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

main.py

@@ -1,146 +1,134 @@
 import os
 import asyncio
-import argparse
 from pathlib import Path
-
 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
 
-# -------------------- 1. LLM and Embeddings --------------------
+# ===================== CONFIG =====================
-llm = ChatOpenAI(
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-    model="openai/gpt-oss-20b:free",
+if not OPENAI_API_KEY:
-    base_url="https://openrouter.ai/api/v1",
+    raise RuntimeError("OPENAI_API_KEY is not set in environment")
-    api_key=os.getenv("OPENAI_API_KEY"),
-    temperature=0.0,
-)
 
+# ===================== EMBEDDINGS & VECTOR STORE =====================
 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,
 )
 
-# -------------------- 2. Chroma DB --------------------
-CHROMA_PATH = Path("./chroma_faq")
-CHROMA_COLLECTION = "course_faq"
-
 vector_store = Chroma(
-    collection_name=CHROMA_COLLECTION,
+    collection_name="faq_knowledge",
     embedding_function=embeddings,
-    persist_directory=str(CHROMA_PATH),
+    persist_directory="./chroma_faq",
 )
 
-# Persist changes
+# ===================== TOOL: SEARCH IN CHROMA =====================
-vector_store.persist()
-
-# -------------------- 3. Tools --------------------
 @tool
-def search_knowledge(query: str) -> str:
+def search_course_docs(query: str, k: int = 3) -> str:
-    """Search the knowledge base for relevant information."""
+    """Search the local FAQ knowledge base for relevant passages."""
-    docs = vector_store.similarity_search(query, k=3)
+    docs: list[Document] = vector_store.similarity_search(query, k=k)
-    return "\n".join(d.page_content for d in docs) if docs else "No results found in course materials."
+    if not docs:
+        return "No relevant information found in the course materials."
+    return "\n\n---\n\n".join(f"**{d.metadata.get('title', 'Untitled')}**\n{d.page_content}" for d in docs)
+
+# ===================== TOOL: FETCH METADATA (MCP‑STYLE) =====================
+# For the purpose of this assignment we use a static JSON file as the mock MCP server response.
+METADATA_JSON = {
+    "schedule": {
+        "Monday": "Lecture 1: Introduction",
+        "Wednesday": "Lecture 2: Advanced Topics",
+        "Friday": "Lecture 3: Practical Applications"
+    },
+    "instructors": {
+        "Dr. Smith": "smith@example.com",
+        "Prof. Doe": "doe@example.com"
+    }
+}
 
 @tool
 def fetch_course_meta(query: str) -> str:
-    """Fetch course metadata (schedule, syllabus, etc.) from a static JSON file."""
+    """Mock MCP tool that returns course metadata based on the query.
-    meta_path = Path("meta.json")
+    In production this would be an HTTP GET to an MCP server.
-    if not meta_path.exists():
+    """
-        return "Metadata file not found."
+    query = query.lower()
-    import json
+    if "schedule" in query:
-    data = json.loads(meta_path.read_text())
+        return "\n".join(f"{day}: {info}" for day, info in METADATA_JSON["schedule"].items())
-    query_lower = query.lower()
+    if "instructor" in query or "email" in query:
-    if "schedule" in query_lower:
+        return "\n".join(f"{name}: {email}" for name, email in METADATA_JSON["instructors"].items())
-        return f"Course schedule: {data.get('schedule', 'Not available')}"
+    return "No metadata matches your query."
-    if "syllabus" in query_lower:
+
-        return f"Syllabus URL: {data.get('syllabus_url', 'Not available')}"
+# ===================== LOAD FAQ TO CHROMA =====================
-    if "instructor" in query_lower:
+MD_DIR = Path("data")
-        return f"Instructor: {data.get('instructor', 'Not available')}"
+if not MD_DIR.exists():
-    # Default: return all
+    MD_DIR.mkdir(parents=True, exist_ok=True)
-    return json.dumps(data, indent=2)
+    # Create example markdown files if none exist
+    (MD_DIR / "faq1.md").write_text("# FAQ 1\nWhat is the course about?\nThe course covers advanced AI techniques.")
+    (MD_DIR / "faq2.md").write_text("# FAQ 2\nHow to install dependencies?\nRun `pip install -r requirements.txt`.")
+    (MD_DIR / "faq3.md").write_text("# FAQ 3\nWhere to find the schedule?\nCheck the course website.")
+
+# Chunking and persisting
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+
+for md_file in MD_DIR.glob("*.md"):
+    content = md_file.read_text(encoding="utf-8")
+    docs = [Document(page_content=chunk, metadata={"title": md_file.stem}) for chunk in text_splitter.split_text(content)]
+    vector_store.add_documents(docs)
+
+vector_store.persist()
+
+# ===================== AGENT SETUP =====================
+llm = ChatOpenAI(
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=OPENAI_API_KEY,
+    temperature=0.0,
+)
 
