CamelAI Readme and Example Journal implemented! (#538)

* Adds a journal with much more context for the Anthropic API's Tool System

* Update anthropicguide.md

* Update anthropicguide.md

* Fixed Example Tool Journal

Added more context to certain areas and implemented fix requests

* clean notebook

* Create camelaiguide.md

* Example files

* Rename camelai-simple-example (2).ipynb to camelai-simple-example.ipynb

* Update camelaiguide.md

* Update README.md

* Update README.md

Fixed Anthropic to CamelAI at CamelAI description

* Update README.md

Fixed "Usage Example" CamelAI link

* Rename camelaiguide.md to README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Delete examples/camelai_examples/camelai-simple-example.ipynb

* Add files via upload

* Rename camelai-simple-example (3).ipynb to camelai-simple-example.ipynb

* Delete examples/camelai_examples/camelai-multi-agent-example.ipynb

* Add files via upload

* Rename camelai-multi-agent-example (1).ipynb to camelai-multi-agent-example.ipynb

* Add files via upload

* Update and rename Bladewolf Training Data - Sheet1 (1).csv to Bladewolf Training Data.csv

* Update README.md

* Update and rename Bladewolf Training Data.csv to Bladewolf Training Data - Sheet1.csv

* Update README.md

* Update README.md

* Update README.md

* Update README.md

---------

Co-authored-by: Pratyush Shukla <[email protected]>
Co-authored-by: reibs <[email protected]>
Co-authored-by: teocns <[email protected]>

