Add TaskWeaver website (#86)

.github/workflows/deploy-website.yaml

@@ -0,0 +1,42 @@
+name: docs
+
+on:
+  push:
+    branches: [main]
+    path:
+      - 'website/*'
+      - '.github/workflows/deploy-website.yml'
+  workflow_dispatch:
+  merge_group:
+    types: [checks_requested]
+
+jobs:
+  gh-release:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: website
+    steps:
+      - uses: actions/checkout@v3
+      - name: Use Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: 20.x
+      - name: Build website
+        run: |
+          if [ -e yarn.lock ]; then
+          yarn install --frozen-lockfile --ignore-engines
+          yarn build
+          elif [ -e package-lock.json ]; then
+          npm ci
+          npm run build
+          else
+          npm i --legacy-peer-deps
+          npm run build
+          fi
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          # Build output to publish to the `gh-pages` branch:
+          publish_dir: ./website/build

README.md

@@ -5,101 +5,46 @@
 A **code-first** agent framework for seamlessly planning and executing data analytics tasks. 
 This innovative framework interprets user requests through coded snippets and efficiently 
 coordinates a variety of plugins in the form of functions to execute 
-data analytics tasks
-
-**Highlighted Features**
-
-- [x] **Rich data structure** - TaskWeaver allows you to work with rich data 
-    structures in Python, such as DataFrames, instead of having to work with 
-    text strings.
-- [x] **Customized algorithms** - TaskWeaver allows you to encapsulate your 
-    own algorithms into plugins (in the form of Python functions), 
-    and orchestrate them to achieve complex tasks.
-- [x] **Incorporating domain-specific knowledge** - TaskWeaver is designed to 
-    be easily incorporating domain-specific knowledge, such as the knowledge 
-    of execution flow, to improve the reliability of the AI copilot.
-- [x] **Stateful conversation** - TaskWeaver is designed to support stateful 
-    conversation. It can remember the context of the conversation and 
-    leverage it to improve the user experience.
-- [x] **Code verification** - TaskWeaver is designed to verify the generated code 
-    before execution. It can detect potential issues in the generated code 
-    and provide suggestions to fix them.
-- [x] **Easy to use** - TaskWeaver is designed to be easy to use. 
-    We provide a set of sample plugins and a tutorial to help you get started.
-    Users can easily create their own plugins based on the sample plugins.
-    TaskWeaver offers an open-box experience, allowing users to run a service immediately after installation.
-- [x] **Easy to debug** - TaskWeaver is designed to be easy to debug. 
-    We have detailed logs to help you understand what is going on during calling the LLM, 
-    the code generation, and execution process.
-- [x] **Security consideration** - TaskWeaver supports a basic session management to keep
-    different users' data separate. The code execution is separated into different processes in order not to interfere with each other.
-- [x] **Easy extension** - TaskWeaver is designed to be easily extended to accomplish 
-    more complex tasks. You can create multiple AI copilots to
-    act in different roles, and orchestrate them to achieve complex tasks.
-
-# News
-
-- [2023-12-12] A simple UI demo is available in playground/UI folder, try with the [README](/playground/UI/README.md)
-- [2023-11-30] TaskWeaver is released on GitHub🎈. 
-
-
-# Getting started
-
-## Prerequisites
-
-- Python 3.10 or above
-- OpenAI (or Azure OpenAI) access with GPT-3.5 above models. However, it is strongly recommended to use the GPT-4, which is more stable.
-- Other requirements can be found in the `requirements.txt` file. 
-
-> OpenAI API had a major [update](https://github.com/openai/openai-python) from 0.xx to 1.xx in November 2023. 
-> Please make sure you are not using an old version because the API is not backward compatible.
+data analytics tasks.
 
