fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,163 +1,162 @@
|
||||
"""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 LangChain’s `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 self‑contained and can be run directly after installing the dependencies listed in
|
||||
`requirements.txt`.
|
||||
"""
|
||||
|
||||
import os
|
||||
import asyncio
|
||||
import pathlib
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_core.documents import Document
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langchain.tools import tool
|
||||
from langchain_community.vectorstores import Qdrant
|
||||
from langchain_community.document_loaders import TextLoader
|
||||
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||||
from langchain.agents import create_agent, AgentExecutor, AgentType
|
||||
from langchain_qdrant import QdrantVectorStore
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Configuration
|
||||
# ---------------------------------------------------------------------------
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
if not OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY environment variable is required")
|
||||
|
||||
# LLM and embeddings 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,
|
||||
)
|
||||
QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333")
|
||||
QDRANT_COLLECTION = "knowledge_base"
|
||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
LLM_MODEL = "openai/gpt-oss-20b:free"
|
||||
BASE_URL = "https://openrouter.ai/api/v1"
|
||||
API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Embeddings and Vector Store
|
||||
# ---------------------------------------------------------------------------
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
model=EMBEDDING_MODEL,
|
||||
base_url=BASE_URL,
|
||||
api_key=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",
|
||||
vector_store = QdrantVectorStore(
|
||||
url=QDRANT_URL,
|
||||
collection_name=QDRANT_COLLECTION,
|
||||
embedding_function=embeddings,
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Text splitter
|
||||
# ---------------------------------------------------------------------------
|
||||
text_splitter = RecursiveCharacterTextSplitter(
|
||||
chunk_size=1000,
|
||||
chunk_overlap=100, # as required by the assignment
|
||||
)
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tools
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def search_knowledge_base(query: str, max_results: int = 3) -> str:
|
||||
"""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)
|
||||
"""Semantic search in the knowledge base."""
|
||||
docs: List[Document] = vector_store.similarity_search(query, k=max_results)
|
||||
if not docs:
|
||||
return "No results found."
|
||||
return "No relevant documents found."
|
||||
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.
|
||||
|
||||
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
|
||||
def add_to_knowledge_base(content: str, title: str = "untitled") -> str:
|
||||
"""Add a new document to the knowledge base."""
|
||||
# Split content into chunks
|
||||
chunks = text_splitter.split_text(content)
|
||||
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}'."
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent creation (LangChain create_agent)
|
||||
# Backend setup
|
||||
# ---------------------------------------------------------------------------
|
||||
# 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."
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# LLM
|
||||
# ---------------------------------------------------------------------------
|
||||
llm = ChatOpenAI(
|
||||
model=LLM_MODEL,
|
||||
base_url=BASE_URL,
|
||||
api_key=API_KEY,
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
agent = create_agent(
|
||||
llm=llm,
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent
|
||||
# ---------------------------------------------------------------------------
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[search_knowledge_base, add_to_knowledge_base],
|
||||
system_prompt=SYSTEM_PROMPT,
|
||||
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
|
||||
backend=backend,
|
||||
system_prompt="You are a helpful assistant with access to a knowledge base. Use the provided tools to search and add information.",
|
||||
)
|
||||
|
||||
agent_executor = AgentExecutor(agent=agent, tools=[search_knowledge_base, add_to_knowledge_base])
|
||||
# ---------------------------------------------------------------------------
|
||||
# Document loader for initialization
|
||||
# ---------------------------------------------------------------------------
|
||||
async def load_documents_from_dir(directory: str):
|
||||
"""Load all text files from a directory into the vector store."""
|
||||
dir_path = Path(directory)
|
||||
if not dir_path.is_dir():
|
||||
print(f"Directory {directory} does not exist.")
|
||||
return
|
||||
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 {title}")], "content": content},
|
||||
{"configurable": {"thread_id": f"init-{file_path.name}"}},
|
||||
)
|
||||
print("Initialization complete.")
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CLI
|
||||
# Interactive CLI
|
||||
# ---------------------------------------------------------------------------
|
||||
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")
|
||||
async def interactive_loop():
|
||||
print("Welcome to the RAG agent. Commands: /add <title>, /search <query>, /quit")
|
||||
while True:
|
||||
user_input = input("> ")
|
||||
if not user_input:
|
||||
continue
|
||||
result = await handle_user_input(user_input)
|
||||
if result == "quit":
|
||||
if user_input.strip() == "/quit":
|
||||
print("Goodbye!")
|
||||
break
|
||||
print(result)
|
||||
if user_input.startswith("/add "):
|
||||
parts = user_input.split(" ", 1)
|
||||
if len(parts) < 2:
|
||||
print("Usage: /add <title>")
|
||||
continue
|
||||
title = parts[1]
|
||||
# For demo, read content from a file with same name
|
||||
file_path = Path("./docs") / f"{title}.txt"
|
||||
if not file_path.exists():
|
||||
print(f"File {file_path} not found.")
|
||||
continue
|
||||
content = file_path.read_text(encoding="utf-8")
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/add {title}")], "content": content},
|
||||
{"configurable": {"thread_id": f"add-{title}"}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
elif user_input.startswith("/search "):
|
||||
query = user_input[len("/search "):]
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/search {query}")]},
|
||||
{"configurable": {"thread_id": f"search-{query}"}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
else:
|
||||
# Regular message to agent
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=user_input)]},
|
||||
{"configurable": {"thread_id": "interactive"}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main entry point
|
||||
# ---------------------------------------------------------------------------
|
||||
async def main():
|
||||
# Optional: load initial documents
|
||||
# await load_documents_from_dir("./initial_docs")
|
||||
await interactive_loop()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user