ThinkOV2 / chatbot.py
Ayush-003's picture
Upload 28 files
9be2851 verified
Raw History Blame Contribute Delete
3.11 kB
"""
Backward-compatible Chatbot class for simple Q&A
For advanced features, use agent.py instead
"""
import asyncio
from typing import Optional
from agent import agent
from memory import session_manager
from rag_chain import RAGChain
from schemas import ChatContext, ChatRequest
import uuid
class Chatbot:
"""Simple chatbot wrapper for backward compatibility"""
def __init__(self, qa_chain=None, vectorstore=None):
self.qa_chain = qa_chain
self.vectorstore = vectorstore
self.rag_chain = RAGChain(vectorstore) if vectorstore else None
def get_response(self, user_input: str, session_id: Optional[str] = None) -> str:
"""
Get response for user input (synchronous wrapper)
For simple use cases. For advanced features, use agent.process_message()
"""
try:
# Use the old qa_chain if available
if self.qa_chain:
response = self.qa_chain({"query": user_input})
return response['result']
# Otherwise use the new agent system
return asyncio.run(self._async_get_response(user_input, session_id))
except Exception as e:
return f"An error occurred: {str(e)}"
async def _async_get_response(self, user_input: str, session_id: Optional[str] = None) -> str:
"""Async response using new agent system"""
session_id = session_id or str(uuid.uuid4())
# Get conversation history
convo_history = await session_manager.get_conversation_history(session_id)
# Get retrieved documents
retrieved_docs = []
if self.rag_chain:
retrieved_docs = await self.rag_chain.retrieve_documents(user_input)
# Build context
context = ChatContext(
user_message=user_input,
convo_history=convo_history,
session_id=session_id,
retrieved_docs=retrieved_docs,
available_tools=[],
locale="en-IN",
timezone="Asia/Kolkata"
)
# Process with agent
response = await agent.process_message(context)
return response.reply_text
if __name__ == "__main__":
from rag_chain import RAGChain
from documentProcessor import DocumentProcessor
from embedding_indexer import EmbeddingIndexer
processor = DocumentProcessor("ecommerce_faq.txt")
texts = processor.load_and_split()
indexer = EmbeddingIndexer()
vectorstore = indexer.create_vectorstore(texts)
rag_chain = RAGChain(vectorstore)
qa_chain = rag_chain.create_chain()
chatbot = Chatbot(qa_chain)
print("Chatbot initialized! Type 'exit' to quit.\n")
while True:
user_input = input("You: ")
if user_input.lower() in ['exit', 'quit', 'bye']:
print("Chatbot: Goodbye!")
break
response = chatbot.get_response(user_input)
print(f"Chatbot: {response}\n")