From f2422c079882b433412fe11feebcc2cd9d8e80ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=93=D0=BB=D0=B5=D0=B1=20=D0=9D=D0=B8=D0=BA=D0=B8=D1=88?= =?UTF-8?q?=D0=B8=D0=BD?= Date: Thu, 4 Jun 2026 16:54:13 +0000 Subject: [PATCH] fix: main.py --- main.py | 140 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 82 insertions(+), 58 deletions(-) diff --git a/main.py b/main.py index 86c9f44..c35d8ff 100644 --- a/main.py +++ b/main.py @@ -1,120 +1,144 @@ import os import asyncio +import json 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 -# ----------------- Configuration ----------------- -# Load OpenRouter 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 in environment") - -# ----------------- LLM and Embeddings ----------------- +# --------------------------------------------------------------------------- +# 1. Настройка LLM и Embeddings (OpenRouter) +# --------------------------------------------------------------------------- llm = ChatOpenAI( model="openai/gpt-oss-20b:free", base_url="https://openrouter.ai/api/v1", - api_key=OPENAI_API_KEY, + api_key=os.getenv("OPENAI_API_KEY"), temperature=0.0, ) embeddings = OpenAIEmbeddings( model="text-embedding-3-small", base_url="https://openrouter.ai/api/v1", - api_key=OPENAI_API_KEY, + api_key=os.getenv("OPENAI_API_KEY"), ) -# ----------------- ChromaDB setup ----------------- +# --------------------------------------------------------------------------- +# 2. ChromaDB: загрузка .md файлов и поиск +# --------------------------------------------------------------------------- CHROMA_PATH = Path("./chroma_faq") CHROMA_COLLECTION = "faq_collection" + vector_store = Chroma( collection_name=CHROMA_COLLECTION, embedding_function=embeddings, persist_directory=str(CHROMA_PATH), ) -# Load markdown files into Chroma if not already loaded -if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()): - data_dir = Path("data") - docs = [] - for md_file in data_dir.glob("*.md"): - text = md_file.read_text(encoding="utf-8") - docs.append(Document(page_content=text, metadata={"source": md_file.name})) +# Если коллекция пуста, загрузим данные из data/*.md +if not vector_store.get_collection().list_documents(): + md_files = list(Path("data").glob("*.md")) + docs: List[Document] = [] + for f in md_files: + text = f.read_text(encoding="utf-8") + docs.append(Document(page_content=text, metadata={"source": f.name})) vector_store.add_documents(docs) vector_store.persist() -# ----------------- Tools ----------------- @tool -def search_course_docs(query: str) -> str: +def search_course_docs(query: str, k: int = 3) -> str: """Search the local FAQ collection for relevant passages.""" - results = vector_store.similarity_search(query, k=3) + results = vector_store.similarity_search(query, k=k) if not results: 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"{doc.metadata.get('source', 'unknown')}\n{doc.page_content}" for doc in results) + +# --------------------------------------------------------------------------- +# 3. MCP‑style tool (mocked via local JSON file) +# --------------------------------------------------------------------------- +META_JSON = Path("course_meta.json") +if not META_JSON.exists(): + # Создаём простую статическую мета‑информацию + META_JSON.write_text(json.dumps({ + "schedule": { + "Monday": "Lecture 1", + "Wednesday": "Lecture 2", + "Friday": "Lab" + }, + "instructor": "Dr. Example" + }, indent=2)) @tool def fetch_course_meta(query: str) -> str: - """Mock MCP-style tool that returns course metadata. - In production this would be an HTTP call to an MCP server. - Here we return a static JSON-like string based on the query. + """Return course metadata that matches the query. + The function simply looks for the query string in the keys of the JSON. """ - # Simple static mapping for demo purposes - meta = { - "schedule": "Monday 10:00-12:00, Wednesday 14:00-16:00", - "instructor": "Dr. Ivanov", - "location": "Room 101", - } - key = query.lower().strip() - return meta.get(key, f"No metadata found for '{query}'.") + data = json.loads(META_JSON.read_text()) + for key, value in data.items(): + if query.lower() in key.lower(): + return json.dumps({key: value}, indent=2) + return "No metadata found for the given query." -# ----------------- Backend ----------------- +# --------------------------------------------------------------------------- +# 4. DeepAgent с маршрутизацией +# --------------------------------------------------------------------------- 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.\n" - "When a user asks about course materials, use the search_course_docs tool.\n" - "When a user asks about schedule, instructor, or location, use the fetch_course_meta tool.\n" - "Do not use both tools unless absolutely necessary.\n" - "In your final answer, prefix the response with 'source: chroma' or 'source: mcp_meta' to indicate where the information came from." + "You are a helpful FAQ bot for a course.\n" + "If the question is about course content, use the search_course_docs tool.\n" + "If the question is about schedule, instructor, or other metadata, 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 where the answer came from." ), ) -# ----------------- CLI ----------------- +# --------------------------------------------------------------------------- +# 5. CLI +# --------------------------------------------------------------------------- PRESET_QUESTIONS = [ - "What topics are covered in the first lecture?", - "When is the next class?", - "Who is the instructor?", + "What topics are covered in Lecture 1?", # should hit chroma + "Who is the instructor for this course?", # should hit mcp_meta + "Explain the concept of polymorphism." ] -async def run_cli(): - print("Welcome to the Course FAQ Bot!\n") +async def run_agent(question: str) -> str: + result = await agent.ainvoke( + {"messages": [HumanMessage(content=question)]}, + {"configurable": {"thread_id": "session-1"}}, + ) + return result["messages"][-1].content + +async def main(): + print("\n--- FAQ Bot Demo ---\n") for i, q in enumerate(PRESET_QUESTIONS, 1): - print(f"{i}. {q}") - print("\nEnter your own question or type 'exit' to quit.") + print(f"Q{i}: {q}") + ans = await run_agent(q) + print(f"A{i}: {ans}\n") + + print("Enter your own question (or press Ctrl+C to exit):") while True: - user_input = input("\n> ") - if user_input.lower() in {"exit", "quit"}: - print("Goodbye!") + try: + user_q = input("> ") + if not user_q.strip(): + continue + ans = await run_agent(user_q) + print(ans) + except KeyboardInterrupt: + print("\nExiting.") break - result = await agent.ainvoke( - {"messages": ["HumanMessage(content=\"{}\")".format(user_input)]}, - {"configurable": {"thread_id": "session-1"}}, - ) - # The agent returns a dict with 'messages'; take the last one - content = result["messages"][-1].content - print(content) if __name__ == "__main__": - asyncio.run(run_cli()) + asyncio.run(main())