Files
task-6a02e23da6fe2e4ac16acf65/main.py
T

143 lines
5.5 KiB
Python

"""
DeepAgents RAG Agent with Qdrant and Ollama embeddings
"""
import os
import asyncio
from pathlib import Path
from typing import List
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
from langchain.tools import tool
from langchain_ollama.embeddings import OllamaEmbeddings
from langchain_qdrant import QdrantVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
# ---------------------------------------------------------------------------
# Configuration
# ---------------------------------------------------------------------------
# Environment variables
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "") # required for OpenRouter LLM
OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")
# LLM via OpenRouter
llm = ChatOpenAI(
model="openai/gpt-oss-20b:free",
base_url="https://openrouter.ai/api/v1",
api_key=OPENAI_API_KEY,
temperature=0.0,
)
# Embeddings via Ollama
embeddings = OllamaEmbeddings(model="nomic-embed-text", base_url=OLLAMA_BASE_URL)
# Qdrant vector store
qdrant_vector_store = QdrantVectorStore(
client_kwargs={"url": QDRANT_URL},
collection_name="knowledge_base",
embeddings=embeddings,
# Create collection if not exists
create_collection=True,
# Use cosine similarity
distance="cosine",
)
# Text splitter
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
# ---------------------------------------------------------------------------
# Tools
# ---------------------------------------------------------------------------
@tool
def search_knowledge_base(query: str, max_results: int = 3) -> str:
"""Semantic search in the knowledge base."""
docs = qdrant_vector_store.similarity_search(query, k=max_results)
if not docs:
return "No results found."
return "\n\n".join(f"{i+1}. {doc.page_content}" for i, doc in enumerate(docs))
@tool
def add_to_knowledge_base(content: str, title: str = "document") -> str:
"""Add content to the knowledge base after chunking."""
# Split content into chunks
chunks = text_splitter.split_text(content)
metadatas = [{"title": title, "chunk_index": i} for i in range(len(chunks))]
# Add to Qdrant
qdrant_vector_store.add_texts(chunks, metadatas=metadatas)
return f"Added {len(chunks)} chunks from '{title}'."
# ---------------------------------------------------------------------------
# Backend setup
# ---------------------------------------------------------------------------
backend = CompositeBackend([
LocalShellBackend(workspace_dir="./workspace"),
FilesystemBackend(),
])
# ---------------------------------------------------------------------------
# Agent creation
# ---------------------------------------------------------------------------
agent = create_deep_agent(
model=llm,
tools=[search_knowledge_base, add_to_knowledge_base],
backend=backend,
system_prompt="You are a helpful assistant with access to a knowledge base. Use the provided tools to search and add information.",
)
# ---------------------------------------------------------------------------
# Document loader for initialization
# ---------------------------------------------------------------------------
async def load_documents_from_dir(directory: str):
"""Load all .txt files from a directory into the knowledge base."""
dir_path = Path(directory)
for file_path in dir_path.rglob("*.txt"):
content = file_path.read_text(encoding="utf-8")
title = file_path.stem
await agent.ainvoke(
{"messages": [HumanMessage(content=f"/add {content}")], "metadata": {"title": title}},
{"configurable": {"thread_id": "init-session"}},
)
# ---------------------------------------------------------------------------
# CLI client
# ---------------------------------------------------------------------------
async def cli():
print("DeepAgents RAG CLI. Commands: /add <text>, /search <query>, /quit")
while True:
user_input = input("> ")
if user_input.strip() == "/quit":
print("Goodbye!")
break
if user_input.startswith("/add "):
content = user_input[5:].strip()
response = await agent.ainvoke(
{"messages": [HumanMessage(content=f"/add {content}")], "metadata": {"title": "user_input"}},
{"configurable": {"thread_id": "cli-session"}},
)
print(response["messages"][-1].content)
elif user_input.startswith("/search "):
query = user_input[8:].strip()
response = await agent.ainvoke(
{"messages": [HumanMessage(content=f"/search {query}")], "metadata": {"query": query}},
{"configurable": {"thread_id": "cli-session"}},
)
print(response["messages"][-1].content)
else:
print("Unknown command. Use /add, /search, or /quit.")
# ---------------------------------------------------------------------------
# Main entry point
# ---------------------------------------------------------------------------
async def main():
# Optional: load initial documents from a folder named 'data'
data_dir = Path("./data")
if data_dir.exists():
await load_documents_from_dir(str(data_dir))
await cli()
if __name__ == "__main__":
asyncio.run(main())