+# News🆕
+- 📅2023-12-21: TaskWeaver now supports a number of LLMs, such as LiteLLM, Ollama, Gemini, and QWen🎈.
+- 📅2023-12-21: TaskWeaver Website is now [available](https://microsoft.github.io/TaskWeaver/) with more documentations.
+- 📅2023-12-12: A simple UI demo is available in playground/UI folder, try it [here](https://microsoft.github.io/TaskWeaver/docs/usage/webui)!
+<!-- - [2023-11-30] TaskWeaver is released on GitHub🎈.  -->
+
+
+## Highlights
+
+- [x] **Rich data structure** - TaskWeaver allows you to work with rich data structures in Python, such as DataFrames, instead of dealing with strings.
+- [x] **Customized algorithms** - TaskWeaver allows you to encapsulate your own algorithms into plugins and orchestrate them.
+- [x] **Incorporating domain-specific knowledge** - TaskWeaver is designed to incorporat domain-specific knowledge easily to improve the reliability.
+- [x] **Stateful execution** - TaskWeaver is designed to support stateful execution of the generated code to ensure consistent and smooth user experience.
+- [x] **Code verification** - TaskWeaver is designed to verify the generated code before execution. It can detect potential issues in the generated code and provide suggestions to fix them.
+- [x] **Easy to use** - TaskWeaver is easy to use with sample plugins, examples and tutorials to help you get started. TaskWeaver offers an open-box experience, allowing users to run it immediately after installation.
+- [x] **Easy to debug** - TaskWeaver is easy to debug with detailed and transparent logs to help you understand the entire process, including LLM prompts, the code generation, and execution process.
+- [x] **Security consideration** - TaskWeaver supports a basic session management to keep different users' data separate. The code execution is separated into different processes to avoid mutal interference.
+- [x] **Easy extension** - TaskWeaver is easy to extend to accomplish more complex tasks with multiple agents as the plugins.
 
 ## Quick Start
 
 ### Installation
-You can install TaskWeaver by running the following command:
+TaskWeaver requires **Python >= 3.10**. It can be installed by running the following command:
 ```bash
+# [optional to create conda environment]
+# conda create -n taskweaver python=3.10
+# conda activate taskweaver
+
+# clone the repository
 git clone https://github.com/microsoft/TaskWeaver.git
 cd TaskWeaver
 # install the requirements
 pip install -r requirements.txt
 ```
 
 
-### Project Directory
-TaskWeaver runs as a process, you need to create a project directory to store plugins and configuration files. 
-We provided a sample project directory in the `project` folder. You can copy the `project` folder to your workspace.
-A project directory typically contains the following files and folders:
-
-```bash
-📦project
- ┣ 📜taskweaver_config.json # the configuration file for TaskWeaver
- ┣ 📂plugins # the folder to store plugins
- ┣ 📂planner_examples # the folder to store planner examples
- ┣ 📂codeinterpreter_examples # the folder to store code interpreter examples
- ┣ 📂sample_data # the folder to store sample data used for evaluations
- ┣ 📂logs # the folder to store logs, will be generated after program starts
- ┗ 📂workspace # the directory stores session data， will be generated after program starts
-    ┗ 📂 session_id 
-      ┣ 📂ces # the folder used by the code execution service
-      ┗ 📂cwd # the current working directory to run the generated code
-```
-
-### OpenAI Configuration
-Before running TaskWeaver, you need to provide your OpenAI API key and other necessary information. 
-You can do this by editing the `taskweaver_config.json` file. 
-If you are using Azure OpenAI, you need to set the following parameters in the `taskweaver_config.json` file:
-#### Azure OpenAI
-```json
-{
-"llm.api_base": "https://xxx.openai.azure.com/",
-"llm.api_key": "your_api_key",
-"llm.api_type": "azure",
-"llm.api_version": "the api version",
-"llm.model": "the model name, e.g., gpt-4"
-}
-```
+### Configure the LLMs
+Before running TaskWeaver, you need to provide your LLM configurations. Taking OpenAI as an example, you can configure `taskweaver_config.json` file as follows. 
 
 #### OpenAI
 ```json
@@ -108,15 +53,14 @@ If you are using Azure OpenAI, you need to set the following parameters in the `
 "llm.model": "the model name, e.g., gpt-4"
 }
 ```
->💡 Only the latest OpenAI API supports the `json_object` response format. 
-> If you are using an older version of OpenAI API, you need to set the `llm.response_format` to `null`.
 
-More configuration options can be found in the [configuration documentation](docs/configuration.md).
+💡 TaskWeaver also supports other LLMs and advanced configurations, please check the [documents](https://microsoft.github.io/TaskWeaver/docs/overview) for more details. 
 
