fix(needs_fixes): 3 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,36 +1,16 @@
|
||||
"""
|
||||
# main.py – RAG‑agent with Qdrant, OpenRouter, and deepagents
|
||||
# ----------------------------------------------------------
|
||||
# 1. Imports and configuration
|
||||
# 2. Qdrant vector store wrapper (embedding, add, search)
|
||||
# 3. Text splitter (RecursiveCharacterTextSplitter)
|
||||
# 4. LangChain tools: search_knowledge_base, add_to_knowledge_base
|
||||
# 5. DeepAgent creation (create_deep_agent)
|
||||
# 6. CLI client for /add, /search, /quit
|
||||
# ----------------------------------------------------------
|
||||
"""
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_openai import ChatOpenAI
|
||||
from langchain_ollama import OllamaEmbeddings
|
||||
from langchain_qdrant import QdrantVectorStore
|
||||
from langchain_core.documents import Document
|
||||
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||||
from langchain.tools import tool
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
from langchain_qdrant import QdrantVectorStore
|
||||
from langchain_core.messages import HumanMessage
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 1. Configuration
|
||||
# ------------------------------------------------------------------
|
||||
# Load environment variables (e.g. OPENAI_API_KEY)
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv()
|
||||
|
||||
# LLM – OpenRouter (free tier)
|
||||
# ---------- LLM ----------
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
@@ -38,110 +18,91 @@ llm = ChatOpenAI(
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
# Embeddings – OpenAI via OpenRouter
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
)
|
||||
# ---------- Embeddings ----------
|
||||
# Using Ollama embeddings as per assignment correction
|
||||
embeddings = OllamaEmbeddings(model="nomic-embed-text")
|
||||
|
||||
# Qdrant client – assumes Qdrant is running locally on default port
|
||||
qdrant_url = os.getenv("QDRANT_URL", "http://localhost:6333")
|
||||
collection_name = "knowledge_base"
|
||||
# ---------- Vector Store (Qdrant) ----------
|
||||
# Ensure Qdrant is running locally (default port 6333)
|
||||
vector_store = QdrantVectorStore(
|
||||
url=qdrant_url,
|
||||
collection_name=collection_name,
|
||||
embeddings=embeddings,
|
||||
url="http://localhost:6333",
|
||||
collection_name="knowledge",
|
||||
embedding_function=embeddings,
|
||||
)
|
||||
|
||||
# Text splitter – 1000 chars max, 200 overlap
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 2. Tools
|
||||
# ------------------------------------------------------------------
|
||||
# ---------- Tools ----------
|
||||
@tool
|
||||
def search_knowledge_base(query: str, max_results: int = 3) -> str:
|
||||
"""Semantic search in the Qdrant knowledge base."""
|
||||
docs: List[Document] = vector_store.similarity_search(query, k=max_results)
|
||||
"""Semantic search in the knowledge base."""
|
||||
docs = vector_store.similarity_search(query, k=max_results)
|
||||
if not docs:
|
||||
return "No relevant documents found."
|
||||
return "\n\n---\n\n".join([f"{doc.metadata.get('title', 'Untitled')}:\n{doc.page_content}" for doc in docs])
|
||||
return "No results found."
|
||||
return "\n---\n".join(f"{i+1}. {doc.page_content[:200]}..." for i, doc in enumerate(docs))
|
||||
|
||||
@tool
|
||||
def add_to_knowledge_base(content: str, title: str = "Untitled") -> str:
|
||||
"""Add a new document to the knowledge base.
|
||||
The content is split into chunks before being stored.
|
||||
"""
|
||||
chunks = text_splitter.split_text(content)
|
||||
docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
|
||||
vector_store.add_documents(docs)
|
||||
return f"Added {len(docs)} chunks for document '{title}'."
|
||||
def add_to_knowledge_base(content: str, title: str = "untitled") -> str:
|
||||
"""Add a document to the knowledge base."""
|
||||
doc = Document(page_content=content, metadata={"title": title})
|
||||
vector_store.add_documents([doc])
|
||||
return f"Document '{title}' added to the knowledge base."
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 3. DeepAgent setup
|
||||
# ------------------------------------------------------------------
|
||||
# ---------- Backend ----------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ---------- Agent ----------
|
||||
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.",
|
||||
system_prompt="You are an assistant with access to a knowledge base. Use the provided tools to search and add information."
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 4. CLI client
|
||||
# ------------------------------------------------------------------
|
||||
async def run_cli():
|
||||
print("Welcome to the RAG Agent CLI. Commands: /add <title> <file>, /search <query>, /quit")
|
||||
thread_id = "cli-session"
|
||||
# ---------- Document Loader ----------
|
||||
async def load_documents_from_dir(directory: str):
|
||||
"""Load all text files from a directory into the vector store."""
|
||||
for file_path in Path(directory).rglob("*.txt"):
|
||||
text = file_path.read_text(encoding="utf-8")
|
||||
title = file_path.stem
|
||||
await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/add {title}")], "content": text},
|
||||
{"configurable": {"thread_id": "init"}},
|
||||
)
|
||||
|
||||
# ---------- Interactive CLI ----------
|
||||
async def interactive_loop():
|
||||
print("Welcome to the RAG Agent. Commands: /add <title>, /search <query>, /quit")
|
||||
while True:
|
||||
try:
|
||||
user_input = input("> ")
|
||||
except EOFError:
|
||||
break
|
||||
if not user_input:
|
||||
continue
|
||||
if user_input.startswith("/quit"):
|
||||
user_input = input("> ")
|
||||
if user_input.strip() == "/quit":
|
||||
print("Goodbye!")
|
||||
break
|
||||
if user_input.startswith("/add"):
|
||||
parts = user_input.split(maxsplit=2)
|
||||
if len(parts) < 3:
|
||||
print("Usage: /add <title> <file_path>")
|
||||
continue
|
||||
title, file_path = parts[1], parts[2]
|
||||
try:
|
||||
content = Path(file_path).read_text(encoding="utf-8")
|
||||
except Exception as e:
|
||||
print(f"Error reading file: {e}")
|
||||
continue
|
||||
# Invoke tool directly
|
||||
result = add_to_knowledge_base(content, title)
|
||||
print(result)
|
||||
continue
|
||||
if user_input.startswith("/search"):
|
||||
query = user_input[len("/search"):].strip()
|
||||
if not query:
|
||||
print("Usage: /search <query>")
|
||||
continue
|
||||
# Use agent to perform search via tool
|
||||
if user_input.startswith("/add "):
|
||||
parts = user_input.split(" ", 1)
|
||||
title = parts[1] if len(parts) > 1 else "untitled"
|
||||
content = input("Enter content: ")
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [{"role": "user", "content": f"search {query}"}]},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
{"messages": [HumanMessage(content=f"/add {title}")], "content": content},
|
||||
{"configurable": {"thread_id": "session"}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
continue
|
||||
# Default: treat as normal user message
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [{"role": "user", "content": user_input}]},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
elif user_input.startswith("/search "):
|
||||
query = user_input.split(" ", 1)[1]
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/search {query}")]},
|
||||
{"configurable": {"thread_id": "session"}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
else:
|
||||
print("Unknown command. Use /add, /search, or /quit.")
|
||||
|
||||
# ---------- Main ----------
|
||||
async def main():
|
||||
# Optional: load initial documents
|
||||
# await load_documents_from_dir("./data")
|
||||
await interactive_loop()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(run_cli())
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user