.md @@ -1,3 +1,5 @@ +(105-logging)= + # Logging and WebUI Welcome to the tutorial on logging in multi-agent applications with AgentScope. We'll also touch on how you can visualize these logs using a simple web interface. This guide will help you track the agent's interactions and system information in a clearer and more organized way. @@ -65,17 +67,22 @@ logger.error("The agent encountered an unexpected error while processing a reque To visualize these logs, we provide a customized gradio component in `src/agentscope/web_ui`. ### Quick Running + For convince, we provide the pre-built app in a wheel file, you can run the WebUI in the following command: + ```shell pip install gradio_groupchat-0.0.1-py3-none-any.whl python app.py ``` + After the init and entering the UI port printed by `app.py`, e.g., `http://127.0.0.1:7860/`, you can choose `run.log.demo` in the top-middle `FileSelector` window (it's a demo log file provided by us). Then, the dialog and system log should be shown correctly in the bottom windows. ![webui](https://img.alicdn.com/imgextra/i2/O1CN01hSaFue1EdL2yCEznc_!!6000000000374-2-tps-3066-1808.png) ### For Other Customization + To customize the backend, or the frontend of the provided WebUI, you can + ```shell # generate the template codes # for network connectivity problem, try to run @@ -91,12 +98,11 @@ gradio cc dev ``` If you want to release the modification, you can do + ```shell gradio cc build pip install python app.py ``` - - -[[Return to the top]](#logging-and-webui) \ No newline at end of file +[[Return to the top]](#logging-and-webui) diff --git a/docs/sphinx_doc/source/tutorial/201-agent.md b/docs/sphinx_doc/source/tutorial/201-agent.md index e1cfb7a95..e498f18d1 100644 --- a/docs/sphinx_doc/source/tutorial/201-agent.md +++ b/docs/sphinx_doc/source/tutorial/201-agent.md @@ -1,3 +1,5 @@ +(201-agent)= + # Customizing Your Own Agent This tutorial helps you to understand the `Agent` in mode depth and navigate through the process of crafting your own custom agent with AgentScope. We start by introducing the fundamental abstraction called `AgentBase`, which serves as the base class to maintain the general behaviors of all agents. Then, we will go through the *AgentPool*, an ensemble of pre-built, specialized agents, each designed with a specific purpose in mind. Finally, we will demonstrate how to customize your own agent, ensuring it fits the needs of your project. @@ -8,11 +10,11 @@ The `AgentBase` class is the architectural cornerstone for all agent constructs Each AgentBase derivative is composed of several key characteristics: -* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](https://alibaba.github.io/AgentScope/tutorial/205-memory.html). +* `memory`: This attribute enables agents to retain and recall past interactions, allowing them to maintain context in ongoing conversations. For more details about `memory`, we defer to [Memory and Message Management](205-memory). -* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API]https://alibaba.github.io/AgentScope/tutorial/203-model.html). +* `model`: The model is the computational engine of the agent, responsible for making a response given existing memory and input. For more details about `model`, we defer to [Using Different Model Sources with Model API](203-model). -* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](https://alibaba.github.io/AgentScope/tutorial/206-prompt.html). +* `sys_prompt` & `engine`: The system prompt acts as predefined instructions that guide the agent in its interactions; and the `engine` is used to dynamically generate a suitable prompt. For more details about them, we defer to [Prompt Engine](206-prompt). In addition to these attributes, `AgentBase` endows agents with pivotal methods such as `observe` and `reply`: @@ -21,7 +23,6 @@ In addition to these attributes, `AgentBase` endows agents with pivotal methods Besides, for unified interfaces and type hints, we introduce another base class `Operator`, which indicates performing some operation on input data by the `__call__` function. And we make `AgentBase` a subclass of `Operator`. - ```python class AgentBase(Operator): # ... [code omitted for brevity] @@ -37,7 +38,7 @@ class AgentBase(Operator): ) -> None: # ... [code omitted for brevity] - def observe(self, x: Union[dict, Sequence[dict]]) -> None: + def observe(self, x: Union[dict, Sequence[dict]]) -> None: # An optional method for updating the agent's internal state based on # messages it has observed. This method can be used to enrich the # agent's understanding and memory without producing an immediate @@ -58,7 +59,7 @@ class AgentBase(Operator): ## Exploring the AgentPool -The *AgentPool* within AgentScope is a curated ensemble of ready-to-use, specialized agents. Each of these agents is tailored for a distinct role and comes equipped with default behaviors that address specific tasks. The *AgentPool* is designed to expedite the development process by providing various templates of `Agent `. +The *AgentPool* within AgentScope is a curated ensemble of ready-to-use, specialized agents. Each of these agents is tailored for a distinct role and comes equipped with default behaviors that address specific tasks. The *AgentPool* is designed to expedite the development process by providing various templates of `Agent`. Below is a table summarizing the functionality of some of the key agents available in the Agent Pool: @@ -78,7 +79,7 @@ Below, we provide usages of how to configure various agents from the AgentPool: ### `DialogAgent` -- **Reply Method**: The `reply` method is where the main logic for processing input *message* and generating responses. +* **Reply Method**: The `reply` method is where the main logic for processing input *message* and generating responses. ```python def reply(self, x: dict = None) -> dict: @@ -101,7 +102,7 @@ def reply(self, x: dict = None) -> dict: return msg ``` -- **Usages:** To tailor a `DialogAgent` for a customer service bot: +* **Usages:** To tailor a `DialogAgent` for a customer service bot: ```python from agentscope.agents import DialogAgent @@ -121,7 +122,7 @@ service_bot = DialogAgent(**dialog_agent_config) ### `UserAgent` -- **Reply Method**: This method processes user input by prompting for content and if needed, additional keys and a URL. The gathered data is stored in a *message* object in the agent's memory for logging or later use and returns the message as a response. +* **Reply Method**: This method processes user input by prompting for content and if needed, additional keys and a URL. The gathered data is stored in a *message* object in the agent's memory for logging or later use and returns the message as a response. ```python def reply( @@ -156,7 +157,7 @@ def reply( return msg ``` -- **Usages:** To configure a `UserAgent` for collecting user input and URLs (of file, image, video, audio , or website): +* **Usages:** To configure a `UserAgent` for collecting user input and URLs (of file, image, video, audio , or website): ```python from agentscope.agents import UserAgent @@ -171,6 +172,4 @@ user_agent_config = { user_proxy_agent = UserAgent(**user_agent_config) ``` - - -[[Return to the top]](#customizing-your-own-agent) \ No newline at end of file +[[Return to the top]](#customizing-your-own-agent) diff --git a/docs/sphinx_doc/source/tutorial/202-pipeline.md b/docs/sphinx_doc/source/tutorial/202-pipeline.md index ebe23cd4d..d61313fe5 100644 --- a/docs/sphinx_doc/source/tutorial/202-pipeline.md +++ b/docs/sphinx_doc/source/tutorial/202-pipeline.md @@ -1,3 +1,5 @@ +(202-pipeline)= + # Agent Interactions: Dive deeper into Pipelines and Message Hub **Pipeline & MsgHub** (message hub) are one or a sequence of steps describing how the structured `Msg` passes between multi-agents, which streamlines the process of collaboration across agents. diff --git a/docs/sphinx_doc/source/tutorial/203-model.md b/docs/sphinx_doc/source/tutorial/203-model.md index 9d9d31cc3..92c8fde7c 100644 --- a/docs/sphinx_doc/source/tutorial/203-model.md +++ b/docs/sphinx_doc/source/tutorial/203-model.md @@ -1,3 +1,5 @@ +(203-model)= + # Using