fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,73 +1,178 @@
|
||||
"""
|
||||
# main.py
|
||||
# FAQ bot using deepagents, ChromaDB and a single MCP‑style HTTP tool.
|
||||
# The agent decides whether to query the local knowledge base or the
|
||||
# external metadata service and annotates the answer with a `source` field.
|
||||
"""
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from langchain_ollama import ChatOllama
|
||||
from typing import List, Dict
|
||||
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
from langchain.embeddings import OllamaEmbeddings
|
||||
from langchain.schema import Document
|
||||
from langchain.prompts import ChatPromptTemplate
|
||||
from langchain.chains import LLMChain
|
||||
from langchain_core.documents import Document
|
||||
from langchain_core.messages import HumanMessage, SystemMessage
|
||||
from langchain.tools import tool
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
|
||||
# 1. Load FAQ into Chroma
|
||||
# ---------------------------------------------------------------------------
|
||||
# Configuration
|
||||
# ---------------------------------------------------------------------------
|
||||
# Load API key from .env or environment variable
|
||||
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
||||
if not OPENAI_API_KEY:
|
||||
raise RuntimeError("OPENAI_API_KEY not set")
|
||||
|
||||
def load_faq_to_chroma(md_path: str, persist_dir: str = "./chroma_faq"):
|
||||
from langchain.document_loaders import TextLoader
|
||||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||||
# LLM configuration – OpenRouter
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
loader = TextLoader(md_path)
|
||||
docs = loader.load()
|
||||
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
|
||||
texts = splitter.split_documents(docs)
|
||||
embeddings = OllamaEmbeddings(model="nomic-embed-text")
|
||||
chroma = Chroma.from_documents(texts, embeddings, persist_directory=persist_dir)
|
||||
chroma.persist()
|
||||
return chroma
|
||||
# Embeddings – OpenRouter
|
||||
embeddings = OpenAIEmbeddings(
|
||||
model="text-embedding-3-small",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=OPENAI_API_KEY,
|
||||
)
|
||||
|
||||
# 2. Search function
|
||||
# ---------------------------------------------------------------------------
|
||||
# ChromaDB setup
|
||||
# ---------------------------------------------------------------------------
|
||||
CHROMA_PATH = Path("./chroma_faq")
|
||||
CHROMA_COLLECTION = "faq_collection"
|
||||
|
||||
def search_course_docs(query: str, k: int = 3):
|
||||
chroma = Chroma(persist_directory="./chroma_faq", embedding_function=OllamaEmbeddings(model="nomic-embed-text"))
|
||||
results = chroma.similarity_search(query, k=k)
|
||||
return [doc.page_content for doc in results]
|
||||
vector_store = Chroma(
|
||||
collection_name=CHROMA_COLLECTION,
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_PATH),
|
||||
)
|
||||
|
||||
# 3. MCP-style tool
|
||||
# Load markdown files into Chroma if not already persisted
|
||||
if not CHROMA_PATH.exists() or not list(CHROMA_PATH.iterdir()):
|
||||
def load_faq_to_chroma(md_dir: str = "data"):
|
||||
md_path = Path(md_dir)
|
||||
docs: List[Document] = []
|
||||
for file in md_path.glob("*.md"):
|
||||
text = file.read_text(encoding="utf-8")
|
||||
docs.append(Document(page_content=text, metadata={"source": file.name}))
|
||||
vector_store.add_documents(docs)
|
||||
vector_store.persist()
|
||||
|
||||
def fetch_course_meta(query: str):
|
||||
# For demo, use static JSON file
|
||||
meta_path = Path("meta.json")
|
||||
load_faq_to_chroma()
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 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(d.page_content for d in docs)
|
||||
|
||||
# MCP‑style tool – simple HTTP GET to a local JSON file
|
||||
# For the purpose of this assignment we use a static JSON file
|
||||
# located at ./meta/course_meta.json
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""Return metadata that matches the query from a local JSON file."""
|
||||
meta_path = Path("./meta/course_meta.json")
|
||||
if not meta_path.exists():
|
||||
return {"error": "Meta not found"}
|
||||
meta = json.loads(meta_path.read_text())
|
||||
# simple search by key
|
||||
return meta.get(query, {})
|
||||
return "Metadata file not found."
|
||||
data = json.loads(meta_path.read_text(encoding="utf-8"))
|
||||
# Very naive matching: return any entry where the query is a substring
|
||||
matches = [item for item in data if query.lower() in item.get("title", "").lower()]
|
||||
if not matches:
|
||||
return "No matching metadata found."