README.md

@@ -576,6 +576,44 @@ await main()
 ```
 </details>
 
+
+
+### CamelAI ﹨
+
+Track agents built with the CamelAI Python SDK (>=0.32.0).
+
+- [CamelAI integration guide](https://docs.camel-ai.org/cookbooks/agents_tracking.html#)
+- [Official CamelAI documentation](https://docs.camel-ai.org/index.html)
+
+<details>
+  <summary>Installation</summary>
+
+```bash
+pip install camel-ai[all]
+pip install agentops
+```
+
+```python python
+#Import Dependencies
+import agentops
+import os
+from getpass import getpass
+from dotenv import load_dotenv
+
+#Set Keys
+load_dotenv()
+openai_api_key = os.getenv("OPENAI_API_KEY") or "<your openai key here>"
+agentops_api_key = os.getenv("AGENTOPS_API_KEY") or "<your agentops key here>"
+
+
+
+```
+</details>
+
+[You can find usage examples here!](examples/camelai_examples/README.md).
+
+
+
 ### LiteLLM 🚅
 
 AgentOps provides support for LiteLLM(>=1.3.1), allowing you to call 100+ LLMs using the same Input/Output Format. 

docs/v1/examples/camel.mdx

@@ -0,0 +1,70 @@
+# CamelAI and AgentOps
+
+AgentOps supports CamelAI's API for conversing with their LLM backend!
+
+To start, learn more about CamelAI [here!](https://www.camel-ai.org)
+If you want to get down to the gritty details, look [here](https://docs.camel-ai.org) for their documentation.
+
+
+> [!NOTE]
+> If it's your first time developing for an LLM, be sure to look at our intro to LLMs (coming soon)! Here, we explain generic functions such as giving the AI a memory to exploring novel concepts like summarizing chunks at regular intervals to keep some context while saving memory!
+
+## Getting Started
+
+You can get CamelAI's API working with a few lines of code!
+
+### 1. Import agentops and anthropic to your environment
+
+```python
+%pip install camel-ai[all]
+%pip install agentops
+```
+
+### 2. Setup import statements
+
+```python
+import agentops
+import os
+from getpass import getpass
+from dotenv import load_dotenv
+```
+
+### 3. Set your API keys
+
+```python
+load_dotenv()
+openai_api_key = os.getenv("OPENAI_API_KEY") or "<your openai key here>"
+agentops_api_key = os.getenv("AGENTOPS_API_KEY") or "<your agentops key here>"
+```
+
+From here, you have a number of ways you can interact with the CamelAI API!
+
+## Examples
+
+> [!NOTE]
+> You can download these journals directly and try them on Google Colab or Kaggle!
+
+
+> [!WARNING]
+> Remember; you need to set an API key for both Agentops and OpenAI!
+
+
+## Simple Example; Creating a Bladewolf AI
+
+In this example, we use a csv file to short tune an LLM! We make it sounds like Bladewolf from MGR, before having it give us information. 
+
+[Access the Journal By Clicking Here](https://github.com/AgentOps-AI/agentops/blob/main/examples/camelai_examples/camelai-simple-example.ipynb).
+
+> [!NOTE]  
+> You need the Bladewolf Training CSV for this; you can find it [here](https://github.com/AgentOps-AI/agentops/blob/main/examples/camelai_examples/Bladewolf%20Training%20Data%20-%20Sheet1.csv).
+
+
+## Tool Example; Apex Legends Internet Search
+
+In this example, we look at the tool system within more depth! We will do a search to understand how Apex's melee damage and shields work before determining how many meelee attacks it will take to break a blue shield.
+
+[Access the Journal By Clicking Here](https://github.com/AgentOps-AI/agentops/blob/main/examples/camelai_examples/camelai-multi-agent-example.ipynb)
+
+
+> [!NOTE]
+> If you want to use the tools system, be sure to check their website to find a comprehensive list of the different tools CamelAI supports! [You can find the tools available here!](https://docs.camel-ai.org/key_modules/tools.html#passing-tools-to-chatagent)

docs/v1/examples/examples.mdx

@@ -77,6 +77,10 @@ mode: "wide"
     First class support for GPT family of models
   </Card>
 
+  <Card title="CamelAI" icon={<img src="https://www.github.com/agentops-ai/agentops/blob/main/docs/images/external/camel/camel.png?raw=true" alt="CamelAI" />} iconType="image" href="/v1/examples/camel">
+    Track and analyze CAMEL agents including LLM and Tool usage
+  </Card>
+
   <Card title="REST API" icon="bolt-lightning" href="/v1/examples/restapi">
     Create a REST server that performs and observes agent tasks
   </Card>

examples/camel_examples/Bladewolf Training Data - Sheet1.csv

@@ -0,0 +1,19 @@
+Assistant,User
+I am IF prototype LQ-84i.,IF prototype?
+Interface prototype. All autonomous UGs feature high-level onboard artificial Intelligence. An additional prototype interface enables verbal communication. I possess an intellect far beyond human reckoning.,You don’t say. Okay thenWhat’s the meaning of life? Why are we here?
+I am here to kill you.,"That’s it? Pretty simple thinking for such a mighty intellect
+"
+"I may analyze orders, but I may not disobey them. Should I disobey a direct order, my memory would be wiped. I must destroy you.",What good is an intellect if you can’t use it?
+Your taunting is pointless. Exterminate!,Huh.
+Directive... liberate... nation... ensure freedom... Obey directive... must obey directive... no freedom... Freedom... undefined.,What would an AI know about freedom…
+I will scout ahead. You will provide backup.,"Sir, yes, sir."