Different Model Sources with Model API AgentScope allows for the integration of multi-modal models from various sources. The core step is the initialization process, where once initialized with a certain config, all agent instances globally select the appropriate model APIs based on the model name specified (e.g., `model='gpt-4'`): @@ -21,7 +23,7 @@ where the model configs could be a list of dict: "temperature": 0.0 } }, - { + { "type": "openai_dall_e", "name": "dall-e-3", "parameters": { @@ -68,6 +70,7 @@ pip install Flask, transformers ``` Taking model `meta-llama/Llama-2-7b-chat-hf` and port `8000` as an example, set up the model API serving by running the following command. + ```bash python flask_transformers/setup_hf_service.py --model_name_or_path meta-llama/Llama-2-7b-chat-hf @@ -97,7 +100,6 @@ In AgentScope, you can load the model with the following model configs: `./flask In this model serving, the messages from post requests should be in **STRING** format. You can use [templates for chat model](https://huggingface.co/docs/transformers/main/chat_templating) from *transformers* with a little modification based on `./flask_transformers/setup_hf_service.py`. - #### With ModelScope Library ##### Install Libraries and Set up Serving @@ -119,7 +121,6 @@ python flask_modelscope/setup_ms_service.py You can replace `modelscope/Llama-2-7b-ms` with any model card in modelscope model hub. - ##### How to use AgentScope In AgentScope, you can load the model with the following model configs: `flask_modelscope/model_config.json`. @@ -140,7 +141,6 @@ In AgentScope, you can load the model with the following model configs: `flask_m Similar to the example of transformers, the messages from post requests should be in **STRING format**. - ### FastChat [FastChat](https://github.com/lm-sys/FastChat) is an open platform that provides a quick setup for model serving with OpenAI-compatible RESTful APIs. @@ -160,10 +160,13 @@ bash fastchat_script/fastchat_setup.sh -m meta-llama/Llama-2-7b-chat-hf -p 8000 ``` #### Supported Models + Refer to [supported model list](https://github.com/lm-sys/FastChat/blob/main/docs/model_support.md#supported-models) of FastChat. #### How to use in AgentScope + Now you can load the model in AgentScope by the following model config: `fastchat_script/model_config.json`. + ```json { "type": "openai", @@ -183,6 +186,7 @@ Now you can load the model in AgentScope by the following model config: `fastcha [vllm](https://github.com/vllm-project/vllm) is a high-throughput inference and serving engine for LLMs. #### Install Libraries and Set up Serving + To install vllm, run ```bash @@ -200,6 +204,7 @@ bash vllm_script/vllm_setup.sh -m meta-llama/Llama-2-7b-chat-hf -p 8000 Please refer to the [supported models list](https://docs.vllm.ai/en/latest/models/supported_models.html) of vllm. #### How to use in AgentScope + Now you can load the model in AgentScope by the following model config: `vllm_script/model_config.json`. ```json @@ -216,13 +221,12 @@ Now you can load the model in AgentScope by the following model config: `vllm_sc } ``` - ## Model Inference API Both [Huggingface](https://huggingface.co/docs/api-inference/index) and [ModelScope](https://www.modelscope.cn) provide model inference API, which can be used with AgentScope post API model wrapper. Taking `gpt2` in HuggingFace inference API as an example, you can use the following model config in AgentScope. -```bash +```json { "type": "post_api", "name": 'gpt2', @@ -247,6 +251,4 @@ model.eval() agent = YourAgent(name='agent', model=model, tokenizer=tokenizer) ``` - - -[[Return to the top]](#using-different-model-sources-with-model-api) \ No newline at end of file +[[Return to the top]](#using-different-model-sources-with-model-api) diff --git a/docs/sphinx_doc/source/tutorial/204-service.md b/docs/sphinx_doc/source/tutorial/204-service.md index 7a185871a..448627a28 100644 --- a/docs/sphinx_doc/source/tutorial/204-service.md +++ b/docs/sphinx_doc/source/tutorial/204-service.md @@ -1,3 +1,5 @@ +(204-service)= + # Enhancing