Files
povtornyy-ekzamen-faq-bot-c…/src/main.py
T

153 lines
4.4 KiB
Python

"""
Main entry point for the FAQ bot using ChromaDB and a single MCP-tool.
"""
import os
import json
import sys
from typing import List, Dict, Any
import openai
from dotenv import load_dotenv
from chromadb_client import ChromadbClient
from mcp_tool import MCPTool
load_dotenv()
# Ensure OpenAI API key is set
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
if not OPENAI_API_KEY:
print("Error: OPENAI_API_KEY not set in environment.", file=sys.stderr)
sys.exit(1)
openai.api_key = OPENAI_API_KEY
# Initialize the ChromaDB client
db_client = ChromadbClient()
# Load FAQ documents from a local file (JSON lines format)
FAQ_FILE = os.getenv("FAQ_FILE", "data/faq.jsonl")
def load_faq_documents(file_path: str) -> List[Dict[str, Any]]:
"""
Load FAQ documents from a JSON lines file.
Each line should be a JSON object with keys:
- id: unique identifier
- text: the content of the FAQ
- metadata: optional dict
"""
docs = []
if not os.path.exists(file_path):
print(f"FAQ file {file_path} not found. Skipping load.", file=sys.stderr)
return docs
with open(file_path, "r", encoding="utf-8") as f:
for line in f:
try:
doc = json.loads(line.strip())
docs.append(doc)
except json.JSONDecodeError:
continue
return docs
# Load and add documents to the collection if not already present
if not db_client.collection.count():
print("Loading FAQ documents into ChromaDB...")
faq_docs = load_faq_documents(FAQ_FILE)
if faq_docs:
db_client.add_documents(faq_docs)
print(f"Added {len(faq_docs)} documents.")
else:
print("No FAQ documents loaded.", file=sys.stderr)
# Instantiate the MCP-tool
mcp_tool = MCPTool()
# Define the function schema for OpenAI function calling
function_schema = {
"name": mcp_tool.name,
"description": mcp_tool.description,
"parameters": {
"type": "object",
"properties": {},
"required": [],
},
}
def ask_question(question: str) -> str:
"""
Ask a question to the bot. The bot will:
1. Retrieve relevant FAQ documents from ChromaDB.
2. Use OpenAI LLM to generate an answer, possibly invoking the MCP-tool.
"""
# Retrieve top 3 relevant documents
hits = db_client.query(question, top_k=3)
# Build context from hits
context = "\n\n".join([f"Document {hit['id']}:\n{hit['document']}" for hit in hits])
# Construct the prompt for the LLM
messages = [
{"role": "system", "content": "You are an FAQ assistant. Use the provided documents to answer questions."},
{"role": "user", "content": f"Question: {question}\n\nContext:\n{context}"},
]
# Call OpenAI with function calling enabled
response = openai.ChatCompletion.create(
model="gpt-4o-mini",
messages=messages,
functions=[function_schema],
function_call="auto",
)
# Parse the response
reply = response["choices"][0]["message"]
if reply.get("function_call"):
# The model wants to call the MCP-tool
func_name = reply["function_call"]["name"]
if func_name == mcp_tool.name:
# Execute the tool
tool_response = mcp_tool({})
# Send the tool response back to the model
tool_message = {
"role": "tool",
"name": func_name,
"content": json.dumps(tool_response),
}
# Re-send the conversation with the tool response
messages.append(reply)
messages.append(tool_message)
# Get the final answer
final_response = openai.ChatCompletion.create(
model="gpt-4o-mini",
messages=messages,
)
return final_response["choices"][0]["message"]["content"]
else:
return f"Unknown function call: {func_name}"
else:
return reply["content"]
def main():
print("FAQ Bot (ChromaDB + MCP-tool). Type 'exit' to quit.")
while True:
try:
user_input = input("\nYou: ").strip()
except (EOFError, KeyboardInterrupt):
print("\nGoodbye!")
break
if user_input.lower() in {"exit", "quit"}:
print("Goodbye!")
break
if not user_input:
continue
answer = ask_question(user_input)
print(f"\nBot: {answer}")
if __name__ == "__main__":
main()