fix(needs_fixes): 1 исправлений, 0 отстояно — main.py

main.py

@@ -1,142 +1,128 @@
 import os
 import asyncio
+import json
+import httpx
 from pathlib import Path
-from langchain_community.embeddings import OllamaEmbeddings
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_chroma import Chroma
 from langchain_core.documents import Document
-from langchain_openai import ChatOpenAI
 from langchain.tools import tool
-from deepagents import create_deep_agent
+from langchain.agents import AgentExecutor, create_openai_tools_agent
-from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from langchain.agents import Tool
-from langchain_core.messages import HumanMessage
+from langchain_community.utilities import RetrievalQA
+from langchain_community.vectorstores import Chroma as ChromaStore
 
-# ---------------------------
+# ---------- Configuration ----------
-# 1. Embeddings & Chroma setup
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-# ---------------------------
+if not OPENAI_API_KEY:
-# Using OllamaEmbeddings with nomic-embed-text as required by the "Исправить" section.
+    raise RuntimeError("OPENAI_API_KEY not set in environment")
-# The embeddings are used for both loading the FAQ and for the search tool.
-embeddings = OllamaEmbeddings(model="nomic-embed-text")
 
-# Persistent Chroma collection for the FAQ knowledge base.
+# ---------- Embeddings & Vector Store ----------
-vector_store = Chroma(
+embeddings = OpenAIEmbeddings(
-    collection_name="faq_collection",
+    model="text-embedding-3-small",
-    embedding_function=embeddings,
+    base_url="https://openrouter.ai/api/v1",
-    persist_directory="./chroma_faq"
+    api_key=OPENAI_API_KEY,
 )
 
-# ---------------------------
+vector_store = ChromaStore(
-# 2. Load FAQ markdown files into Chroma
+    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 persistent Chroma collection.
+    """Load all .md files from data_dir into the Chroma vector store.
-    Each file is split into documents with a simple line‑based splitter.
+    The function clears the existing collection before loading.
     """
-    data_path = Path(data_dir)
+    vector_store.delete_collection()
-    if not data_path.exists():
-        raise FileNotFoundError(f"Data directory {data_dir} not found")
     docs = []
-    for md_file in data_path.glob("*.md"):
+    for md_file in Path(data_dir).glob("*.md"):
         text = md_file.read_text(encoding="utf-8")
-        # Simple split by double newlines to create chunks
+        docs.append(Document(page_content=text, metadata={"source": md_file.name}))
-        for i, chunk in enumerate(text.split("\n\n")):
-            docs.append(Document(page_content=chunk, metadata={"source": md_file.name, "chunk": i}))
     vector_store.add_documents(docs)
     vector_store.persist()
 
-# ---------------------------
+# ---------- Tools ----------
-# 3. Tools
-# ---------------------------
 @tool
 def search_course_docs(query: str, k: int = 3) -> str:
-    """Search the FAQ knowledge base for relevant information."""
+    """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 FAQ."
+        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)
+    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:
-    """Mock MCP‑style tool that returns course metadata.
+    """MCP‑style tool that queries a local mock server for course metadata.
-    In production this would perform an HTTP GET to an MCP server.
+    The mock server should serve a JSON file at http://localhost:8000/meta.json.
-    Here we simply return a static JSON string based on the query.
     """
-    # Simple static mapping for demo purposes
+    url = "http://localhost:8000/meta.json"
-    meta = {
+    try:
-        "schedule": "Monday 10:00-12:00, Wednesday 14:00-16:00",
+        response = httpx.get(url, timeout=5.0)
-        "instructor": "Dr. Ivanov",
+        response.raise_for_status()
-        "credits": "3"
+        data = response.json()
-    }
+    except Exception as e:
-    key = query.lower().strip()
+        return f"Error fetching metadata: {e}"
-    return meta.get(key, f"No metadata found for '{query}'.")
+    # 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 ----------
-# 4. Agent setup with deepagents
-# ---------------------------
-# LLM via OpenRouter as per course requirement
 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,
 )
 
-backend = CompositeBackend([
+# Define the system prompt with routing rule
-    LocalShellBackend(workspace_dir="./workspace"),
-    FilesystemBackend(),
-])
-
-# System prompt instructs the agent to choose the appropriate tool and to label the source.
 system_prompt = (
-    "You are a helpful FAQ assistant.\n"
+    "You are a helpful assistant that answers questions about the course. "
-    "When a user asks a question about course materials, use the tool `search_course_docs`.\n"
+    "If the question is about course content, use the search_course_docs tool. "
-    "When a user asks about schedule, instructor, or credits, use the tool `fetch_course_meta`.\n"
+    "If the question is about schedule, metadata, or other non‑content info, "
-    "Do not call both tools unless necessary.\n"
+    "use the fetch_course_meta tool. Do not call both tools unless the question "
-    "In your final answer, prepend the source label: `source: chroma` or `source: mcp_meta`."
+    "explicitly requires both. In your final answer, prepend 'source: chroma' "
+    "or 'source: mcp_meta' to indicate which tool provided the information."
 )
 
-agent = create_deep_agent(
+# Create Tool objects
-    model=llm,
+search_tool = Tool(name="search_course_docs", func=search_course_docs, description="Search local course documents.")
-    tools=[search_course_docs, fetch_course_meta],
+meta_tool = Tool(name="fetch_course_meta", func=fetch_course_meta, description="Fetch course metadata from MCP mock server.")
-    backend=backend,
-    system_prompt=system_prompt,
-)
 
-# ---------------------------
+# Build the agent executor
-# 5. CLI
+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)
-PRESET_QUESTIONS = [
-    "What topics are covered in the first lecture?",
-    "Who is the instructor for this course?",
-    "When is the next class?"
-]
 
-async def run_agent(question: str, thread_id: str = "session-1"):
+# ---------- CLI ----------
-    result = await agent.ainvoke(
+async def run_cli():
-        {"messages": [HumanMessage(content=question)]},
+    # Preload data if not already present
-        {"configurable": {"thread_id": thread_id}},
+    if not Path("./chroma_faq").exists():
-    )
+        load_faq_to_chroma()
-    # The last message is the agent's response
-    return result["messages"][-1].content
 
-async def main():
+    # Predefined questions
-    # Ensure FAQ is loaded
+    predefined = [
-    load_faq_to_chroma()
+        "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]
+    else:
+        query = user_input
 
-    print("--- FAQ Bot Demo ---\n")
+    result = await agent_executor.ainvoke({"input": query})
-    for i, q in enumerate(PRESET_QUESTIONS, 1):
+    print("\n--- Answer ---")
-        print(f"Q{i}: {q}")
+    print(result["output"])
-        answer = await run_agent(q, thread_id=f"demo-{i}")
-        print(f"A{i}: {answer}\n")
-
-    # Interactive mode
-    print("Enter your own questions (type 'exit' to quit):")
-    while True:
-        user_input = input("> ")
-        if user_input.lower() in {"exit", "quit"}:
-            break
-        answer = await run_agent(user_input, thread_id="interactive")
-        print(answer)
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(run_cli())