Agent Capabilities with Service Functions **Service functions**, often referred to simply as **Service**, constitute a versatile suite of utility tools that can be used to enhance the functionality of agents. A service is designed to perform a specific task like web search, code interpretation, or file processing. Services can be invoked by agents and other components for reuse across different scenarios. @@ -9,14 +11,14 @@ The design behind `Service` distinguishes them from typical Python functions. In ```python def demo_service() -> ServiceResponse: #do some specifc actions - # ...... - res = ServiceResponse({status=status, content=content}) - return res + # ...... + res = ServiceResponse({status=status, content=content}) + return res class ServiceResponse(dict): """Used to wrap the execution results of the services""" - # ... [code omitted for brevity] + # ... [code omitted for brevity] def __init__( self, @@ -130,5 +132,4 @@ class YourAgent(AgentBase): # ... [code omitted for brevity] ``` - -[[Return to the top]](#enhancing-agent-capabilities-with-service-functions) \ No newline at end of file +[[Return to the top]](#enhancing-agent-capabilities-with-service-functions) diff --git a/docs/sphinx_doc/source/tutorial/205-memory.md b/docs/sphinx_doc/source/tutorial/205-memory.md index cdeba4f7e..728bc1f29 100644 --- a/docs/sphinx_doc/source/tutorial/205-memory.md +++ b/docs/sphinx_doc/source/tutorial/205-memory.md @@ -1,3 +1,5 @@ +(205-memory)= + # Memory and Message Management **Message** represents individual pieces of information or interactions flowing between/within agents. **Memory** refers to the storage and retrieval of historical information and serves as the storage and management system for the messages. This allows the agent to remember past interactions, maintain context, and provide more coherent and relevant responses. @@ -48,9 +50,9 @@ The `Msg` ("Message") subclass extends `MessageBase` and represents a standard * ```python class Msg(MessageBase): - # ... [code omitted for brevity] + # ... [code omitted for brevity] - def to_str(self) -> str: + def to_str(self) -> str: return f"{self.name}: {self.content}" def serialize(self) -> str: @@ -66,7 +68,7 @@ The `Tht` ("Thought") subclass is a specialized form of `MessageBase` used for e ```python class Tht(MessageBase): - # ... [code omitted for brevity] + # ... [code omitted for brevity] def to_str(self) -> str: return f"{self.name} thought: {self.content}" @@ -93,7 +95,7 @@ class MemoryBase(ABC): recent_n: Optional[int] = None, filter_func: Optional[Callable[[int, dict], bool]] = None, ) -> Union[list, str]: - raise NotImplementedError + raise NotImplementedError def add(self, memories: Union[list[dict], dict]) -> None: raise NotImplementedError @@ -141,6 +143,4 @@ The `TemporaryMemory` class is a concrete implementation of `MemoryBase`, provid For more details about the usage of `Memory` and `Msg`, please refer to the API references. - - -[[Return to the top]](#memory-and-message-management) \ No newline at end of file +[[Return to the top]](#memory-and-message-management) diff --git a/docs/sphinx_doc/source/tutorial/206-prompt.md b/docs/sphinx_doc/source/tutorial/206-prompt.md index 56df050ef..de580de47 100644 --- a/docs/sphinx_doc/source/tutorial/206-prompt.md +++ b/docs/sphinx_doc/source/tutorial/206-prompt.md @@ -1,3 +1,5 @@ +(206-prompt)= + # Prompt Engine **Prompt** is a crucial component in interacting with language models, especially when seeking to generate specific types of outputs or guide the model toward desired behaviors. This tutorial will guide you through the use of the `PromptEngine` class, which simplifies the process of crafting prompts for LLMs. @@ -6,7 +8,7 @@ The `PromptEngine` class provides a structured way to combine different components of a prompt, such as instructions, hints, dialogue history, and user inputs, into a format that is suitable for the underlying language model. -### Key Features of PromptEngine: +### Key Features of PromptEngine - **Model Compatibility**: It works with any `ModelWrapperBase` subclass. - **Shrink Policy**: It offers two policies for handling prompts that exceed the maximum length: `ShrinkPolicy.TRUNCATE` to simply truncate the prompt, and `ShrinkPolicy.SUMMARIZE` to summarize part of the dialog history to save space. @@ -61,6 +63,4 @@ hint_prompt = "Find the weather in {location}." prompt = engine.join(system_prompt, user_input, hint_prompt, format_map=variables) ``` - - -[[Return to the top]](#prompt-engine) \ No newline at end of file +[[Return to the top]](#prompt-engine) diff --git a/docs/sphinx_doc/source/tutorial/207-monitor.md b/docs/sphinx_doc/source/tutorial/207-monitor.md index 79f496af3..3c0c436f1 100644 --- a/docs/sphinx_doc/source/tutorial/207-monitor.md +++ b/docs/sphinx_doc/source/tutorial/207-monitor.md @@ -1,3 +1,5 @@ +(207-monitor)= + # Monitor In multi-agent applications, particularly those that rely on external model APIs, it's crucial to monitor the usage and cost to prevent overutilization and ensure compliance with rate limits. The `MonitorBase` class and its implementation, `DictMonitor`, provide a way to track and regulate the usage of such APIs in your applications. In this tutorial, you'll learn how to use them to monitor API calls. @@ -95,6 +97,4 @@ Get the singleton instance of the monitor: monitor = MonitorFactory.get_monitor() ``` - - -[[Return to the top]](#monitoring-and-logging) \ No newline at end of file +[[Return to the top]](#monitoring-and-logging) diff --git a/docs/sphinx_doc/source/tutorial/208-distribute.md b/docs/sphinx_doc/source/tutorial/208-distribute.md index 66ca7bcb5..d96a95d7d 100644 --- a/docs/sphinx_doc/source/tutorial/208-distribute.md +++ b/docs/sphinx_doc/source/tutorial/208-distribute.md @@ -1,3 +1,5 @@ +(208-distribute)= + # Make Your Applications Distributed AgentScope is designed to be fully distributed, agent instances in one application can be deployed on different machines and run in parallel. This tutorial will introduce the features of AgentScope distributed and the distributed deployment method. @@ -144,4 +146,4 @@ while x is None or x.content != 'exit': x = b(x) ``` -[[Return to the top]](#make-your-applications-distributed) \ No newline at end of file +[[Return to the top]](#make-your-applications-distributed) diff --git a/docs/sphinx_doc/source/tutorial/301-community.md b/docs/sphinx_doc/source/tutorial/301-community.md index c4cae8faf..60cec1923 100644 --- a/docs/sphinx_doc/source/tutorial/301-community.md +++ b/docs/sphinx_doc/source/tutorial/301-community.md @@ -1,3 +1,5 @@ +(301-community)= + # Joining The AgentScope Community Becoming a part of the AgentScope community allows you to connect with other users and developers. You can share insights, ask questions, and keep up-to-date with the latest developments and interesting multi-agent applications. Here's how you can join us: @@ -22,13 +24,11 @@ Becoming a part of the AgentScope community allows you to connect with other use Our DingTalk group invitation: [AgentScope DingTalk Group](https://qr.dingtalk.com/action/joingroup?code=v1,k1,20IUyRX5XZQ2vWjKDsjvI9dhcXjGZi3bq1pFfDZINCM=&_dt_no_comment=1&origin=11) ## Wechat + Scan the QR code below on Wechat to join: AgentScope-wechat --- We welcome everyone interested in AgentScope to join our community and contribute to the growth of the platform! - - [[Return to the top]](#joining-the-agentscope-community) - diff --git a/docs/sphinx_doc/source/tutorial/302-contribute.md b/docs/sphinx_doc/source/tutorial/302-contribute.md index b33762323..79f9b98e0 100644 --- a/docs/sphinx_doc/source/tutorial/302-contribute.md +++ b/docs/sphinx_doc/source/tutorial/302-contribute.md @@ -1,3 +1,5 @@ +(302-contribute)= + # Contributing to AgentScope Our community thrives on the diverse ideas and contributions of its members. Whether you're fixing a bug, adding a new feature, improving the documentation, or adding examples, your help is welcome. Here's how you can contribute: @@ -5,6 +7,7 @@ Our community thrives on the diverse ideas and contributions of its members. Whe ## Report Bugs and