fix(needs_fixes): 5 исправлений, 0 отстояно — main.py

main.py

@@ -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 deepagents import create_deep_agent
-from langchain.agents import Tool
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
-from langchain_community.utilities import RetrievalQA
+from langchain_core.messages import HumanMessage
-from langchain_community.vectorstores import Chroma as ChromaStore
 
-# ---------- 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 ----------
+# LLM via OpenRouter
-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 = 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
+# Embeddings via OpenRouter
-system_prompt = (
+embeddings = OpenAIEmbeddings(
-    "You are a helpful assistant that answers questions about the course. "
+    model="text-embedding-3-small",
-    "If the question is about course content, use the search_course_docs tool. "
+    base_url="https://openrouter.ai/api/v1",
-    "If the question is about schedule, metadata, or other non‑content info, "
+    api_key=OPENAI_API_KEY,
-    "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."
 )
 
-# Create Tool objects
+# Chroma vector store (persisted)
-search_tool = Tool(name="search_course_docs", func=search_course_docs, description="Search local course documents.")
+CHROMA_PATH = Path("./chroma_faq")
-meta_tool = Tool(name="fetch_course_meta", func=fetch_course_meta, description="Fetch course metadata from MCP mock server.")
+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)
+# Data loading
-agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=[search_tool, meta_tool], verbose=True)
+# ---------------------------
 
-# ---------- CLI ----------
+def load_faq_to_chroma(md_folder: str = "data"):
-async def run_cli():
+    """Load all .md files from md_folder into ChromaDB.
-    # Preload data if not already present
+    Each file is split into chunks and added to the vector store.
-    if not Path("./chroma_faq").exists():
+    """
-        load_faq_to_chroma()
+    md_path = Path(md_folder)
-
+    if not md_path.exists():
-    # Predefined questions
+        raise FileNotFoundError(f"Markdown folder {md_folder} not found")
-    predefined = [
+    docs = []
-        "What is the main topic of the first lecture?",
+    for md_file in md_path.glob("*.md"):
-        "Explain the concept of polymorphism in the course.",
+        text = md_file.read_text(encoding="utf-8")
-        "What is the schedule for the next week?",
+        # Simple chunking: split by double newlines
-    ]
+        chunks = [c.strip() for c in text.split("\n\n") if c.strip()]
-    print("--- Predefined questions ---")
+        for i, chunk in enumerate(chunks):
-    for i, q in enumerate(predefined, 1):
+            docs.append(Document(page_content=chunk, metadata={"source": md_file.name, "chunk": i}))
-        print(f"{i}. {q}")
+    if docs:
-    print("\nEnter a number to ask a predefined question or type your own query.")
+        vector_store.add_documents(docs)
-    user_input = input("> ")
+        vector_store.persist()
-    if user_input.isdigit() and 1 <= int(user_input) <= len(predefined):
-        query = predefined[int(user_input)-1]
     else:
-        query = user_input
+        print("No markdown files found to load.")
 
-    result = await agent_executor.ainvoke({"input": query})
+# ---------------------------
-    print("\n--- Answer ---")
+# Tools
-    print(result["output"])
+# ---------------------------
+@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())