diff --git a/main.py b/main.py index 2c08a31..f531129 100644 --- a/main.py +++ b/main.py @@ -9,144 +9,116 @@ from deepagents import create_deep_agent from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend from langchain_core.messages import HumanMessage -# --------------------------- -# Configuration -# --------------------------- -OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") -if not OPENAI_API_KEY: - raise RuntimeError("OPENAI_API_KEY not set in environment") +# --------------------- Configuration --------------------- +BASE_DIR = Path(__file__).parent +DATA_DIR = BASE_DIR / "data" +CHROMA_DIR = BASE_DIR / "chroma_faq" +MOCK_META_FILE = BASE_DIR / "course_meta.json" -# LLM via OpenRouter +# --------------------- LLM and Embeddings --------------------- 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 via OpenRouter 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"), ) -# Chroma vector store (persisted) -CHROMA_PATH = Path("./chroma_faq") +# --------------------- Chroma Vector Store --------------------- vector_store = Chroma( collection_name="faq_collection", embedding_function=embeddings, - persist_directory=str(CHROMA_PATH), + persist_directory=str(CHROMA_DIR), ) -# --------------------------- -# Data loading -# --------------------------- - -def load_faq_to_chroma(md_folder: str = "data"): - """Load all .md files from md_folder into ChromaDB. - Each file is split into chunks and added to the vector store. - """ - md_path = Path(md_folder) - if not md_path.exists(): - raise FileNotFoundError(f"Markdown folder {md_folder} not found") - docs = [] - for md_file in md_path.glob("*.md"): - text = md_file.read_text(encoding="utf-8") - # Simple chunking: split by double newlines - chunks = [c.strip() for c in text.split("\n\n") if c.strip()] - for i, chunk in enumerate(chunks): - docs.append(Document(page_content=chunk, metadata={"source": md_file.name, "chunk": i})) - if docs: - vector_store.add_documents(docs) - vector_store.persist() - else: - print("No markdown files found to load.") - -# --------------------------- -# Tools -# --------------------------- +# --------------------- 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 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('title', 'Document')}**\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. + In production this would be an HTTP call to an MCP server. + Here we read a local JSON file 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}" + import json + if not MOCK_META_FILE.exists(): + return "Metadata source not available." + with open(MOCK_META_FILE, "r", encoding="utf-8") as f: + data = json.load(f) + # Simple keyword search in the metadata + results = [f"{k}: {v}" for k, v in data.items() if query.lower() in k.lower() or query.lower() in str(v).lower()] + return "\n".join(results) if results else "No metadata matches your query." -# --------------------------- -# Backend setup -# --------------------------- +# --------------------- Backend --------------------- backend = CompositeBackend([ LocalShellBackend(workspace_dir="./workspace"), FilesystemBackend(), ]) -# --------------------------- -# Agent creation -# --------------------------- +# --------------------- 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. 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.", + system_prompt=( + "You are a helpful FAQ bot for the course.\n" + "Use the search_course_docs tool for questions about lecture materials.\n" + "Use the fetch_course_meta tool for questions about schedule or metadata.\n" + "Do not call both tools unless absolutely necessary.\n" + "In your final answer, prefix the source with 'source: chroma' or 'source: mcp_meta'." + ), ) -# --------------------------- -# CLI -# --------------------------- +# --------------------- Data Loading --------------------- +async def load_faq_to_chroma(): + """Load all .md files from data/ into the Chroma collection.""" + if not DATA_DIR.exists(): + print("Data directory not found.") + return + docs = [] + for md_file in DATA_DIR.glob("*.md"): + text = md_file.read_text(encoding="utf-8") + docs.append(Document(page_content=text, metadata={"title": md_file.stem})) + if docs: + vector_store.add_documents(docs) + vector_store.persist() + print(f"Loaded {len(docs)} documents into Chroma.") + else: + print("No markdown files found in data/.") + +# --------------------- CLI --------------------- PRESET_QUESTIONS = [ - "What topics are covered in Lecture 1?", # should hit chroma + "What is the deadline for the final project?", # chroma "Explain the concept of tokenization in NLP.", # chroma - "When is the next lab session?", # should hit mcp_meta + "When is the next lecture scheduled?", # 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 +async def run_cli(): + await load_faq_to_chroma() + print("\n--- FAQ Bot CLI ---\n") 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):") + print(f"{i}. {q}") + print("\nEnter your own question (or 'exit' to quit):") while True: user_input = input("> ") if user_input.lower() in {"exit", "quit"}: break - await run_agent(user_input, thread_id="interactive") + result = await agent.ainvoke( + {"messages": [HumanMessage(content=user_input)]}, + {"configurable": {"thread_id": "session-1"}}, + ) + print(result["messages"][-1].content) if __name__ == "__main__": - asyncio.run(main()) + asyncio.run(run_cli())