|
||||
return json.dumps(matches, indent=2)
|
||||
|
||||
# 4. Agent logic
|
||||
# ---------------------------------------------------------------------------
|
||||
# Backend for deepagents
|
||||
# ---------------------------------------------------------------------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
def answer_question(question: str):
|
||||
# Simple heuristic: if question contains "schedule" or "метаданные" use meta
|
||||
if any(word in question.lower() for word in ["schedule", "расписание", "метаданные"]):
|
||||
source = "mcp_meta"
|
||||
answer = fetch_course_meta(question)
|
||||
else:
|
||||
source = "chroma"
|
||||
answer = search_course_docs(question, k=1)[0]
|
||||
return {"answer": answer, "source": source}
|
||||
# ---------------------------------------------------------------------------
|
||||
# Agent definition
|
||||
# ---------------------------------------------------------------------------
|
||||
# System prompt instructs the agent to choose the appropriate tool and
|
||||
# to annotate the answer with a `source` field.
|
||||
SYSTEM_PROMPT = (
|
||||
"You are an FAQ assistant for a course.\n"
|
||||
"If the user asks about course materials, use the `search_course_docs` tool.\n"
|
||||
"If the user asks about schedule or metadata, use the `fetch_course_meta` tool.\n"
|
||||
"Respond in JSON format with two fields: `answer` (string) and `source` (either `chroma` or `mcp_meta`).\n"
|
||||
"Do not call both tools unless absolutely necessary."
|
||||
)
|
||||
|
||||
if __name__ == "__main__":
|
||||
# CLI with preset questions
|
||||
preset = [
|
||||
"Что такое ChromaDB?",
|
||||
"Как подключить Ollama embeddings?",
|
||||
"Когда будет расписание следующего занятия?"
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[search_course_docs, fetch_course_meta],
|
||||
backend=backend,
|
||||
system_prompt=SYSTEM_PROMPT,
|
||||
)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CLI helpers
|
||||
# ---------------------------------------------------------------------------
|
||||
PRESET_QUESTIONS = [
|
||||
"What topics are covered in the first lecture?", # chroma
|
||||
"How can I access the lecture slides?", # chroma
|
||||
"What is the schedule for the next week?", # mcp_meta
|
||||
]
|
||||
for q in preset:
|
||||
res = answer_question(q)
|
||||
print(f"Q: {q}\nA: {res['answer']}\nSource: {res['source']}\n")
|
||||
# interactive
|
||||
|
||||
async def run_interactive():
|
||||
print("FAQ Bot – type your question (or 'exit' to quit).\n")
|
||||
while True:
|
||||
q = input("Ask a question (or 'exit'): ")
|
||||
if q.lower() == "exit":
|
||||
user_input = input("> ")
|
||||
if user_input.lower() in {"exit", "quit"}:
|
||||
break
|
||||
res = answer_question(q)
|
||||
print(f"A: {res['answer']} (source: {res['source']})")
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=user_input)]},
|
||||
{"configurable": {"thread_id": "session-1"}},
|
||||
)
|
||||
# The agent returns a list of messages; the last is the assistant
|
||||
assistant_msg = result["messages"][-1].content
|
||||
try:
|
||||
data = json.loads(assistant_msg)
|
||||
print(f"\nAnswer: {data['answer']}\nSource: {data['source']}\n")
|
||||
except Exception:
|
||||
print("\nUnexpected response format:\n", assistant_msg)
|
||||
|
||||
async def run_presets():
|
||||
for q in PRESET_QUESTIONS:
|
||||
print(f"\nQuestion: {q}")
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=q)]},
|
||||
{"configurable": {"thread_id": "session-1"}},
|
||||
)
|
||||
assistant_msg = result["messages"][-1].content
|
||||
try:
|
||||
data = json.loads(assistant_msg)
|
||||
print(f"Answer: {data['answer']}\nSource: {data['source']}")
|
||||
except Exception:
|
||||
print("Unexpected response format:\n", assistant_msg)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Entry point
|
||||
# ---------------------------------------------------------------------------
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="FAQ Bot CLI")
|
||||
parser.add_argument("--presets", action="store_true", help="Run preset questions")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.presets:
|
||||
asyncio.run(run_presets())
|
||||
else:
|
||||
asyncio.run(run_interactive())
|
||||
|
||||
Reference in New Issue
Block a user