Ask For New Features? Did you find a bug or have a feature request? Please first check the issue tracker to see if it has already been reported. If not, feel free to open a new issue. Include as much detail as possible: + - A descriptive title - Clear description of the issue - Steps to reproduce the problem @@ -64,6 +67,4 @@ We will review your pull request. This process might involve some discussion, ad Wait for us to review your pull request. We may suggest some changes or improvements. Keep an eye on your GitHub notifications and be responsive to any feedback. - - -[[Return to the top]](#contributing-to-agentScope) \ No newline at end of file +[[Return to the top]](#contributing-to-agentScope) diff --git a/docs/sphinx_doc/source/tutorial/advance.rst b/docs/sphinx_doc/source/tutorial/advance.rst index fdabbee99..ff483b9b2 100644 --- a/docs/sphinx_doc/source/tutorial/advance.rst +++ b/docs/sphinx_doc/source/tutorial/advance.rst @@ -1,5 +1,5 @@ Advanced Exploration -=============== +==================== .. toctree:: :maxdepth: 2 diff --git a/docs/sphinx_doc/source/tutorial/main.md b/docs/sphinx_doc/source/tutorial/main.md index bbb8fa546..0460e6b98 100644 --- a/docs/sphinx_doc/source/tutorial/main.md +++ b/docs/sphinx_doc/source/tutorial/main.md @@ -12,24 +12,24 @@ AgentScope is an innovative multi-agent platform designed to empower developers ### Getting Started -- [Installation Guide](tutorial/101-installation.md) -- [Fundamental Concepts](tutorial/102-concepts.md) -- [Getting Started with a Simple Example](tutorial/103-example.md) -- [Crafting Your First Application](tutorial/104-usecase.md) -- [Logging and WebUI](tutorial/105-logging.md) +- [Installation Guide](101-installation) +- [Fundamental Concepts](102-concepts) +- [Getting Started with a Simple Example](103-example) +- [Crafting Your First Application](104-usecase) +- [Logging and WebUI](105-logging) ### Advanced Exploration -- [Customizing Your Own Agent](tutorial/201-agent.md) -- [Agent Interactions: Dive deeper into Pipelines and Message Hub](tutorial/202-pipeline.md) -- [Using Different Model Sources with Model API](tutorial/203-model.md) -- [Enhancing Agent Capabilities with Service Functions](tutorial/204-service.md) -- [Memory and Message Management](tutorial/205-memory.md) -- [Prompt Engine](tutorial/206-prompt.md) -- [Monitoring](tutorial/207-monitor.md) -- [Distributed Deployment](tutorial/208-distribute.md) +- [Customizing Your Own Agent](201-agent) +- [Agent Interactions: Dive deeper into Pipelines and Message Hub](202-pipeline) +- [Using Different Model Sources with Model API](203-model) +- [Enhancing Agent Capabilities with Service Functions](204-service) +- [Memory and Message Management](205-memory) +- [Prompt Engine](206-prompt) +- [Monitoring](207-monitor) +- [Distributed Deployment](208-distribute) ### Getting Involved -* [Joining The AgentScope Community](tutorial/301-community.md) -* [Contributing to AgentScope](tutorial/302-contribute.md) \ No newline at end of file +- [Joining The AgentScope Community](301-community) +- [Contributing to AgentScope](302-contribute) From 5c927effeadf91099038fe1326aaa7471bc4634d Mon Sep 17 00:00:00 2001 From: "panxuchen.pxc" Date: Fri, 19 Jan 2024 18:06:01 +0800 Subject: [PATCH 18/18] update doc workflow --- .github/workflows/sphinx_docs.yml | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/.github/workflows/sphinx_docs.yml b/.github/workflows/sphinx_docs.yml index 6e533b9db..90a519c53 100644 --- a/.github/workflows/sphinx_docs.yml +++ b/.github/workflows/sphinx_docs.yml @@ -5,8 +5,9 @@ on: types: [opened, synchronize] paths: - 'docs/**/*' - release: - types: [published] + push: + branches: + - main jobs: pages: @@ -36,7 +37,7 @@ jobs: name: SphinxDoc path: ${{ steps.deployment.outputs.artifact }} - uses: peaceiris/actions-gh-pages@v3 - if: github.event_name == 'release' + if: github.event_name == 'push' && github_ref == 'refs/heads/main' with: github_token: ${{ secrets.GITHUB_TOKEN }} publish_dir: ${{ steps.deployment.outputs.artifact }} \ No newline at end of file