 ### Start TaskWeaver
+
+#### 1. Command Line Interaction
 ```bash
-# assume you are in the taskweaver folder
-# -p is the path to the project directory
+# assume you are in the cloned TaskWeaver folder
 python -m taskweaver -p ./project/
 ```
 This will start the TaskWeaver process and you can interact with it through the command line interface. 
@@ -134,7 +78,22 @@ TaskWeaver: I am TaskWeaver, an AI assistant. To get started, could you please e
 Human: ___
 ```
 
-### Two Walkthrough Examples
+#### 2. Web UI 
+TaskWeaver also supports WebUI for demo purpose, please refers to [web UI docs](https://microsoft.github.io/TaskWeaver/docs/usage/webui) for more details.
+
+#### 3. Import as a Library
+TaskWeaver can be imported as a library to integrate with your existing project, more information can be found in [docs](https://microsoft.github.io/TaskWeaver/docs/usage/library)
+
+## Documentation
+More documentations can be found on [TaskWeaver Website](https://microsoft.github.io/TaskWeaver).
+
+
+
+---
+---
+
+
+## Demo Examples
 
 
 
@@ -178,47 +137,6 @@ For more examples, please refer to our [paper](http://export.arxiv.org/abs/2311.
 > 💡 The planning of TaskWeaver are based on the LLM model. Therefore, if you want to repeat the examples, the execution process may be different
 > from what you see in the videos. Typically, more concrete prompts will help the model to generate better plans and code.
 
-## How to use TaskWeaver in your project
-
-### Using TaskWeaver as a library
-After cloning the TaskWeaver repository, you can install TaskWeaver as a library by running the following command:
-```bash
-# clone the repository
-cd TaskWeaver
-pip install -e .
-```
-Then, you can follow the [documentation](docs/taskweaver_as_a_lib.md) to use TaskWeaver in your code.
-
-### Using TaskWeaver as a service
-TaskWeaver can be used as a service that can be called by other programs. More details are TBD.
-
-## Customizing TaskWeaver
-
-There are two ways to customize TaskWeaver: creating plugins and creating examples. 
-
-### Creating Plugins
-
-Since TaskWeaver can already perform some basic tasks, you can create plugins to extend its capabilities.
-A plugin is a python function that takes a set of arguments and returns a set of results.
-
-Typically, you only need to write a plugin in the following example scenarios:
-- You want to encapsulate your own algorithm into a plugin.
-- You want to import a python package that is not supported by TaskWeaver.
-- You want to connect to an external data source to pull data.
-- You want to query a web API.
-
-Refer to the [plugin documentation](docs/plugin.md) for more details. Otherwise, you can leverage TaskWeaver's code generation capability to perform tasks.
-
-### Creating Examples
-
-The purpose of examples is to help LLMs understand how to perform tasks especially when 
-the tasks are complex and need domain-specific knowledge.
-
-There are two types of examples: (1) planning examples and (2) code interpreter examples.
-Planning examples are used to demonstrate how to use TaskWeaver to plan for a specific task.
-Code generation examples are used to demonstrate how to generate code or orchestrate plugins to perform a specific task.
-
-Refer to the [example documentation](docs/example.md) for more details.
 
 ## Citation
 Our paper could be found [here](http://export.arxiv.org/abs/2311.17541). 

taskweaver/llm/google_genai.py

@@ -135,16 +135,29 @@ def _chat_completion(
         **kwargs: Any,
     ) -> Generator[ChatMessageType, None, None]:
         genai_messages = []
+        prev_role = ""
         for msg in messages:
-            if msg["role"] == "system" or msg["role"] == "user":
+            if msg["role"] == "system":
                 genai_messages.append({"role": "user", "parts": [msg["content"]]})
+                genai_messages.append(
+                    {
+                        "role": "model",
+                        "parts": ["I understand your requirements, and I will assist you in the conversations."],
+                    },
+                )
+                prev_role = "model"
+            elif msg["role"] == "user":
+                if prev_role == "user":
+                    # a placeholder to create alternating user and model messages
+                    genai_messages.append({"role": "model", "parts": ["  "]})
+                genai_messages.append({"role": "user", "parts": [msg["content"]]})
+                prev_role = "user"
             elif msg["role"] == "assistant":
                 genai_messages.append({"role": "model", "parts": [msg["content"]]})
+                prev_role = "model"
+            else:
+                raise Exception(f"Invalid role: {msg['role']}")
 
-        genai_messages.insert(
-            1,
-            {"role": "model", "parts": ["I understand your requirements, and I will assist you in the conversations."]},
-        )
         if stream is False:
             response = self.model.generate_content(genai_messages, stream=False)
             yield format_chat_message("assistant", response.text)