Design & implmentation of instinct-agent

[RobinQu]

Manifest

• ToolAgent, or functional calling basement
  • rool rendering, invocation command parser
  • function tool and function toolkits protocol
  • with local memory and checkpoint
• Multi-agent ochestration
  • control flow: loop/if-else/switch
  • human in the loop
• distributed agent protocol. (Agent Protocol based implementaion?)
  • agent state checkpoint
  • disributed memory, tool server
• built-in tools
  • external retriever: Google Search, Wikipedia, SERP API
  • calculator
  • LLM
  • python interpreter ?
• built-in agents
  • ReACT Tool Execution Agent
  • Plan & Execute
  • LLMCompiler

Project plans

Stage 0 - POC - for one week

I'm still getting too many questions about implementation. Let's do some minimum implementation for inspirations.

• [x] ToolAgent
• [x] Built-in toolkits: Search (one of Google, Tavily, duc-duck-go or SERP API) , Calculator, Python Interpreter
• [ ] Human in the loop: pause, resume

Stage 1 - Assistant API Server for v0.1.2

19

First version of mini-assistant

• Sync api calls for Assistant, File, Run, RunStep, Message, Thread
• Function call support, using ReACT

Future developments

Sprint	Features
v0.1.3	file search tool paralled call using LLMCompiler ?
v0.1.4	* code interpreter
v0.1.5	stream support scaliblity on cloud: PGSQL, Kafka, …

[RobinQu]

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

[RobinQu]

https://github.com/langchain-ai/langgraph/tree/main/examples/multi_agent

[RobinQu]

Tool Agent

langchian tool invocation without function calling API https://python.langchain.com/docs/use_cases/tool_use/prompting/

Tool description rendering

def render_text_description(tools: List[BaseTool]) -> str:
    """Render the tool name and description in plain text.

    Output will be in the format of:

    .. code-block:: markdown

        search: This tool is used for search
        calculator: This tool is used for math
    """
    return "\n".join([f"{tool.name}: {tool.description}" for tool in tools])

def render_text_description_and_args(tools: List[BaseTool]) -> str:
    """Render the tool name, description, and args in plain text.

    Output will be in the format of:

    .. code-block:: markdown

        search: This tool is used for search, args: {"query": {"type": "string"}}
        calculator: This tool is used for math, \
args: {"expression": {"type": "string"}}
    """
    tool_strings = []
    for tool in tools:
        args_schema = str(tool.args)
        tool_strings.append(f"{tool.name}: {tool.description}, args: {args_schema}")
    return "\n".join(tool_strings)

[RobinQu]

it should be closed with release of v0.1.3.