app.py

import gradio as gr
import pinecone
import openai
import os
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.vectorstores import Pinecone 


BOOK_TOKEN = os.getenv("book")
pine = os.getenv("pine")
HF_TOKEN = os.getenv("HF_TOKEN")

os.environ["OPENAI_API_KEY"] = BOOK_TOKEN

OPENAI_API_KEY = ""
PINECONE_API_KEY = ""
PINECONE_API_ENV = "gcp-starter"

#embedding = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEYs)
embed_model = "text-embedding-ada-002"

pinecone.init(
    api_key=pine,
    environment=PINECONE_API_ENV
)
openai.api_key=BOOK_TOKEN
index_n = "ibc-12"
index = pinecone.Index(index_n)
index.describe_index_stats()

limit = 3750

llm = ChatOpenAI(temperature=0, model_name="gpt-4" )

embeddings = OpenAIEmbeddings(
    model="text-embedding-ada-002"
)

#get the db index
db = Pinecone.from_existing_index(index_name=index_n, embedding=embeddings)



with gr.Blocks() as demo:
    chatbot = gr.Chatbot(label="Talk to the Bot")
    msg = gr.Textbox()
    clear = gr.Button("Clear")
    chat_history = []
    
    def user(user_message, chat_history):

        memory = ConversationBufferMemory(
            memory_key='chat_history',
            return_messages=False
        )
    
        #Initalize lanchain - Conversation Retrieval Chain
        qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0), retriever=db.as_retriever(), memory=memory)

    

        #get response from QA Chain
        response = qa({'question': user_message, "chat_history": chat_history})
        #append user message and respone to chat history
        chat_history.append((user_message, response["answer"]))
        return gr.update(value=""), chat_history
    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False)
    clear.click(lambda: None, None, chatbot, queue=False)

if __name__ == "__main__":
  demo.launch(debug=True)