fix(needs_fixes): 5 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,78 +1,22 @@
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
from langchain_core.documents import Document
|
||||
from langchain.tools import tool
|
||||
from langchain.agents import AgentExecutor, create_openai_tools_agent
|
||||
from langchain.agents import Tool
|
||||
from langchain_community.utilities import RetrievalQA
|
||||
from langchain_community.vectorstores import Chroma as ChromaStore
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
from langchain_core.messages import HumanMessage
|
||||
|
||||
# ---------- Configuration ----------
|
||||
# ---------------------------
|
||||
# Configuration
|
||||
# ---------------------------
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
if not OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY not set in environment")
|
||||
|
||||
# ---------- Embeddings & Vector Store ----------
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
vector_store = ChromaStore(
|
||||
collection_name="faq_collection",
|
||||
embedding_function=embeddings,
|
||||
persist_directory="./chroma_faq",
|
||||
)
|
||||
|
||||
# ---------- Load FAQ into Chroma ----------
|
||||
|
||||
def load_faq_to_chroma(data_dir: str = "data"):
|
||||
"""Load all .md files from data_dir into the Chroma vector store.
|
||||
The function clears the existing collection before loading.
|
||||
"""
|
||||
vector_store.delete_collection()
|
||||
docs = []
|
||||
for md_file in Path(data_dir).glob("*.md"):
|
||||
text = md_file.read_text(encoding="utf-8")
|
||||
docs.append(Document(page_content=text, metadata={"source": md_file.name}))
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
|
||||
# ---------- Tools ----------
|
||||
@tool
|
||||
def search_course_docs(query: str, k: int = 3) -> str:
|
||||
"""Search the local FAQ collection for relevant passages."""
|
||||
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"{doc.metadata.get('source', 'unknown')}\n{doc.page_content}" for doc in docs])
|
||||
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""MCP‑style tool that queries a local mock server for course metadata.
|
||||
The mock server should serve a JSON file at http://localhost:8000/meta.json.
|
||||
"""
|
||||
url = "http://localhost:8000/meta.json"
|
||||
try:
|
||||
response = httpx.get(url, timeout=5.0)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
except Exception as e:
|
||||
return f"Error fetching metadata: {e}"
|
||||
# Simple lookup: return value if query matches a key (case‑insensitive)
|
||||
key = query.strip().lower()
|
||||
value = data.get(key)
|
||||
if value is None:
|
||||
return f"No metadata entry found for '{query}'."
|
||||
return f"{key}: {value}"
|
||||
|
||||
# ---------- Agent Setup ----------
|
||||
# LLM via OpenRouter
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
@@ -80,49 +24,129 @@ llm = ChatOpenAI(
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
# Define the system prompt with routing rule
|
||||
system_prompt = (
|
||||
"You are a helpful assistant that answers questions about the course. "
|
||||
"If the question is about course content, use the search_course_docs tool. "
|
||||
"If the question is about schedule, metadata, or other non‑content info, "
|
||||
"use the fetch_course_meta tool. Do not call both tools unless the question "
|
||||
"explicitly requires both. In your final answer, prepend 'source: chroma' "
|
||||
"or 'source: mcp_meta' to indicate which tool provided the information."
|
||||
# Embeddings via OpenRouter
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
# Create Tool objects
|
||||
search_tool = Tool(name="search_course_docs", func=search_course_docs, description="Search local course documents.")
|
||||
meta_tool = Tool(name="fetch_course_meta", func=fetch_course_meta, description="Fetch course metadata from MCP mock server.")
|
||||
# Chroma vector store (persisted)
|
||||
CHROMA_PATH = Path("./chroma_faq")
|
||||
vector_store = Chroma(
|
||||
collection_name="faq_collection",
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_PATH),
|
||||
)
|
||||
|
||||
# Build the agent executor
|
||||
agent = create_openai_tools_agent(llm=llm, tools=[search_tool, meta_tool], system_message=system_prompt)
|
||||
agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=[search_tool, meta_tool], verbose=True)
|
||||
# ---------------------------
|
||||
# Data loading
|
||||
# ---------------------------
|
||||
|
||||
# ---------- CLI ----------
|
||||
async def run_cli():
|
||||
# Preload data if not already present
|
||||
if not Path("./chroma_faq").exists():
|
||||
load_faq_to_chroma()
|
||||
|
||||
# Predefined questions
|
||||
predefined = [
|
||||
"What is the main topic of the first lecture?",
|
||||
"Explain the concept of polymorphism in the course.",
|
||||
"What is the schedule for the next week?",
|
||||
]
|
||||
print("--- Predefined questions ---")
|
||||
for i, q in enumerate(predefined, 1):
|
||||
print(f"{i}. {q}")
|
||||
print("\nEnter a number to ask a predefined question or type your own query.")
