Update agent.py
This commit is contained in:
@@ -1,72 +1,128 @@
|
||||
"""
|
||||
Agent creation for the RAG system.
|
||||
"""Agent construction for RAG with local KB and web search.
|
||||
|
||||
Provides a function ``create_agent`` that returns an ``AgentExecutor`` capable of
|
||||
choosing between the local KB search and the Tavily 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 List
|
||||
from typing import Dict, Any
|
||||
|
||||
from langchain_core.prompts import ChatPromptTemplate
|
||||
from langchain_ollama import ChatOllama
|
||||
from langchain.agents import AgentExecutor, create_openai_functions_agent
|
||||
from langchain.tools import Tool
|
||||
from langchain.agents import create_openai_functions_agent, AgentExecutor
|
||||
|
||||
# Import the tools defined in tools.py
|
||||
from tools import search_local_kb, web_search
|
||||
from rag_tools import search_local_kb, web_search
|
||||
from vectorstore import create_vectorstore
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent creation
|
||||
# Helper: decide whether to use web search
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def create_agent(vectorstore_instance) -> AgentExecutor:
|
||||
"""Create an agent that can decide between local KB and 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_instance
|
||||
Instance of the Chroma vector store to be used by the local search tool.
|
||||
vectorstore: Chroma
|
||||
The vector store used by the local KB search tool.
|
||||
|
||||
Returns
|
||||
-------
|
||||
AgentExecutor
|
||||
Configured agent ready for use.
|
||||
Configured agent.
|
||||
"""
|
||||
# Make the vectorstore available to the tool via the module global
|
||||
import tools
|
||||
tools.vectorstore = vectorstore_instance
|
||||
# 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)
|
||||
|
||||
# Define the tools
|
||||
tools_list: List[Tool] = [
|
||||
Tool(
|
||||
name="search_local_kb",
|
||||
func=search_local_kb,
|
||||
description="Search the local knowledge base (ChromaDB). Use when the answer is likely contained in the local documents.",
|
||||
),
|
||||
Tool(
|
||||
name="web_search",
|
||||
func=web_search,
|
||||
description="Search the web via Tavily. Use when the answer requires up‑to‑date information.",
|
||||
),
|
||||
]
|
||||
# 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)
|
||||
|
||||
# LLM for the agent
|
||||
llm = ChatOllama(model="llama3", temperature=0)
|
||||
# Define tools list with updated references
|
||||
tools = [search_local_kb_wrapper, web_search_wrapper]
|
||||
|
||||
# System prompt guiding the agent
|
||||
system_prompt = (
|
||||
"You are an assistant that answers user questions. "
|
||||
"If the answer can be found in the local knowledge base, use the tool "
|
||||
"`search_local_kb`. If the question asks for recent or current information, "
|
||||
"use the tool `web_search`. After obtaining the information, provide a "
|
||||
"concise answer and state the source (`chromadb` or `tavily`)."
|
||||
)
|
||||
# LLM
|
||||
llm = ChatOllama(model="llama3")
|
||||
|
||||
# Create the agent using the function calling approach
|
||||
agent = create_openai_functions_agent(llm=llm, tools=tools_list, system_message=system_prompt)
|
||||
# Prompt template
|
||||
prompt = ChatPromptTemplate.from_messages([
|
||||
("system", SYSTEM_PROMPT),
|
||||
("human", "{input}"),
|
||||
])
|
||||
|
||||
# Wrap in an executor for easy use
|
||||
return AgentExecutor(agent=agent, tools=tools_list, verbose=True)
|
||||
# Create agent
|
||||
agent = create_openai_functions_agent(llm=llm, tools=tools, prompt=prompt)
|
||||
|
||||
# Wrap with AgentExecutor
|
||||
return AgentExecutor(agent=agent, tools=tools, verbose=True)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# End of module
|
||||
# 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", ""))
|
||||
""
|
||||
Reference in New Issue
Block a user