Merge pull request #23 from AgentOps-AI/autogen-research

added some autogen template code and readme

Author: bboynton97

README.md

@@ -13,6 +13,10 @@ If you have questions or need help, please ask in our [Discord community](https:
 
 > 🛠️🚨 AgentStack is in open preview. We're building in public, use at your own risk but have fun :)
 
+AgentStack serves as a great tool for starting your agent project and offers many CLI utilities for easy code-gen throughout the development process.
+
+AgentStack is _not_ a low-code alternative to development. Developers will still need an understanding of how to build with their selected agent framework.
+
 ## Quick Overview
 
 ```sh
@@ -73,12 +77,14 @@ Runs the agent project in development mode.<br>
 
 ## Philosophy
 
-- **Agents should be easy:** There are so many frameworks out there, but starting from scratch is a pain. Similar to Create React App, AgentStack aims to simplify the "from scratch" process by giving you a simple boilerplate of an agent. It uses popular agent frameworks and LLM providers, but provides a cohesive curated experience on top of them.
+- **Agents should be easy:** There are so many frameworks out there, but starting from scratch is a pain. Similar to `create-react-app`, AgentStack aims to simplify the "from scratch" process by giving you a simple boilerplate of an agent. It uses popular agent frameworks and LLM providers, but provides a cohesive curated experience on top of them.
 
 - **No Configuration Required:** You don't need to configure anything. A reasonably good configuration of both development and production builds is handled for you so you can focus on writing code.
 
 - **No Lock-In:** You can customize your setup at any time. AgentStack is designed to make it easy to get the components you need running right off the bat; it's up to you what to do next.
 
+AgentStack is not designed to be a low-code solution to building agents. Instead it is a great head-start for starting an agent project from scratch. 
+
 ## What's Included?
 
 Your environment will have everything you need to build a modern AI agent project:
@@ -92,16 +98,24 @@ Your environment will have everything you need to build a modern AI agent projec
 - Hassle-free updates for the above tools with a single dependency.
 
 ## Roadmap
-* Frameworks
-  * Autogen
-  * LiteLLM
-  * Swarms (OpenAI)
-* Tools
-  * MultiOn
-  * Firecrawl
-  * Anon
-  * E2B
-  * More
+
+### Frameworks
+
+#### CrewAI
+Development of AgentStack is being done primarily on [CrewAI](https://crewai.com).
+
+#### AutoGen
+Some work has been done to add Microsoft's [AutoGen](https://microsoft.github.io/autogen/0.2/), although these efforts have been paused. AutoGen is currently in the process of making [large design decisions](https://microsoft.github.io/autogen/dev/) that will effect the integration with AgentStack.
+
+### Tools
+Many tools are currently supported. The short-term roadmap includes:
+* MultiOn
+* Firecrawl
+* Anon
+* E2B
+* More
+
+### Other Features
 * Generated testing
 * Integrated benchmarking
 

agentstack/generation/agent_generation.py

@@ -92,7 +92,7 @@ def generate_crew_agent(
         f"def {name}(self) -> Agent:",
         "    return Agent(",
         f"        config=self.agents_config['{name}'],",
-        "        tools=[],  # add tools here or use `agentstack tools add <tool_name>",
+        "        tools=[],  # add tools here or use `agentstack tools add <tool_name>",  # TODO: Add any tools in agentstack.json
         "        verbose=True",
         "    )",
         ""

agentstack/templates/autogen/{{cookiecutter.project_metadata.project_slug}}/.gitignore

@@ -162,3 +162,4 @@ cython_debug/
 #.idea/
 
 .agentops/
+OAI_CONFIG_LIST

agentstack/templates/autogen/{{cookiecutter.project_metadata.project_slug}}/OAI_CONFIG_LIST

@@ -0,0 +1,7 @@
+[
+    {
+        "model": "gpt-4",
+        "api_key": "<your_key>",
+        "tags": ["gpt-4", "tool"]
+    }
+]

agentstack/templates/autogen/{{cookiecutter.project_metadata.project_slug}}/pyproject.toml

@@ -8,6 +8,4 @@ license = "{{cookiecutter.project_metadata.license}}"
 [tool.poetry.dependencies]
 python = "^3.11"
 agentops = "^0.3.12"
-{%- if cookiecutter.framework == "crewai" %}
-crewai = "^0.63.6"
-{%- endif %}
+autogen-agentchat = "~0.2"

agentstack/templates/autogen/{{cookiecutter.project_metadata.project_slug}}/src/main.py

@@ -0,0 +1,62 @@
+from typing import Annotated, Literal
+
+import agentops
+
+from autogen import ConversableAgent, UserProxyAgent, config_list_from_json, register_function
+
+agentops.init()
+
+
+def main():
+    # Load LLM inference endpoints from an env variable or a file
+    # See https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints
+    # and OAI_CONFIG_LIST_sample.
+    # For example, if you have created a OAI_CONFIG_LIST file in the current working directory, that file will be used.
+    config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
+
+    {%- for agent in cookiecutter.structure.agents %}
+
+    {{agent.name}}_agent = ConversableAgent(
+        name="{{agent.name}}",
+        system_message="""
+    role:
+      {{agent.role}}
+    goal:
+      {{agent.goal}}
+    backstory:
+      {{agent.backstory}}
+        """,
+        llm_config={"config_list": config_list},  # TODO: support other models
+    )
+    {%- endfor %}
+
+    # # The user proxy agent is used for interacting with the assistant agent
+    # # and executes tool calls.
+    user_proxy = ConversableAgent(
+        name="User",
+        llm_config=False,
+        is_termination_msg=lambda msg: msg.get("content") is not None and "TERMINATE" in msg["content"],
+        human_input_mode="NEVER",
+    )
+
+    # TODO: use this as tool add example
+    # assistant.register_for_llm(name="calculator", description="A simple calculator")(calculator)
+    # user_proxy.register_for_execution(name="calculator")(calculator)
+
+    # Register the calculator function to the two agents.
+    # register_function(
+    #     calculator,
+    #     caller=assistant,  # The assistant agent can suggest calls to the calculator.
+    #     executor=user_proxy,  # The user proxy agent can execute the calculator calls.
+    #     name="calculator",  # By default, the function name is used as the tool name.
+    #     description="A simple calculator",  # A description of the tool.
+    # )
+
+    # Let the assistant start the conversation.  It will end when the user types exit.
+    # user_proxy.initiate_chat(assistant, message="What is (1423 - 123) / 3 + (32 + 23) * 5?")
+
+    agentops.end_session("Success")
+
+
+if __name__ == "__main__":
+    main()