|
||||
user_input = input("> ")
|
||||
if user_input.isdigit() and 1 <= int(user_input) <= len(predefined):
|
||||
query = predefined[int(user_input)-1]
|
||||
def load_faq_to_chroma(md_folder: str = "data"):
|
||||
"""Load all .md files from md_folder into ChromaDB.
|
||||
Each file is split into chunks and added to the vector store.
|
||||
"""
|
||||
md_path = Path(md_folder)
|
||||
if not md_path.exists():
|
||||
raise FileNotFoundError(f"Markdown folder {md_folder} not found")
|
||||
docs = []
|
||||
for md_file in md_path.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()]
|
||||
for i, chunk in enumerate(chunks):
|
||||
docs.append(Document(page_content=chunk, metadata={"source": md_file.name, "chunk": i}))
|
||||
if docs:
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
else:
|
||||
query = user_input
|
||||
print("No markdown files found to load.")
|
||||
|
||||
result = await agent_executor.ainvoke({"input": query})
|
||||
print("\n--- Answer ---")
|
||||
print(result["output"])
|
||||
# ---------------------------
|
||||
# Tools
|
||||
# ---------------------------
|
||||
@tool
|
||||
def search_course_docs(query: str, k: int = 3) -> str:
|
||||
"""Search the FAQ knowledge base for relevant information."""
|
||||
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"**{doc.metadata.get('source')}** (chunk {doc.metadata.get('chunk')}):\n{doc.page_content}" for doc in docs)
|
||||
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""Mock MCP-style tool that returns course metadata.
|
||||
In production this would perform an HTTP GET to an MCP server.
|
||||
Here we return a static JSON-like string for simplicity.
|
||||
"""
|
||||
# Static mock data
|
||||
meta = {
|
||||
"schedule": {
|
||||
"Monday": "Lecture 1: Introduction",
|
||||
"Wednesday": "Lecture 2: Advanced Topics",
|
||||
"Friday": "Lab Session"
|
||||
},
|
||||
"instructor": "Dr. Jane Doe",
|
||||
"credits": 3
|
||||
}
|
||||
return f"Course metadata: {meta}"
|
||||
|
||||
# ---------------------------
|
||||
# Backend setup
|
||||
# ---------------------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ---------------------------
|
||||
# Agent creation
|
||||
# ---------------------------
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[search_course_docs, fetch_course_meta],
|
||||
backend=backend,
|
||||
system_prompt="You are a helpful FAQ bot for the course. Use the search_course_docs tool for questions about lecture materials, and fetch_course_meta for questions about schedule or metadata. In your answer, clearly indicate the source: either 'chroma' or 'mcp_meta'. Do not use both tools unless necessary.",
|
||||
)
|
||||
|
||||
# ---------------------------
|
||||
# CLI
|
||||
# ---------------------------
|
||||
PRESET_QUESTIONS = [
|
||||
"What topics are covered in Lecture 1?", # should hit chroma
|
||||
"Explain the concept of tokenization in NLP.", # chroma
|
||||
"When is the next lab session?", # should hit mcp_meta
|
||||
]
|
||||
|
||||
async def run_agent(question: str, thread_id: str = "session-1"):
|
||||
result = await agent.ainvoke(
|
||||
{"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")
|
||||
|
||||
async def main():
|
||||
# Load data if not already loaded
|
||||
if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
|
||||
print("Loading FAQ data into Chroma...")
|
||||
load_faq_to_chroma()
|
||||
else:
|
||||
print("Chroma database already loaded.")
|
||||
|
||||
# Run preset questions
|
||||
for i, q in enumerate(PRESET_QUESTIONS, 1):
|
||||
await run_agent(q, thread_id=f"preset-{i}")
|
||||
|
||||
# Interactive mode
|
||||
print("Enter your own questions (type 'exit' to quit):")
|
||||
while True:
|
||||
user_input = input("> ")
|
||||
if user_input.lower() in {"exit", "quit"}:
|
||||
break
|
||||
await run_agent(user_input, thread_id="interactive")
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(run_cli())
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user