fix(needs_fixes): 1 исправлений, 0 отстояно — main.py

This commit is contained in:
+111 -90
View File
@@ -1,29 +1,38 @@
"""RAG Agent with Qdrant and OpenRouter.
This script implements the assignment requirements:
* Two tools `search_knowledge_base` and `add_to_knowledge_base` are defined with the `@tool` decorator.
* A Qdrant vector store is used for semantic search. Documents are split into chunks with a
`RecursiveCharacterTextSplitter` that has `chunk_overlap=100` as requested.
* The agent is created with LangChains `create_agent` (the "Исправить" instruction overrides the
earlier requirement to use `create_deep_agent`).
* A simple CLI allows adding documents, searching the knowledge base and quitting.
The code is selfcontained and can be run directly after installing the dependencies listed in
`requirements.txt`.
"""
DeepAgents RAG Agent with Qdrant and Ollama embeddings
"""
import os
import asyncio
from pathlib import Path
import pathlib
from typing import List
from langchain_openai import ChatOpenAI
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_core.messages import HumanMessage
from langchain.tools import tool
from langchain_ollama.embeddings import OllamaEmbeddings
from langchain_qdrant import QdrantVectorStore
from langchain_community.vectorstores import Qdrant
from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
from langchain.agents import create_agent, AgentExecutor, AgentType
# ---------------------------------------------------------------------------
# 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")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
if not OPENAI_API_KEY:
raise RuntimeError("OPENAI_API_KEY environment variable is required")
# LLM via OpenRouter
# LLM and embeddings via OpenRouter
llm = ChatOpenAI(
model="openai/gpt-oss-20b:free",
base_url="https://openrouter.ai/api/v1",
@@ -31,112 +40,124 @@ llm = ChatOpenAI(
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",
embeddings = OpenAIEmbeddings(
model="text-embedding-3-small",
base_url="https://openrouter.ai/api/v1",
api_key=OPENAI_API_KEY,
)
# ---------------------------------------------------------------------------
# Vector store setup (Qdrant)
# ---------------------------------------------------------------------------
# Qdrant is expected to be running locally on the default port 6333.
# If you need a different host/port, adjust the `url` parameter.
vector_store = Qdrant.from_existing_index(
collection_name="knowledge",
embeddings=embeddings,
url="http://localhost:6333",
)
# ---------------------------------------------------------------------------
# Text splitter
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
# ---------------------------------------------------------------------------
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=100, # as required by the assignment
)
# ---------------------------------------------------------------------------
# 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)
"""Search the knowledge base for relevant information.
Parameters
----------
query: str
The search query.
max_results: int, optional
Number of top results to return. Defaults to 3.
"""
docs = 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))
return "\n\n---\n\n".join(doc.page_content for doc in 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
"""Add content to the knowledge base.
Parameters
----------
content: str
The raw text to add.
title: str, optional
A title for the document. Defaults to "document".
"""
# Split into chunks and create Document objects
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}'."
from langchain_core.documents import Document
docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
vector_store.add_documents(docs)
return f"Added {len(docs)} chunks for title '{title}'."
# ---------------------------------------------------------------------------
# Backend setup
# Agent creation (LangChain create_agent)
# ---------------------------------------------------------------------------
backend = CompositeBackend([
LocalShellBackend(workspace_dir="./workspace"),
FilesystemBackend(),
])
# The system prompt instructs the agent to use the knowledge base tools.
SYSTEM_PROMPT = (
"You are an AI assistant with access to a knowledge base. "
"Use the tools `search_knowledge_base` and `add_to_knowledge_base` to answer user queries. "
"If the user asks to add information, store it. If the user asks for information, search the base."
)
# ---------------------------------------------------------------------------
# Agent creation
# ---------------------------------------------------------------------------
agent = create_deep_agent(
model=llm,
agent = create_agent(
llm=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.",
system_prompt=SYSTEM_PROMPT,
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
)
# ---------------------------------------------------------------------------
# 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"}},
)
agent_executor = AgentExecutor(agent=agent, tools=[search_knowledge_base, add_to_knowledge_base])
# ---------------------------------------------------------------------------
# CLI client
# CLI
# ---------------------------------------------------------------------------
async def cli():
print("DeepAgents RAG CLI. Commands: /add <text>, /search <query>, /quit")
async def handle_user_input(user_input: str) -> str:
if user_input.startswith("/add "):
# Expected format: /add <title> | <content>
try:
_, rest = user_input.split("/add ", 1)
title, content = rest.split("|", 1)
title = title.strip()
content = content.strip()
result = add_to_knowledge_base(content, title)
return result
except ValueError:
return "Invalid format. Use: /add <title> | <content>"
elif user_input.startswith("/search "):
query = user_input[len("/search "):].strip()
return search_knowledge_base(query)
elif user_input == "/quit":
return "quit"
else:
# Forward to the agent
response = await agent_executor.ainvoke({"messages": [HumanMessage(content=user_input)]})
return response["messages"][-1].content
async def main():
print("RAG Agent CLI. Commands: /add <title> | <content>, /search <query>, /quit")
while True:
user_input = input("> ")
if user_input.strip() == "/quit":
if not user_input:
continue
result = await handle_user_input(user_input)
if result == "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()
print(result)
if __name__ == "__main__":
asyncio.run(main())