fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,19 +1,20 @@
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
from langchain_core.documents import Document
|
||||
from langchain_core.messages import HumanMessage
|
||||
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
|
||||
# ---------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
if not OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY not set in environment")
|
||||
@@ -26,93 +27,111 @@ llm = ChatOpenAI(
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
# Embeddings for Chroma
|
||||
# Embeddings via OpenRouter
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
# ---------------------------
|
||||
# Chroma DB utilities
|
||||
# ---------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# Chroma persistence
|
||||
# ---------------------------------------------------------------------------
|
||||
CHROMA_DIR = Path("./chroma_faq")
|
||||
CHROMA_DIR.mkdir(parents=True, exist_ok=True)
|
||||
vector_store = Chroma(
|
||||
collection_name="faq_collection",
|
||||
persist_directory=str(CHROMA_DIR),
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_DIR),
|
||||
)
|
||||
|
||||
|
||||
def load_faq_to_chroma(md_dir: str = "data"):
|
||||
"""Load all .md files from md_dir into ChromaDB.
|
||||
Each file is split into chunks and added to the vector store.
|
||||
# ---------------------------------------------------------------------------
|
||||
# Utility: load markdown files into Chroma
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def load_faq_to_chroma() -> str:
|
||||
"""Load all .md files from data/ into the Chroma vector store.
|
||||
This tool is idempotent – it will overwrite existing collection.
|
||||
"""
|
||||
md_path = Path(md_dir)
|
||||
if not md_path.exists():
|
||||
raise FileNotFoundError(f"Markdown directory {md_dir} not found")
|
||||
for md_file in md_path.glob("*.md"):
|
||||
data_dir = Path("data")
|
||||
if not data_dir.exists():
|
||||
return "Data directory not found."
|
||||
docs: List[Document] = []
|
||||
for md_file in data_dir.glob("*.md"):
|
||||
text = md_file.read_text(encoding="utf-8")
|
||||
# Simple chunking: split by double newlines
|
||||
chunks = [c.strip() for c in text.split("\n\n") if c.strip()]
|
||||
docs = [Document(page_content=c, metadata={"source": md_file.name}) for c in chunks]
|
||||
docs.append(Document(page_content=text, metadata={"source": md_file.name}))
|
||||
if docs:
|
||||
vector_store.delete_collection()
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
vector_store.persist()
|
||||
return f"Loaded {len(docs)} documents into Chroma."
|
||||
return "No markdown files found."
|
||||
|
||||
# ---------------------------
|
||||
# Tools
|
||||
# ---------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tool: search knowledge base
|
||||
# ---------------------------------------------------------------------------
|
||||
@tool
|
||||
def search_course_docs(query: str, k: int = 3) -> str:
|
||||
"""Search the local FAQ ChromaDB for relevant passages."""
|
||||
"""Search the FAQ collection for relevant passages.
|
||||
Returns a string with the top k passages and a source tag.
|
||||
"""
|
||||
docs = vector_store.similarity_search(query, k=k)
|
||||
if not docs:
|
||||
return "No relevant information found in the course materials."
|
||||
return "\n\n---\n\n".join(f"{d.metadata.get('source', 'unknown')}\n{d.page_content}" for d in docs)
|
||||
return "No relevant information found in the FAQ."
|
||||
results = "\n\n".join(f"{i+1}. {doc.page_content}" for i, doc in enumerate(docs))
|
||||
return f"source: chroma\n{results}"
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# MCP-style tool: fetch course metadata
|
||||
# ---------------------------------------------------------------------------
|
||||
# For simplicity we use a static JSON file in the repo. In production this
|
||||
# would be an HTTP call to an MCP server.
|
||||
METADATA_FILE = Path("course_meta.json")
|
||||
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""Mock MCP-style tool that fetches course metadata from a local JSON file.
|
||||
In production this would be an HTTP call to an MCP server.
|
||||
"""Return metadata that matches the query.
|
||||
The function performs a simple keyword search in the static JSON.
|
||||
"""
|
||||
# For simplicity, we use a local JSON file. In a real scenario, replace with httpx.get.
|
||||
meta_path = Path("course_meta.json")
|
||||
if not meta_path.exists():
|
||||
return "Course metadata not available."
