69 lines
2.5 KiB
Python
69 lines
2.5 KiB
Python
"""Agent implementation using LangChain 1.x.
|
||
|
||
The agent uses a simple tool‑based architecture. The LLM is a local
|
||
`ChatOllama` model (llama3). Two tools are available:
|
||
|
||
* ``search_local_kb`` – semantic search in Qdrant.
|
||
* ``web_search`` – web search via Tavily.
|
||
|
||
The system prompt instructs the LLM to decide which tool to use based on the
|
||
question. The response always contains a marker indicating the source
|
||
(`chromadb`/`tavily`). The marker is added by the LLM itself.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
from typing import List
|
||
|
||
from langchain_ollama import ChatOllama
|
||
from langchain_core.prompts import ChatPromptTemplate
|
||
from langchain_core.runnables import Runnable
|
||
from langchain_core.tools import BaseTool
|
||
|
||
# Import tools without relative import to allow top‑level import
|
||
import tools
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Helper: create a tool list
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def get_tools() -> List[BaseTool]:
|
||
"""Return the list of tools used by the agent."""
|
||
return [tools.search_local_kb, tools.web_search]
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# System prompt
|
||
# ---------------------------------------------------------------------------
|
||
SYSTEM_PROMPT = (
|
||
"You are an AI assistant that can answer questions using two sources: "
|
||
"1) a local knowledge base (Qdrant) and 2) the web via Tavily. "
|
||
"If the answer can be found in the local KB, use the `search_local_kb` tool. "
|
||
"If the answer requires up‑to‑date information, use the `web_search` tool. "
|
||
"Return the answer followed by a source marker on a new line: "
|
||
"`Source: chromadb` or `Source: tavily`."
|
||
)
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Agent construction
|
||
# ---------------------------------------------------------------------------
|
||
|
||
def create_agent() -> Runnable:
|
||
"""Create a runnable agent.
|
||
|
||
The agent is a simple chain: system prompt → user message → tool calls → LLM
|
||
response. It uses the default tool‑calling behaviour of LangChain 1.x.
|
||
"""
|
||
llm = ChatOllama(model="llama3", temperature=0.0)
|
||
|
||
# AgentExecutor can accept a system message via agent_kwargs
|
||
from langchain.agents import AgentExecutor
|
||
|
||
agent = AgentExecutor.from_llm_and_tools(
|
||
llm=llm,
|
||
tools=get_tools(),
|
||
verbose=True,
|
||
# Provide the system prompt so the LLM knows how to behave
|
||
agent_kwargs={"system_message": SYSTEM_PROMPT},
|
||
)
|
||
|
||
return agent |