fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,5 +1,7 @@
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
@@ -7,16 +9,20 @@ from langchain_core.documents import Document
|
||||
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 -----------------
|
||||
# Load API key from .env or environment variable
|
||||
os.environ.setdefault("OPENAI_API_KEY", os.getenv("OPENAI_API_KEY", ""))
|
||||
# ---------------------------
|
||||
# Configuration
|
||||
# ---------------------------
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
if not OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY not set in environment")
|
||||
|
||||
# LLM via OpenRouter
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
api_key=OPENAI_API_KEY,
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
@@ -24,97 +30,114 @@ llm = ChatOpenAI(
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
# ----------------- Chroma DB -----------------
|
||||
CHROMA_PATH = Path("./chroma_faq")
|
||||
CHROMA_COLLECTION = "faq_collection"
|
||||
# ---------------------------
|
||||
# Chroma DB utilities
|
||||
# ---------------------------
|
||||
CHROMA_DIR = Path("./chroma_faq")
|
||||
CHROMA_DIR.mkdir(parents=True, exist_ok=True)
|
||||
vector_store = Chroma(
|
||||
collection_name=CHROMA_COLLECTION,
|
||||
collection_name="faq_collection",
|
||||
persist_directory=str(CHROMA_DIR),
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_PATH),
|
||||
)
|
||||
|
||||
# Load markdown files into Chroma (idempotent)
|
||||
DATA_DIR = Path("./data")
|
||||
if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
|
||||
docs = []
|
||||
for md_file in DATA_DIR.glob("*.md"):
|
||||
|
||||
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.
|
||||
"""
|
||||
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"):
|
||||
text = md_file.read_text(encoding="utf-8")
|
||||
docs.append(Document(page_content=text, metadata={"source": md_file.name}))
|
||||
vector_store.add_documents(docs)
|
||||
# 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]
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
|
||||
# ----------------- Tools -----------------
|
||||
# ---------------------------
|
||||
# Tools
|
||||
# ---------------------------
|
||||
@tool
|
||||
def search_course_docs(query: str) -> str:
|
||||
"""Search the local FAQ collection for relevant passages."""
|
||||
results = vector_store.similarity_search(query, k=3)
|
||||
if not results:
|
||||
def search_course_docs(query: str, k: int = 3) -> str:
|
||||
"""Search the local FAQ ChromaDB 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".join(f"{doc.metadata.get('source', 'unknown')}\n{doc.page_content}" for doc in results)
|
||||
return "\n\n---\n\n".join(f"{d.metadata.get('source', 'unknown')}\n{d.page_content}" for d in docs)
|
||||
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""Mock MCP-style tool that returns course metadata.
|
||||
"""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.
|
||||
Here we return a static JSON-like string based on the query.
|
||||
"""
|
||||
meta = {
|
||||
"schedule": "Mon 10-12, Wed 14-16, Fri 9-11",
|
||||
"instructor": "Dr. Ivanov",
|
||||
"credits": 3,
|
||||
}
|
||||
# Simple keyword matching
|
||||
if "schedule" in query.lower():
|
||||
return f"Course schedule: {meta['schedule']}"
|
||||
if "instructor" in query.lower():
|
||||
return f"Instructor: {meta['instructor']}"
|
||||
if "credits" in query.lower():
|
||||
return f"Credits: {meta['credits']}"
|
||||
return "No metadata matches your query."
|
||||
# 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."
|
||||
|
||||
# ----------------- Backend -----------------
|
||||
# ---------------------------
|
||||
# Agent setup
|
||||
# ---------------------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# ----------------- Agent -----------------
|
||||
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, instructor, or credits. Do not use both tools unless necessary. In your final answer, prefix the source with 'source: chroma' or 'source: mcp_meta'.",
|
||||
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."
|
||||
),
|
||||
)
|
||||
|
||||
# ----------------- CLI -----------------
|
||||
# ---------------------------
|
||||
# CLI
|
||||
# ---------------------------
|
||||
PRESET_QUESTIONS = [
|
||||
"What topics are covered in lecture 3?",
|
||||
"When is the next class?",
|
||||
"Who is the instructor for this course?",
|
||||
"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
|
||||
]
|
||||
|
||||
async def run_agent(question: str, thread_id: str = "session-1"):
|
||||
result = await agent.ainvoke(
|
||||
{"messages": ["HumanMessage(content=\"{}\")".format(question)]},
|
||||
{"messages": [HumanMessage(content=question)]},
|
||||
{"configurable": {"thread_id": thread_id}},
|
||||
)
|
||||
# The agent returns a dict with 'messages'; extract last content
|
||||
content = result["messages"][-1].content
|
||||
print(f"\nQ: {question}\nA: {content}\n")
|
||||
# The last message is the agent's reply
|
||||
reply = result["messages"][-1].content
|
||||
print(f"\nQ: {question}\nA: {reply}\n")
|
||||
|
||||
async def main():
|
||||
print("--- FAQ Bot Demo ---")
|
||||
for i, q in enumerate(PRESET_QUESTIONS, 1):
|
||||
await run_agent(q, thread_id=f"demo-{i}")
|
||||
print("Enter your own question (or 'exit' to quit):")
|
||||
# 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 ---")
|
||||
for q in PRESET_QUESTIONS:
|
||||
await run_agent(q)
|
||||
print("\n--- Interactive mode (type 'exit' to quit) ---")
|
||||
while True:
|
||||
q = input("> ")
|
||||
if q.lower() in {"exit", "quit"}:
|
||||
user_input = input("You: ")
|
||||
if user_input.lower() in {"exit", "quit"}:
|
||||
break
|
||||
await run_agent(q, thread_id="interactive")
|
||||
await run_agent(user_input)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
Reference in New Issue
Block a user