|
||||
data = json.loads(meta_path.read_text(encoding="utf-8"))
|
||||
# Very naive search: return any entry where query is a substring of title or description
|
||||
results = [f"{item['title']}: {item['description']}" for item in data if query.lower() in item.get('title', '').lower() or query.lower() in item.get('description', '').lower()]
|
||||
return "\n".join(results) if results else "No matching metadata found."
|
||||
if not METADATA_FILE.exists():
|
||||
return "Metadata file not found."
|
||||
data = json.loads(METADATA_FILE.read_text(encoding="utf-8"))
|
||||
matches = [item for item in data if query.lower() in item.get("title", "").lower()]
|
||||
if not matches:
|
||||
return "No metadata matches the query."
|
||||
return f"source: mcp_meta\n" + json.dumps(matches, indent=2)
|
||||
|
||||
# ---------------------------
|
||||
# Agent setup
|
||||
# ---------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend setup
|
||||
# ---------------------------------------------------------------------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent definition
|
||||
# ---------------------------------------------------------------------------
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[search_course_docs, fetch_course_meta],
|
||||
tools=[load_faq_to_chroma, search_course_docs, fetch_course_meta],
|
||||
backend=backend,
|
||||
system_prompt=(
|
||||
"You are a helpful FAQ bot for the course.\n"
|
||||
"When a user asks about course content, use the search_course_docs tool.\n"
|
||||
"When a user asks about schedule, metadata, or other non-content info, use fetch_course_meta.\n"
|
||||
"Do not call both tools unless absolutely necessary.\n"
|
||||
"In your final answer, prepend 'source: chroma' or 'source: mcp_meta' to indicate the origin."
|
||||
"You are a helpful FAQ bot for a course. "
|
||||
"Use the search_course_docs tool for questions about lecture materials. "
|
||||
"Use fetch_course_meta for questions about schedule or metadata. "
|
||||
"Do not call both tools unless necessary. "
|
||||
"Always prefix your answer with the source tag (chroma or mcp_meta)."
|
||||
),
|
||||
)
|
||||
|
||||
# ---------------------------
|
||||
# CLI
|
||||
# ---------------------------
|
||||
# ---------------------------------------------------------------------------
|
||||
# CLI helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
PRESET_QUESTIONS = [
|
||||
"What is the deadline for the final project?", # likely in metadata
|
||||
"Explain the concept of tokenization in NLP.", # content
|
||||
"How many lectures are there in the first module?", # content
|
||||
"What is the deadline for the final project?", # should hit metadata
|
||||
"Explain the concept of polymorphism in OOP.", # should hit FAQ
|
||||
"How many lectures are there in the first module?", # metadata
|
||||
]
|
||||
|
||||
async def run_agent(question: str, thread_id: str = "session-1"):
|
||||
@@ -120,24 +139,25 @@ async def run_agent(question: str, thread_id: str = "session-1"):
|
||||
{"messages": [HumanMessage(content=question)]},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
# The last message is the agent's reply
|
||||
reply = result["messages"][-1].content
|
||||
print(f"\nQ: {question}\nA: {reply}\n")
|
||||
return result["messages"][-1].content
|
||||
|
||||
async def main():
|
||||
# Load data into Chroma if not already persisted
|
||||
if not CHROMA_DIR.exists() or not any(CHROMA_DIR.iterdir()):
|
||||
print("Loading FAQ data into ChromaDB...")
|
||||
load_faq_to_chroma()
|
||||
print("\n--- Predefined questions ---")
|
||||
# Ensure FAQ is loaded once
|
||||
await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content="load_faq_to_chroma()")]},
|
||||
{"configurable": {"thread_id": "init"}},
|
||||
)
|
||||
print("\n--- Preset questions ---")
|
||||
for q in PRESET_QUESTIONS:
|
||||
await run_agent(q)
|
||||
ans = await run_agent(q)
|
||||
print(f"Q: {q}\nA: {ans}\n")
|
||||
print("\n--- Interactive mode (type 'exit' to quit) ---")
|
||||
while True:
|
||||
user_input = input("You: ")
|
||||
user_input = input("> ")
|
||||
if user_input.lower() in {"exit", "quit"}:
|
||||
break
|
||||
await run_agent(user_input)
|
||||
ans = await run_agent(user_input)
|
||||
print(ans)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user