add: main.py

main.py

@@ -0,0 +1,120 @@
+import os
+import asyncio
+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 deepagents import create_deep_agent
+from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
+
+# ----------------- Configuration -----------------
+# Load API key from .env or environment variable
+os.environ.setdefault("OPENAI_API_KEY", os.getenv("OPENAI_API_KEY", ""))
+
+# LLM via OpenRouter
+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,
+)
+
+# Embeddings for Chroma
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",
+    base_url="https://openrouter.ai/api/v1",
+    api_key=os.getenv("OPENAI_API_KEY"),
+)
+
+# ----------------- Chroma DB -----------------
+CHROMA_PATH = Path("./chroma_faq")
+CHROMA_COLLECTION = "faq_collection"
+vector_store = Chroma(
+    collection_name=CHROMA_COLLECTION,
+    embedding_function=embeddings,
+    persist_directory=str(CHROMA_PATH),
+)
+
+# Load markdown files into Chroma (idempotent)
+DATA_DIR = Path("./data")
+if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
+    docs = []
+    for md_file in 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) -> str:
+    """Search the local FAQ collection for relevant passages."""
+    results = vector_store.similarity_search(query, k=3)
+    if not results:
+        return "No relevant information found in the course materials."
+    return "\n---\n".join(f"{doc.metadata.get('source', 'unknown')}\n{doc.page_content}" for doc in results)
+
+@tool
+def fetch_course_meta(query: str) -> str:
+    """Mock MCP-style tool that returns course metadata.
+    In production this would be an HTTP call to an MCP server.
+    Here we return a static JSON-like string based on the query.
+    """
+    meta = {
+        "schedule": "Mon 10-12, Wed 14-16, Fri 9-11",
+        "instructor": "Dr. Ivanov",
+        "credits": 3,
+    }
+    # Simple keyword matching
+    if "schedule" in query.lower():
+        return f"Course schedule: {meta['schedule']}"
+    if "instructor" in query.lower():
+        return f"Instructor: {meta['instructor']}"
+    if "credits" in query.lower():
+        return f"Credits: {meta['credits']}"
+    return "No metadata matches your query."
+
+# ----------------- Backend -----------------
+backend = CompositeBackend([
+    LocalShellBackend(workspace_dir="./workspace"),
+    FilesystemBackend(),
+])
+
+# ----------------- 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, instructor, or credits. Do not use both tools unless necessary. In your final answer, prefix the source with 'source: chroma' or 'source: mcp_meta'.",
+)
+
+# ----------------- CLI -----------------
+PRESET_QUESTIONS = [
+    "What topics are covered in lecture 3?",
+    "When is the next class?",
+    "Who is the instructor for this course?",
+]
+
+async def run_agent(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 content
+    content = result["messages"][-1].content
+    print(f"\nQ: {question}\nA: {content}\n")
+
+async def main():
+    print("--- FAQ Bot Demo ---")
+    for i, q in enumerate(PRESET_QUESTIONS, 1):
+        await run_agent(q, thread_id=f"demo-{i}")
+    print("Enter your own question (or 'exit' to quit):")
+    while True:
+        q = input("> ")
+        if q.lower() in {"exit", "quit"}:
+            break
+        await run_agent(q, thread_id="interactive")
+
+if __name__ == "__main__":
+    asyncio.run(main())