fix: main.py
This commit is contained in:
@@ -1,7 +1,5 @@
|
||||
import os
|
||||
import asyncio
|
||||
import json
|
||||
import httpx
|
||||
from pathlib import Path
|
||||
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
|
||||
from langchain_chroma import Chroma
|
||||
@@ -10,46 +8,49 @@ from langchain.tools import tool
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
|
||||
# --------------------- Configuration ---------------------
|
||||
BASE_DIR = Path(__file__).parent
|
||||
DATA_DIR = BASE_DIR / "data"
|
||||
CHROMA_DIR = BASE_DIR / "chroma_faq"
|
||||
META_JSON = BASE_DIR / "course_meta.json"
|
||||
# ----------------- 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 & Embeddings ---------------------
|
||||
# ----------------- LLM and Embeddings -----------------
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
api_key=OPENAI_API_KEY,
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
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,
|
||||
)
|
||||
|
||||
# --------------------- Chroma DB ---------------------
|
||||
# ----------------- ChromaDB setup -----------------
|
||||
CHROMA_PATH = Path("./chroma_faq")
|
||||
CHROMA_COLLECTION = "faq_collection"
|
||||
vector_store = Chroma(
|
||||
collection_name="faq_collection",
|
||||
collection_name=CHROMA_COLLECTION,
|
||||
embedding_function=embeddings,
|
||||
persist_directory=str(CHROMA_DIR),
|
||||
persist_directory=str(CHROMA_PATH),
|
||||
)
|
||||
|
||||
# Load markdown files into Chroma if not already loaded
|
||||
if not CHROMA_DIR.exists() or not any(CHROMA_DIR.iterdir()):
|
||||
if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
|
||||
data_dir = Path("data")
|
||||
docs = []
|
||||
for md_file in DATA_DIR.glob("*.md"):
|
||||
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 ---------------------
|
||||
# ----------------- Tools -----------------
|
||||
@tool
|
||||
def search_course_docs(query: str) -> str:
|
||||
"""Search the FAQ knowledge base for relevant information."""
|
||||
"""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."
|
||||
@@ -57,67 +58,63 @@ def search_course_docs(query: str) -> str:
|
||||
|
||||
@tool
|
||||
def fetch_course_meta(query: str) -> str:
|
||||
"""Fetch course metadata (e.g., schedule) from a local JSON mock."""
|
||||
if not META_JSON.exists():
|
||||
return "Metadata file not found."
|
||||
data = json.loads(META_JSON.read_text(encoding="utf-8"))
|
||||
# Simple keyword search in the metadata
|
||||
matches = [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(matches) if matches else "No metadata matches the query."
|
||||
"""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 -----------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
])
|
||||
|
||||
# --------------------- Agent ---------------------
|
||||
# ----------------- Agent -----------------
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[search_course_docs, fetch_course_meta],
|
||||
backend=backend,
|
||||
system_prompt=(
|
||||
"You are a helpful FAQ assistant for the course.\n"
|
||||
"When a user asks about course content, use the search_course_docs tool.\n"
|
||||
"When a user asks about schedule, metadata, or other non‑content info, use fetch_course_meta.\n"
|
||||
"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 source with 'source: chroma' or 'source: mcp_meta'."
|
||||
"In your final answer, prefix the response with 'source: chroma' or 'source: mcp_meta' to indicate where the information came from."
|
||||
),
|
||||
)
|
||||
|
||||
# --------------------- CLI ---------------------
|
||||
SAMPLE_QUESTIONS = [
|
||||
"What topics are covered in the first lecture?", # should hit chroma
|
||||
"Explain the concept of tokenization in NLP.", # chroma
|
||||
"When is the next class scheduled?", # meta
|
||||
# ----------------- CLI -----------------
|
||||
PRESET_QUESTIONS = [
|
||||
"What topics are covered in the first lecture?",
|
||||
"When is the next class?",
|
||||
"Who is the instructor?",
|
||||
]
|
||||
|
||||
async def run_interactive():
|
||||
print("Welcome to the Course FAQ Bot! Type 'exit' to quit.")
|
||||
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("\nYou: ")
|
||||
user_input = input("\n> ")
|
||||
if user_input.lower() in {"exit", "quit"}:
|
||||
print("Goodbye!")
|
||||
break
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [{"role": "user", "content": user_input}]},
|
||||
{"configurable": {"thread_id": "interactive-session"}},
|
||||
{"messages": ["HumanMessage(content=\"{}\")".format(user_input)]},
|
||||
{"configurable": {"thread_id": "session-1"}},
|
||||
)
|
||||
print("\nAssistant:", result["messages"][-1]["content"])
|
||||
|
||||
async def run_samples():
|
||||
for q in SAMPLE_QUESTIONS:
|
||||
print("\nQuestion:", q)
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [{"role": "user", "content": q}]},
|
||||
{"configurable": {"thread_id": "sample-session"}},
|
||||
)
|
||||
print("Answer:", result["messages"][-1]["content"])
|
||||
|
||||
async def main():
|
||||
# Run sample questions first
|
||||
await run_samples()
|
||||
# Then enter interactive mode
|
||||
await run_interactive()
|
||||
# The agent returns a dict with 'messages'; take the last one
|
||||
content = result["messages"][-1].content
|
||||
print(content)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
asyncio.run(run_cli())
|
||||
|
||||
Reference in New Issue
Block a user