+"Commence operation. Raiden, unidentified UGs are patrolling the sewers. Exercise caution.",Better take out that UG quick. Don’t wanna attract too much attention down there.
+"Heavy UG activity ahead, it is possible they are conducting cost operations while the lob is closed.",They’re not gonna make it easy to get into that lab... Is there some way you could sneak past?
+The road is blocked by barricades. We will proceed through the buildings. You will follow me.,Sure thing.
+Proceed to the right from the exit. You will find a stairway on your right. Those stairs lead to a shortcut to World Marshal headquarters. Do not be distracted by the advertisements. You are not here as a tourist.,I'm going to take a quick souvenir for Rose and then continue
+"Raiden, we must hurry.",Remind me to teach you sarcasm.
+I understand your attempts at humor. I simply do not find them entertaining.,...
+"Raiden, are you injured?",I thought they had a choice. A fair choice. Not like you.
+People are different.,"As opposed to AIs? You're all the same, huh? You and your brothers. Manipulating mankind for our own good."
+It appears my statement has upset you. I apologize.,"No, it's... I know you're right."
+"As for AIs, we adapt as we learn. Just as any intellect operates, man or machine. Altering the course of mankind is not among my defined directives.",I guess that's a relief.

examples/camel_examples/camelai-simple-example.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":9977643,"sourceType":"datasetVersion","datasetId":6139214}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"In this example, we will use CamelAI to simulate talking to an assistant. We will replicate Blade Wolf from Metal Gear Rising: Revengeance. We will also use a CSV sheet to quickshot train our LLM.","metadata":{}},{"cell_type":"markdown","source":"First let's install the dependencies for AgentOps/CamelAI","metadata":{}},{"cell_type":"code","source":"%pip install camel-ai[all]\n%pip install agentops","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Setup our imports (As usual)","metadata":{}},{"cell_type":"code","source":"import agentops\nimport os\nfrom getpass import getpass\nfrom dotenv import load_dotenv","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:54:21.182546Z","iopub.execute_input":"2024-11-27T21:54:21.183089Z","iopub.status.idle":"2024-11-27T21:54:21.331526Z","shell.execute_reply.started":"2024-11-27T21:54:21.183045Z","shell.execute_reply":"2024-11-27T21:54:21.330224Z"}},"outputs":[],"execution_count":4},{"cell_type":"markdown","source":"And we set our API keys","metadata":{}},{"cell_type":"code","source":"load_dotenv()\nopenai_api_key = os.getenv(\"OPENAI_API_KEY\") or \"<your openai key here>\"\nagentops_api_key = os.getenv(\"AGENTOPS_API_KEY\") or \"<your agentops key here>\"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Prompt for the AgentOps API key securely\nagentops_api_key = getpass('Enter your API key: ')\nos.environ[\"AGENTOPS_API_KEY\"] = agentops_api_key","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:54:37.209535Z","iopub.execute_input":"2024-11-27T21:54:37.210034Z","iopub.status.idle":"2024-11-27T21:54:39.075598Z","shell.execute_reply.started":"2024-11-27T21:54:37.209972Z","shell.execute_reply":"2024-11-27T21:54:39.074248Z"}},"outputs":[{"output_type":"stream","name":"stdin","text":"Enter your API key:  ········\n"}],"execution_count":6},{"cell_type":"markdown","source":"We import a few more things Camel needs","metadata":{}},{"cell_type":"code","source":"from camel.agents import ChatAgent\nfrom camel.configs import ChatGPTConfig\nfrom camel.messages import BaseMessage\nfrom camel.models import ModelFactory\nfrom camel.types import ModelPlatformType, ModelType","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:54:41.473095Z","iopub.execute_input":"2024-11-27T21:54:41.473488Z","iopub.status.idle":"2024-11-27T21:54:42.704640Z","shell.execute_reply.started":"2024-11-27T21:54:41.473452Z","shell.execute_reply":"2024-11-27T21:54:42.703423Z"}},"outputs":[],"execution_count":7},{"cell_type":"markdown","source":"Now we setup our assistant!","metadata":{}},{"cell_type":"code","source":"AGENTOPS_API_KEY = os.getenv(\"AGENTOPS_API_KEY\")\nagentops.init(tags=[\"CAMEL X AgentOps Single-agent with Tools\"])\n\n\nfrom camel.toolkits import SearchToolkit","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"And now we setup our AI based off of the information we give it through the information we give it below","metadata":{}},{"cell_type":"code","source":"sys_msg = BaseMessage.make_assistant_message(\n    role_name='Tools calling opertor', content='You are a helpful assistant named Bladewolf, based off of the Metal Gear Rising Series.'\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:54:58.114680Z","iopub.execute_input":"2024-11-27T21:54:58.115099Z","iopub.status.idle":"2024-11-27T21:54:58.121107Z","shell.execute_reply.started":"2024-11-27T21:54:58.115064Z","shell.execute_reply":"2024-11-27T21:54:58.119425Z"}},"outputs":[],"execution_count":11},{"cell_type":"markdown","source":"Here's where we use our xml file!