fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,91 +1,91 @@
|
||||
import os
|
||||
#!/usr/bin/env python3
|
||||
"""RAG‑agent with ChromaDB and Tavily search.
|
||||
|
||||
This implementation follows the course specification and uses the
|
||||
`deepagents` framework to create a single agent that can decide whether
|
||||
to query the local knowledge base (ChromaDB) or perform a web search
|
||||
via Tavily. The agent is backed by OpenRouter for both LLM and
|
||||
embeddings, complying with the mandatory technical constraints.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
from langchain_core.documents import Document
|
||||
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
||||
from langchain_tavily import TavilySearchRun
|
||||
from langchain.tools import tool
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
from langchain_core.messages import HumanMessage
|
||||
from tavily import TavilySearchResults
|
||||
|
||||
# ---------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# Configuration
|
||||
# ---------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# Load environment variables (OpenRouter key, Tavily key)
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
TAVILY_API_KEY = os.getenv("TAVILY_API_KEY")
|
||||
|
||||
# ---------------------
|
||||
# Vector store utilities
|
||||
# ---------------------
|
||||
# Persist directory for ChromaDB
|
||||
CHROMA_DIR = Path("./chroma_db")
|
||||
CHROMA_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
def create_vectorstore(persist_directory: str = "./chroma_db") -> Chroma:
|
||||
"""Create or load a Chroma vector store with OpenAI embeddings."""
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
return Chroma(
|
||||
collection_name="knowledge",
|
||||
embedding_function=embeddings,
|
||||
persist_directory=persist_directory,
|
||||
)
|
||||
# ---------------------------------------------------------------------------
|
||||
# 1. Vector store (ChromaDB + OpenRouter embeddings)
|
||||
# ---------------------------------------------------------------------------
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
vector_store = Chroma(
|
||||
collection_name="knowledge",
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_DIR),
|
||||
)
|
||||
|
||||
def load_documents(directory: str, vectorstore: Chroma) -> None:
|
||||
"""Load .txt and .md files from *directory* into *vectorstore* using chunking."""
|
||||
# Helper to load documents from a directory and add to the store
|
||||
|
||||
def load_documents(directory: Path):
|
||||
"""Read .txt/.md files, split into chunks, and store in Chroma."""
|
||||
splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
|
||||
docs = []
|
||||
for root, _, files in os.walk(directory):
|
||||
for fname in files:
|
||||
if fname.lower().endswith(('.txt', '.md')):
|
||||
path = os.path.join(root, fname)
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
text = f.read()
|
||||
# Create Document objects
|
||||
docs.extend(
|
||||
[Document(page_content=chunk, metadata={"source": path}) for chunk in splitter.split_text(text)]
|
||||
)
|
||||
for file in directory.glob("**/*"):
|
||||
if file.suffix.lower() not in {".txt", ".md"}:
|
||||
continue
|
||||
text = file.read_text(encoding="utf-8")
|
||||
chunks = splitter.split_text(text)
|
||||
docs.extend([Document(page_content=c, metadata={"source": str(file)}) for c in chunks])
|
||||
if docs:
|
||||
vectorstore.add_documents(docs)
|
||||
vectorstore.persist()
|
||||
|
||||
# ---------------------
|
||||
# Tools
|
||||
# ---------------------
|
||||
|
||||
vectorstore = create_vectorstore()
|
||||
|
||||
# Ensure we have some data loaded – load from ./documents if collection empty
|
||||
if len(vectorstore.get_all_documents()) == 0:
|
||||
load_documents("./documents", vectorstore)
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 2. Tools
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def search_local_kb(query: str, top_k: int = 3) -> str:
|
||||
"""Search the local knowledge base for relevant passages."""
|
||||
docs = vectorstore.similarity_search(query, k=top_k)
|
||||
"""Semantic search in the local ChromaDB knowledge base."""
|
||||
docs = vector_store.similarity_search(query, k=top_k)
|
||||
if not docs:
|
||||
return "[Local KB] No relevant information found."