-# -------------------- 4. Backend --------------------
 backend = CompositeBackend([
     LocalShellBackend(workspace_dir="./workspace"),
     FilesystemBackend(),
 ])
 
-# -------------------- 5. Agent --------------------
-SYSTEM_PROMPT = (
-    "You are a helpful FAQ bot for the course.\n"
-    "Use the 'search_knowledge' tool to answer questions about course materials.\n"
-    "Use the 'fetch_course_meta' tool for questions about schedule, syllabus, instructor, etc.\n"
-    "Do not call both tools unnecessarily.\n"
-    "In your final answer, prepend 'source: chroma' or 'source: mcp_meta' to indicate which tool provided the information."
-)
-
 agent = create_deep_agent(
     model=llm,
-    tools=[search_knowledge, fetch_course_meta],
+    tools=[search_course_docs, fetch_course_meta],
     backend=backend,
-    system_prompt=SYSTEM_PROMPT,
+    system_prompt="You are a helpful FAQ assistant. Use only the provided tools. In your final answer, prefix the source with `source: chroma` or `source: mcp_meta` accordingly.",
 )
 
-# -------------------- 6. Data Loader --------------------
+# ===================== CLI =====================
+PRESET_QUESTIONS = [
+    "What is the course about?",  # chroma
+    "How to install dependencies?",  # chroma
+    "What is the lecture schedule?",  # mcp_meta
+]
 
-def load_faq_to_chroma():
+async def run_cli():
-    data_dir = Path("data")
+    print("=== FAQ Assistant ===")
-    if not data_dir.exists():
+    print("Type your question or 'exit' to quit.")
-        data_dir.mkdir()
+    for i, q in enumerate(PRESET_QUESTIONS, 1):
-        # Create sample markdown files if missing
+        print(f"\nPreset {i}: {q}")
-        (data_dir / "file1.md").write_text(
+        await handle_question(q)
-            "## Course Overview\nThis course covers advanced topics in AI. Topics include machine learning, deep learning, and natural language processing."
-        )
-        (data_dir / "file2.md").write_text(
-            "## FAQ\nQ: What is the schedule?\nA: Sessions are held on Mondays and Wednesdays.\nQ: Where can I find the syllabus?\nA: Syllabus is available on the course website."
-        )
-    docs = []
-    for md_file in data_dir.glob("*.md"):
-        text = md_file.read_text()
-        docs.append(Document(page_content=text, metadata={"source": md_file.name}))
-    vector_store.add_documents(docs)
-    vector_store.persist()
-    print(f"Loaded {len(docs)} documents into Chroma collection '{CHROMA_COLLECTION}'.")
-
-# -------------------- 7. CLI --------------------
-PRESET_QUESTIONS = {
-    "1": "What topics are covered in the course?",
-    "2": "Where can I find the syllabus?",
-    "3": "What is the course schedule?",
-}
-
-async def run_question(question: str, thread_id: str = "session-1"):
-    result = await agent.ainvoke(
-        {"messages": ["HumanMessage(content=\"{}\")".format(question)]},
-        {"configurable": {"thread_id": thread_id}},
-    )
-    # The agent returns a dict with 'messages'; extract last message
-    content = result["messages"][-1].content
-    print(content)
-
-async def main():
-    # Ensure data is loaded
-    load_faq_to_chroma()
-
-    parser = argparse.ArgumentParser(description="FAQ Bot CLI")
-    parser.add_argument("--preset", choices=["1", "2", "3"], help="Run a preset question")
-    args = parser.parse_args()
-
-    if args.preset:
-        question = PRESET_QUESTIONS[args.preset]
-        print(f"Preset question {args.preset}: {question}")
-        await run_question(question)
-    else:
-        print("Enter your question (type 'exit' to quit):")
     while True:
-            q = input("> ")
+        user_input = input("\nYour question: ")
-            if q.lower() in {"exit", "quit"}:
+        if user_input.lower() in {"exit", "quit"}:
             break
-            if q.strip():
+        await handle_question(user_input)
-                await run_question(q)
+
+async def handle_question(question: str):
+    result = await agent.ainvoke(
+        {"messages": [HumanMessage(content=question)]},
+        {"configurable": {"thread_id": "session-1"}},
+    )
+    answer = result["messages"][-1].content
+    print("\nAnswer:\n", answer)
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(run_cli())