Added main.py
This commit is contained in:
@@ -1,3 +1,8 @@
|
||||
# main.py
|
||||
# Полностью рабочий пример агента с RAG‑памятью на Qdrant и OpenRouter
|
||||
# Использует deepagents, langchain‑openai, langchain‑qdrant, langchain‑core
|
||||
# Запуск: python main.py
|
||||
|
||||
import os
|
||||
import asyncio
|
||||
from pathlib import Path
|
||||
@@ -5,157 +10,159 @@ 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_text_splitters import RecursiveCharacterTextSplitter
|
||||
from langchain_qdrant import QdrantVectorStore
|
||||
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_core.messages import HumanMessage
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Configuration
|
||||
# ---------------------------------------------------------------------------
|
||||
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=EMBEDDING_MODEL,
|
||||
base_url=BASE_URL,
|
||||
api_key=API_KEY,
|
||||
)
|
||||
|
||||
vector_store = QdrantVectorStore(
|
||||
url=QDRANT_URL,
|
||||
collection_name=QDRANT_COLLECTION,
|
||||
embedding_function=embeddings,
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Text splitter
|
||||
# ---------------------------------------------------------------------------
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tools
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def search_knowledge_base(query: str, max_results: int = 3) -> str:
|
||||
"""Semantic search in the knowledge base."""
|
||||
docs: List[Document] = vector_store.similarity_search(query, k=max_results)
|
||||
if not docs:
|
||||
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 = "untitled") -> str:
|
||||
"""Add a new document to the knowledge base."""
|
||||
# Split content into chunks
|
||||
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 title '{title}'."
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend setup
|
||||
# ---------------------------------------------------------------------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# LLM
|
||||
# Конфигурация LLM и Embeddings
|
||||
# ---------------------------------------------------------------------------
|
||||
llm = ChatOpenAI(
|
||||
model=LLM_MODEL,
|
||||
base_url=BASE_URL,
|
||||
api_key=API_KEY,
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent
|
||||
# Qdrant клиент и коллекция
|
||||
# ---------------------------------------------------------------------------
|
||||
# Предполагается, что Qdrant запущен локально на порту 6333
|
||||
qdrant_url = "http://localhost:6333"
|
||||
collection_name = "knowledge_base"
|
||||
|
||||
vector_store = QdrantVectorStore(
|
||||
embeddings=embeddings,
|
||||
url=qdrant_url,
|
||||
collection_name=collection_name,
|
||||
# Если коллекция не существует, она будет создана автоматически
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Чанкинг
|
||||
# ---------------------------------------------------------------------------
|
||||
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Инструменты для агента
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def search_knowledge_base(query: str, max_results: int = 5) -> str:
|
||||
"""Semantic search in the knowledge base.
|
||||
Returns a formatted string with the top results.
|
||||
"""
|
||||
results = vector_store.similarity_search_with_score(query, k=max_results)
|
||||
if not results:
|
||||
return "No relevant documents found."
|
||||
formatted = []
|
||||
for doc, score in results:
|
||||
formatted.append(f"Title: {doc.metadata.get('title', 'Untitled')}\nScore: {score:.4f}\nContent: {doc.page_content[:200]}...\n")
|
||||
return "\n".join(formatted)
|
||||
|
||||
@tool
|
||||
def add_to_knowledge_base(content: str, title: str) -> str:
|
||||
"""Add a new document to the knowledge base.
|
||||
The content is split into chunks, embedded and stored.
|
||||
"""
|
||||
# Split into chunks
|
||||
chunks = text_splitter.split_text(content)
|
||||
docs: List[Document] = []
|
||||
for i, chunk in enumerate(chunks):
|
||||
docs.append(Document(page_content=chunk, metadata={"title": title, "chunk_index": i}))
|
||||
# Add to vector store
|
||||
vector_store.add_documents(docs)
|
||||
return f"Added {len(docs)} chunks for document '{title}'."
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend для deepagents
|
||||
# ---------------------------------------------------------------------------
|
||||
backend = CompositeBackend(
|
||||
default=LocalShellBackend(root_dir="./workspace", virtual_mode=True, inherit_env=True),
|
||||
routes={},
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Создание агента
|
||||
# ---------------------------------------------------------------------------
|
||||
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 a helpful assistant with access to a knowledge base. Use the provided tools to search and add information."
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Document loader for initialization
|
||||
# Инициализация: загрузка документов из директории
|
||||
# ---------------------------------------------------------------------------
|
||||
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.")
|
||||
DOCS_DIR = Path("./docs")
|
||||
|
||||
async def load_documents_from_dir(directory: Path):
|
||||
if not directory.exists():
|
||||
return
|
||||
for file_path in dir_path.rglob("*.txt"):
|
||||
for file_path in directory.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}"}},
|
||||
{"configurable": {"thread_id": "init-session"}},
|
||||
)
|
||||
print("Initialization complete.")
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Interactive CLI
|
||||
# Интерактивный клиент
|
||||
# ---------------------------------------------------------------------------
|
||||
async def interactive_loop():
|
||||
print("Welcome to the RAG agent. Commands: /add <title>, /search <query>, /quit")
|
||||
thread_id = "interactive-session"
|
||||
while True:
|
||||
user_input = input("> ")
|
||||
if user_input.strip() == "/quit":
|
||||
print("Goodbye!")
|
||||
break
|
||||
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(
|
||||
title = user_input[5:].strip()
|
||||
print("Enter content (end with a single line containing only 'END'): ")
|
||||
lines = []
|
||||
while True:
|
||||
line = input()
|
||||
if line.strip() == "END":
|
||||
break
|
||||
lines.append(line)
|
||||
content = "\n".join(lines)
|
||||
await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/add {title}")], "content": content},
|
||||
{"configurable": {"thread_id": f"add-{title}"}},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
print(f"Document '{title}' added.")
|
||||
elif user_input.startswith("/search "):
|
||||
query = user_input[len("/search "):]
|
||||
response = await agent.ainvoke(
|
||||
query = user_input[8:].strip()
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=f"/search {query}")]},
|
||||
{"configurable": {"thread_id": f"search-{query}"}},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
print(result["messages"][-1].content)
|
||||
else:
|
||||
# Regular message to agent
|
||||
response = await agent.ainvoke(
|
||||
# обычный запрос к LLM
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=user_input)]},
|
||||
{"configurable": {"thread_id": "interactive"}},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
print(response["messages"][-1].content)
|
||||
print(result["messages"][-1].content)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main entry point
|
||||
# Основной запуск
|
||||
# ---------------------------------------------------------------------------
|
||||
async def main():
|
||||
# Optional: load initial documents
|
||||
# await load_documents_from_dir("./initial_docs")
|
||||
# Загрузим документы из каталога docs при старте
|
||||
await load_documents_from_dir(DOCS_DIR)
|
||||
await interactive_loop()
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user