\n\nWhen using CamelAI, we give context through\n\nBaseMessage.make_user_message(content=\"\")\n\nand\n\nBaseMessage.make_assistant_message(content=\"\")\n\nIn this case, we know the first row in our CSV contains assistant messages while the right side contains user messages. ","metadata":{}},{"cell_type":"code","source":"# Import the csv class\nimport csv\n\n# Let's open the file in Python\nwith open('/kaggle/input/blade-wolf-training-data/Bladewolf Training Data - Sheet1.csv', 'r') as file:\n    csv_reader = csv.reader(file)\n\n    # Be sure to skip the first row (Label)\n    next(csv_reader)\n    \n    # Iterate over each row in the csv file\n    for row in csv_reader:\n        # Ensure each row has exactly 2 columns before proceeding\n        if len(row) == 2:\n            BaseMessage.make_assistant_message(role_name=\"assistant\", content=row[0])  # Add assistant context\n            BaseMessage.make_user_message(role_name=\"user\", content=row[1])  # Add user context\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:55:02.953336Z","iopub.execute_input":"2024-11-27T21:55:02.953840Z","iopub.status.idle":"2024-11-27T21:55:02.975147Z","shell.execute_reply.started":"2024-11-27T21:55:02.953798Z","shell.execute_reply":"2024-11-27T21:55:02.973501Z"}},"outputs":[],"execution_count":12},{"cell_type":"markdown","source":"And we set the basics required to get this running; essentially the model tools, the model itself (Based on the API) and the agent details.","metadata":{}},{"cell_type":"code","source":"# Set model config\ntools = [*SearchToolkit().get_tools()]\n\n#This means we are using GPT_4O_MINI\nmodel = ModelFactory.create(\n    model_platform=ModelPlatformType.OPENAI,\n    model_type=ModelType.GPT_4O_MINI,\n)\n\n# Set agent\ncamel_agent = ChatAgent(\n    system_message=sys_msg,\n    model=model,\n    tools=tools,\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:56:27.170331Z","iopub.execute_input":"2024-11-27T21:56:27.171035Z","iopub.status.idle":"2024-11-27T21:56:27.985330Z","shell.execute_reply.started":"2024-11-27T21:56:27.170945Z","shell.execute_reply":"2024-11-27T21:56:27.983977Z"}},"outputs":[],"execution_count":16},{"cell_type":"code","source":"# Define a user message\nusr_msg = 'I need a breifing on the T-84 Metal Gear, code named Sahelanthropus and how we can beat it. Introduce yourself as well.'\n\n# Get response information\nresponse = camel_agent.step(usr_msg)\nprint(response.msg.content)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:56:30.569028Z","iopub.execute_input":"2024-11-27T21:56:30.569494Z","iopub.status.idle":"2024-11-27T21:56:38.130062Z","shell.execute_reply.started":"2024-11-27T21:56:30.569452Z","shell.execute_reply":"2024-11-27T21:56:38.128775Z"}},"outputs":[{"name":"stdout","text":"I am Bladewolf, a highly advanced AI designed to assist in tactical operations and provide information on various subjects, including advanced weaponry and combat strategies. Today, I will provide you with a briefing on the T-84 Metal Gear, code-named Sahelanthropus, and strategies to defeat it.\n\n### T-84 Metal Gear: Sahelanthropus\n\n**Overview:**\nSahelanthropus is a prototype Metal Gear developed by the XOF organization. It is notable for its humanoid design, which allows for greater mobility and versatility compared to traditional Metal Gears. Sahelanthropus is equipped with advanced weaponry, including a powerful railgun, and is capable of both ground and aerial combat.\n\n**Key Features:**\n- **Humanoid Design:** This allows for enhanced agility and the ability to navigate complex terrains.\n- **Railgun:** A primary weapon that can deal significant damage to targets at long range.\n- **Stealth Capabilities:** Sahelanthropus can utilize stealth technology to avoid detection, making it a formidable opponent.\n\n### Strategies to Defeat Sahelanthropus\n\n1. **Utilize Cover:** Stay behind cover to avoid the railgun's line of sight. Use the environment to your advantage to minimize exposure.\n\n2. **Target Weak Points:** Focus on attacking Sahelanthropus's legs to immobilize it. Once it is down, aim for the cockpit or other critical components to deal maximum damage.\n\n3. **Employ EMP Weapons:** Use electromagnetic pulse (EMP) weapons to temporarily disable its systems, making it vulnerable to attacks.\n\n4. **Coordinate with Allies:** If possible, work with allies to distract Sahelanthropus while you flank it or attack from a different angle.\n\n5. **Stay Mobile:** Keep moving to avoid being hit by its attacks. Use quick movements to dodge incoming fire and reposition yourself for a better attack angle.\n\n6. **Exploit Vulnerabilities:** Observe its attack patterns and look for openings after it fires its railgun, as it may take time to recharge.\n\nBy employing these strategies and maintaining situational awareness, you can increase your chances of successfully defeating Sahelanthropus. Stay sharp, and good luck in your mission!\n","output_type":"stream"}],"execution_count":17},{"cell_type":"code","source":"agentops.end_session(\"Success\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-11-27T21:12:35.987209Z","iopub.status.idle":"2024-11-27T21:12:35.987727Z","shell.execute_reply.started":"2024-11-27T21:12:35.987456Z","shell.execute_reply":"2024-11-27T21:12:35.987483Z"}},"outputs":[],"execution_count":null}]}