62 lines
2.1 KiB
Python
62 lines
2.1 KiB
Python
import os
|
||
import asyncio
|
||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||
from langchain_chroma import Chroma
|
||
from langchain_core.messages import HumanMessage
|
||
from langchain.tools import tool
|
||
from deepagents import create_deep_agent
|
||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||
|
||
# LLM configuration – always OpenRouter
|
||
llm = ChatOpenAI(
|
||
model="openai/gpt-oss-20b:free",
|
||
base_url="https://openrouter.ai/api/v1",
|
||
api_key=os.getenv("OPENAI_API_KEY"),
|
||
temperature=0.0,
|
||
)
|
||
|
||
# Embeddings and vector store for RAG
|
||
embeddings = OpenAIEmbeddings(
|
||
model="text-embedding-3-small",
|
||
base_url="https://openrouter.ai/api/v1",
|
||
api_key=os.getenv("OPENAI_API_KEY"),
|
||
)
|
||
vector_store = Chroma(collection_name="knowledge", embedding_function=embeddings)
|
||
|
||
# Backend for file operations – virtual mode so no real files are created
|
||
backend = CompositeBackend(
|
||
default=LocalShellBackend(root_dir="./workspace", virtual_mode=True, inherit_env=True),
|
||
routes={},
|
||
)
|
||
|
||
# Tool that performs a vector search and returns the top 3 snippets
|
||
@tool
|
||
def rag_search(query: str) -> str:
|
||
"""Search the vector store for relevant documents and return a concise summary."""
|
||
docs = vector_store.similarity_search(query, k=3)
|
||
if not docs:
|
||
return "No relevant information found."
|
||
snippets = "\n---\n".join(doc.page_content for doc in docs)
|
||
return f"Top matches:\n{snippets}"
|
||
|
||
# Create the deep agent with the RAG tool
|
||
agent = create_deep_agent(
|
||
model=llm,
|
||
tools=[rag_search],
|
||
backend=backend,
|
||
system_prompt="You are a helpful assistant that uses a knowledge base to answer questions. Use the rag_search tool when you need external information.",
|
||
)
|
||
|
||
async def main():
|
||
# Example user query
|
||
user_query = "What are the main causes of climate change?"
|
||
result = await agent.ainvoke(
|
||
{"messages": [HumanMessage(content=user_query)]},
|
||
{"configurable": {"thread_id": "session-1"}},
|
||
)
|
||
# Print the final assistant message
|
||
print(result["messages"][-1].content)
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|