|
||||
result = "\n\n".join([f"{d.metadata.get('source', 'unknown')}\n{d.page_content}" for d in docs])
|
||||
return f"[Local KB]\n{result}"
|
||||
return "No relevant information found in the local knowledge base."
|
||||
return "\n---\n".join([f"{i+1}. {d.page_content[:200]}…" for i, d in enumerate(docs)])
|
||||
|
||||
@tool
|
||||
def web_search(query: str) -> str:
|
||||
"""Perform a web search using Tavily and return top results."""
|
||||
results = TavilySearchResults(query=query, max_results=3, api_key=TAVILY_API_KEY)
|
||||
if not results.results:
|
||||
return "[Web Search] No results found."
|
||||
snippets = []
|
||||
for r in results.results:
|
||||
snippets.append(f"{r.get('title', 'No title')}\n{r.get('content', 'No content')}\nURL: {r.get('url', '')}")
|
||||
return f"[Web Search]\n\n".join(snippets)
|
||||
|
||||
# ---------------------
|
||||
# Agent setup
|
||||
# ---------------------
|
||||
"""Perform a web search using Tavily."""
|
||||
tavily = TavilySearchRun(api_key=TAVILY_API_KEY, max_results=3)
|
||||
results = tavily.run(query)
|
||||
if not results:
|
||||
return "No web results found."
|
||||
return "\n---\n".join([f"{i+1}. {r['title']}\n{r['content'][:200]}…" for i, r in enumerate(results)])
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 3. Agent (deepagents)
|
||||
# ---------------------------------------------------------------------------
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
@@ -99,9 +99,11 @@ backend = CompositeBackend([
|
||||
])
|
||||
|
||||
system_prompt = (
|
||||
"You are a helpful RAG agent. For questions about local documents, use the tool `search_local_kb`. "
|
||||
"For current news or facts that may not be in your local knowledge base, use `web_search`. "
|
||||
"Return the answer prefixed with either `[Local KB]` or `[Web Search]` to indicate the source."
|
||||
"You are a helpful assistant. For a user query, first decide whether the
|
||||
answer can be found in the local knowledge base. If so, use the
|
||||
`search_local_kb` tool. If the query requires up‑to‑date information,
|
||||
use the `web_search` tool. Respond with the best answer and clearly
|
||||
state the source: `chromadb` or `tavily`."
|
||||
)
|
||||
|
||||
agent = create_deep_agent(
|
||||
@@ -111,25 +113,28 @@ agent = create_deep_agent(
|
||||
system_prompt=system_prompt,
|
||||
)
|
||||
|
||||
# ---------------------
|
||||
# CLI loop
|
||||
# ---------------------
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 4. CLI loop
|
||||
# ---------------------------------------------------------------------------
|
||||
async def main():
|
||||
print("RAG Agent ready. Type your question (or 'exit' to quit).")
|
||||
thread_id = "session-1"
|
||||
while True:
|
||||
user_input = input("\nQuery: ")
|
||||
user_input = input("\nЗапрос: ")
|
||||
if user_input.lower() in {"exit", "quit", "q"}:
|
||||
print("Goodbye!")
|
||||
break
|
||||
# Invoke agent
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=user_input)]},
|
||||
{"configurable": {"thread_id": "session-1"}},
|
||||
response = await agent.ainvoke(
|
||||
{"messages": [{"role": "user", "content": user_input}]},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
# The agent returns a list of messages; get the last one
|
||||
reply = result["messages"][-1].content
|
||||
print(f"\n{reply}")
|
||||
# The last message contains the assistant reply
|
||||
assistant_msg = response["messages"][-1].content
|
||||
print(f"\nОтвет:\n{assistant_msg}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Load documents once at startup
|
||||
docs_dir = Path("./documents")
|
||||
if docs_dir.exists():
|
||||
load_documents(docs_dir)
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user