121 lines
4.2 KiB
Python
121 lines
4.2 KiB
Python
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 OpenRouter API key from .env or environment variable
|
|
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
|
|
if not OPENAI_API_KEY:
|
|
raise RuntimeError("OPENAI_API_KEY not set in environment")
|
|
|
|
# ----------------- LLM and Embeddings -----------------
|
|
llm = ChatOpenAI(
|
|
model="openai/gpt-oss-20b:free",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
api_key=OPENAI_API_KEY,
|
|
temperature=0.0,
|
|
)
|
|
|
|
embeddings = OpenAIEmbeddings(
|
|
model="text-embedding-3-small",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
api_key=OPENAI_API_KEY,
|
|
)
|
|
|
|
# ----------------- ChromaDB setup -----------------
|
|
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 if not already loaded
|
|
if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
|
|
data_dir = Path("data")
|
|
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.
|
|
"""
|
|
# Simple static mapping for demo purposes
|
|
meta = {
|
|
"schedule": "Monday 10:00-12:00, Wednesday 14:00-16:00",
|
|
"instructor": "Dr. Ivanov",
|
|
"location": "Room 101",
|
|
}
|
|
key = query.lower().strip()
|
|
return meta.get(key, f"No metadata found for '{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.\n"
|
|
"When a user asks about course materials, use the search_course_docs tool.\n"
|
|
"When a user asks about schedule, instructor, or location, use the fetch_course_meta tool.\n"
|
|
"Do not use both tools unless absolutely necessary.\n"
|
|
"In your final answer, prefix the response with 'source: chroma' or 'source: mcp_meta' to indicate where the information came from."
|
|
),
|
|
)
|
|
|
|
# ----------------- CLI -----------------
|
|
PRESET_QUESTIONS = [
|
|
"What topics are covered in the first lecture?",
|
|
"When is the next class?",
|
|
"Who is the instructor?",
|
|
]
|
|
|
|
async def run_cli():
|
|
print("Welcome to the Course FAQ Bot!\n")
|
|
for i, q in enumerate(PRESET_QUESTIONS, 1):
|
|
print(f"{i}. {q}")
|
|
print("\nEnter your own question or type 'exit' to quit.")
|
|
while True:
|
|
user_input = input("\n> ")
|
|
if user_input.lower() in {"exit", "quit"}:
|
|
print("Goodbye!")
|
|
break
|
|
result = await agent.ainvoke(
|
|
{"messages": ["HumanMessage(content=\"{}\")".format(user_input)]},
|
|
{"configurable": {"thread_id": "session-1"}},
|
|
)
|
|
# The agent returns a dict with 'messages'; take the last one
|
|
content = result["messages"][-1].content
|
|
print(content)
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(run_cli())
|