147 lines
5.1 KiB
Python
147 lines
5.1 KiB
Python
import os
|
|
import asyncio
|
|
import argparse
|
|
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
|
|
|
|
# -------------------- 1. 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"),
|
|
temperature=0.0,
|
|
)
|
|
|
|
embeddings = OpenAIEmbeddings(
|
|
model="text-embedding-3-small",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
api_key=os.getenv("OPENAI_API_KEY"),
|
|
)
|
|
|
|
# -------------------- 2. Chroma DB --------------------
|
|
CHROMA_PATH = Path("./chroma_faq")
|
|
CHROMA_COLLECTION = "course_faq"
|
|
|
|
vector_store = Chroma(
|
|
collection_name=CHROMA_COLLECTION,
|
|
embedding_function=embeddings,
|
|
persist_directory=str(CHROMA_PATH),
|
|
)
|
|
|
|
# Persist changes
|
|
vector_store.persist()
|
|
|
|
# -------------------- 3. Tools --------------------
|
|
@tool
|
|
def search_knowledge(query: str) -> str:
|
|
"""Search the knowledge base for relevant information."""
|
|
docs = vector_store.similarity_search(query, k=3)
|
|
return "\n".join(d.page_content for d in docs) if docs else "No results found in course materials."
|
|
|
|
@tool
|
|
def fetch_course_meta(query: str) -> str:
|
|
"""Fetch course metadata (schedule, syllabus, etc.) from a static JSON file."""
|
|
meta_path = Path("meta.json")
|
|
if not meta_path.exists():
|
|
return "Metadata file not found."
|
|
import json
|
|
data = json.loads(meta_path.read_text())
|
|
query_lower = query.lower()
|
|
if "schedule" in query_lower:
|
|
return f"Course schedule: {data.get('schedule', 'Not available')}"
|
|
if "syllabus" in query_lower:
|
|
return f"Syllabus URL: {data.get('syllabus_url', 'Not available')}"
|
|
if "instructor" in query_lower:
|
|
return f"Instructor: {data.get('instructor', 'Not available')}"
|
|
# Default: return all
|
|
return json.dumps(data, indent=2)
|
|
|
|
# -------------------- 4. Backend --------------------
|
|
backend = CompositeBackend([
|
|
LocalShellBackend(workspace_dir="./workspace"),
|
|
FilesystemBackend(),
|
|
])
|
|
|
|
# -------------------- 5. Agent --------------------
|
|
SYSTEM_PROMPT = (
|
|
"You are a helpful FAQ bot for the course.\n"
|
|
"Use the 'search_knowledge' tool to answer questions about course materials.\n"
|
|
"Use the 'fetch_course_meta' tool for questions about schedule, syllabus, instructor, etc.\n"
|
|
"Do not call both tools unnecessarily.\n"
|
|
"In your final answer, prepend 'source: chroma' or 'source: mcp_meta' to indicate which tool provided the information."
|
|
)
|
|
|
|
agent = create_deep_agent(
|
|
model=llm,
|
|
tools=[search_knowledge, fetch_course_meta],
|
|
backend=backend,
|
|
system_prompt=SYSTEM_PROMPT,
|
|
)
|
|
|
|
# -------------------- 6. Data Loader --------------------
|
|
|
|
def load_faq_to_chroma():
|
|
data_dir = Path("data")
|
|
if not data_dir.exists():
|
|
data_dir.mkdir()
|
|
# Create sample markdown files if missing
|
|
(data_dir / "file1.md").write_text(
|
|
"## Course Overview\nThis course covers advanced topics in AI. Topics include machine learning, deep learning, and natural language processing."
|
|
)
|
|
(data_dir / "file2.md").write_text(
|
|
"## FAQ\nQ: What is the schedule?\nA: Sessions are held on Mondays and Wednesdays.\nQ: Where can I find the syllabus?\nA: Syllabus is available on the course website."
|
|
)
|
|
docs = []
|
|
for md_file in data_dir.glob("*.md"):
|
|
text = md_file.read_text()
|
|
docs.append(Document(page_content=text, metadata={"source": md_file.name}))
|
|
vector_store.add_documents(docs)
|
|
vector_store.persist()
|
|
print(f"Loaded {len(docs)} documents into Chroma collection '{CHROMA_COLLECTION}'.")
|
|
|
|
# -------------------- 7. CLI --------------------
|
|
PRESET_QUESTIONS = {
|
|
"1": "What topics are covered in the course?",
|
|
"2": "Where can I find the syllabus?",
|
|
"3": "What is the course schedule?",
|
|
}
|
|
|
|
async def run_question(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 message
|
|
content = result["messages"][-1].content
|
|
print(content)
|
|
|
|
async def main():
|
|
# Ensure data is loaded
|
|
load_faq_to_chroma()
|
|
|
|
parser = argparse.ArgumentParser(description="FAQ Bot CLI")
|
|
parser.add_argument("--preset", choices=["1", "2", "3"], help="Run a preset question")
|
|
args = parser.parse_args()
|
|
|
|
if args.preset:
|
|
question = PRESET_QUESTIONS[args.preset]
|
|
print(f"Preset question {args.preset}: {question}")
|
|
await run_question(question)
|
|
else:
|
|
print("Enter your question (type 'exit' to quit):")
|
|
while True:
|
|
q = input("> ")
|
|
if q.lower() in {"exit", "quit"}:
|
|
break
|
|
if q.strip():
|
|
await run_question(q)
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|