128 lines
4.7 KiB
Python
128 lines
4.7 KiB
Python
"""Agent construction for RAG with local KB and web search.
|
|
|
|
The agent uses LangChain's `create_openai_functions_agent` style with a custom
|
|
`AgentExecutor` that routes queries to either the local knowledge base or the
|
|
web search based on a simple heuristic: if the query contains words that
|
|
suggest recent events ("news", "today", "now", "latest"), we use the web
|
|
search; otherwise we use the local KB.
|
|
|
|
The agent returns the answer along with the source used.
|
|
"""
|
|
|
|
from typing import Dict, Any
|
|
|
|
from langchain_core.prompts import ChatPromptTemplate
|
|
from langchain_ollama import ChatOllama
|
|
from langchain.agents import create_openai_functions_agent, AgentExecutor
|
|
|
|
from rag_tools import search_local_kb, web_search
|
|
from vectorstore import create_vectorstore
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Helper: decide whether to use web search
|
|
# ---------------------------------------------------------------------------
|
|
|
|
WEB_KEYWORDS = {"news", "today", "now", "latest", "recent", "current"}
|
|
|
|
|
|
def should_use_web(query: str) -> bool:
|
|
words = set(query.lower().split())
|
|
return bool(words & WEB_KEYWORDS)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# System prompt
|
|
# ---------------------------------------------------------------------------
|
|
|
|
SYSTEM_PROMPT = "You are an assistant that answers questions. Use the local knowledge base when the question is about stored documents; otherwise use web search. Respond with the answer and indicate the source (chromadb or tavily)."
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Agent construction
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def create_agent(vectorstore) -> AgentExecutor:
|
|
"""Create an AgentExecutor that routes queries to the appropriate tool.
|
|
|
|
Parameters
|
|
----------
|
|
vectorstore: Chroma
|
|
The vector store used by the local KB search tool.
|
|
|
|
Returns
|
|
-------
|
|
AgentExecutor
|
|
Configured agent.
|
|
"""
|
|
# Attach the vectorstore to the local search tool via closure
|
|
def search_local_kb_wrapper(query: str, top_k: int = 3) -> str:
|
|
return search_local_kb(query, top_k=top_k, vectorstore=vectorstore)
|
|
|
|
# Wrap the web search tool (no extra params needed)
|
|
def web_search_wrapper(query: str, top_k: int = 3) -> str:
|
|
return web_search(query, top_k=top_k)
|
|
|
|
# Define tools list with updated references
|
|
tools = [search_local_kb_wrapper, web_search_wrapper]
|
|
|
|
# LLM
|
|
llm = ChatOllama(model="llama3")
|
|
|
|
# Prompt template
|
|
prompt = ChatPromptTemplate.from_messages([
|
|
("system", SYSTEM_PROMPT),
|
|
("human", "{input}"),
|
|
])
|
|
|
|
# Create agent
|
|
agent = create_openai_functions_agent(llm=llm, tools=tools, prompt=prompt)
|
|
|
|
# Wrap with AgentExecutor
|
|
return AgentExecutor(agent=agent, tools=tools, verbose=True)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Simple executor for tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def create_agent_executor(vectorstore) -> Any:
|
|
"""Return a simple callable that mimics the agent for testing.
|
|
|
|
The returned callable takes a dictionary with keys ``input`` and optionally
|
|
``tool_choice``. It selects the appropriate tool based on the query and
|
|
returns a dictionary with an ``output`` key containing the result.
|
|
"""
|
|
agent = create_agent(vectorstore)
|
|
|
|
def executor(inputs: Dict[str, Any]) -> Dict[str, Any]:
|
|
query = inputs.get("input", "")
|
|
tool_choice = inputs.get("tool_choice")
|
|
if tool_choice == "web_search":
|
|
result = web_search(query)
|
|
elif tool_choice == "search_local_kb":
|
|
result = search_local_kb(query, vectorstore=vectorstore)
|
|
else:
|
|
# Default routing
|
|
if should_use_web(query):
|
|
result = web_search(query)
|
|
else:
|
|
result = search_local_kb(query, vectorstore=vectorstore)
|
|
return {"output": result}
|
|
|
|
return executor
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Example usage
|
|
# ---------------------------------------------------------------------------
|
|
|
|
if __name__ == "__main__":
|
|
store = create_vectorstore()
|
|
agent = create_agent(store)
|
|
while True:
|
|
q = input("Query> ")
|
|
if q.lower() in {"exit", "quit", "q"}:
|
|
break
|
|
# Simple routing: if query contains web keywords, use web tool
|
|
if should_use_web(q):
|
|
result = agent.invoke({"input": q, "tool_choice": "web_search"})
|
|
else:
|
|
result = agent.invoke({"input": q, "tool_choice": "search_local_kb"})
|
|
print("Answer:", result.get("output", ""))
|
|
"" |