add main.py

main.py

@@ -0,0 +1,114 @@
+import asyncio, os
+from pathlib import Path
+from langchain_openai import ChatOpenAI
+from langchain_core.messages import HumanMessage
+from langchain.tools import tool
+from deepagents import create_deep_agent
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+from langchain_chroma import Chroma
+from langchain_ollama import OllamaEmbeddings
+import httpx
+import json
+
+# ---------- LLM ----------
+llm = ChatOpenAI(
+    model="openai/gpt-oss-20b:free",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+    temperature=0.0,
+)
+
+# ---------- Backend ----------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
+
+# ---------- Chroma DB ----------
+CHROMA_PATH = Path("./chroma_faq")
+CHROMA_PATH.mkdir(exist_ok=True)
+
+embeddings = OllamaEmbeddings(model="nomic-embed-text")
+
+# Load or create vector store
+if CHROMA_PATH.exists() and any(CHROMA_PATH.iterdir()):
+    chroma = Chroma(persist_directory=str(CHROMA_PATH), embedding_function=embeddings)
+else:
+    # Load markdown files
+    docs = []
+    for md_file in Path("data").glob("*.md"):
+        text = md_file.read_text(encoding="utf-8")
+        docs.append(text)
+    chroma = Chroma.from_texts(docs, embedding=embeddings, persist_directory=str(CHROMA_PATH))
+    chroma.persist()
+
+@tool
+def search_course_docs(query: str, k: int = 3) -> str:
+    """Search local course documents in Chroma."""
+    results = chroma.similarity_search(query, k=k)
+    return "\n---\n".join(doc.page_content for doc in results) if results else "No relevant docs found."
+
+# ---------- MCP‑style tool ----------
+# For demo we use a static JSON file. In production this would be an HTTP call.
+META_JSON = Path("meta.json")
+if not META_JSON.exists():
+    # Create a simple mock meta file
+    META_JSON.write_text(json.dumps({
+        "schedule": "Mon 10-12, Wed 14-16, Fri 9-11",
+        "instructor": "Dr. Smith",
+        "location": "Room 101"
+    }))
+
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Return course metadata matching the query keyword."""
+    data = json.loads(META_JSON.read_text())
+    # Simple keyword search in values
+    for key, value in data.items():
+        if query.lower() in key.lower() or query.lower() in str(value).lower():
+            return f"{key}: {value}"
+    return "No metadata found for the query."
+
+# ---------- 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"
+        "If the question is about course content, use search_course_docs.\n"
+        "If the question is about schedule, instructor, or location, use fetch_course_meta.\n"
+        "Do not call both tools unless necessary.\n"
+        "In your answer, prefix the source with 'source: chroma' or 'source: mcp_meta'."
+    ),
+)
+
+# ---------- CLI ----------
+PRESET_QUESTIONS = [
+    "What is the main topic of the first lecture?",
+    "How can I access the lecture slides?",
+    "When is the next class?"
+]
+
+async def run_cli():
+    print("--- FAQ Bot CLI ---")
+    for i, q in enumerate(PRESET_QUESTIONS, 1):
+        print(f"\nPreset {i}: {q}")
+        result = await agent.ainvoke(
+            {"messages": [HumanMessage(content=q)]},
+            {"configurable": {"thread_id": f"preset-{i}"}},
+        )
+        print(result["messages"][-1].content)
+    print("\nEnter your own question (or 'exit'): ")
+    while True:
+        user_q = input("> ")
+        if user_q.lower() in {"exit", "quit"}:
+            break
+        result = await agent.ainvoke(
+            {"messages": [HumanMessage(content=user_q)]},
+            {"configurable": {"thread_id": "interactive"}},
+        )
+        print(result["messages"][-1].content)
+
+if __name__ == "__main__":
+    asyncio.run(run_cli())