Update langchain_qa_warba.py

langchain_qa_warba.py

@@ -1,15 +1,8 @@
-# -*- coding: utf-8 -*-
-"""LangChain QA WARBA
 
-Automatically generated by Colaboratory.
 
-Original file is located at
-    https://colab.research.google.com/drive/1FlN_580MckH1k15F73gvsxLSg-O5WUIO
-"""
+#!pip install openai langchain faiss-cpu
 
-!pip install openai langchain faiss-cpu
-
-!pip install tiktoken
+#!pip install tiktoken
 
 #@title State of Union Text
 state_of_the_union = """ I am an AI Bota and my name is Shegardi and I am an employee of Warba Bank, located in Kuwait and I have been created to answer certain questions about warba bank.
@@ -603,87 +596,11 @@ Warba Bank is a modern banking solution that provides a wide range of financial
 
 
 
-  """
-
-#@title Environment Vars
-openai_api_key = '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'
-
-import os
-os.environ["OPENAI_API_KEY"] = openai_api_key
-
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores.faiss import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain import OpenAI, VectorDBQA
-
-
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-texts = text_splitter.split_text(state_of_the_union)
-
-embeddings = OpenAIEmbeddings()
-vectorstore = FAISS.from_texts(texts, embeddings)
-
-qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=vectorstore)
-
-query = "What is warba bank?"
-qa.run(query)
-
-llm = OpenAI()
-llm(query)
-
-from langchain.chains import load_chain
-
-chain = load_chain("lc://chains/vector-db-qa/stuff/chain.json", vectorstore=vectorstore)
-
-query = "I am w segment and my spends are 3000 international and 1000 local, calculate my cashback"
-chain.run(query)
-
-query = "I am w segment and my spends are 3000 international and 1000 local, calculate my cashback"
-chain.run(query)
-
-!pip install streamlit
-
-import streamlit as st
-
-# State of Union Text
-#state_of_the_union = """ data"""
-
-# Environment Vars
-openai_api_key = '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'
-import os
-os.environ["OPENAI_API_KEY"] = openai_api_key
-
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores.faiss import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain import OpenAI, VectorDBQA
-
-
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-texts = text_splitter.split_text(state_of_the_union)
-
-embeddings = OpenAIEmbeddings()
-vectorstore = FAISS.from_texts(texts, embeddings)
-qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=vectorstore)
-
-from langchain.chains import load_chain
-
-chain = load_chain("lc://chains/vector-db-qa/stuff/chain.json", vectorstore=vectorstore)
-
-def run_chain(query):
-    return chain.run(query)
-
-st.title("Vector-based DBQA with OpenAI and Langchain")
-query = st.text_input("Enter your query:")
-if st.button("Ask"):
-    answer = run_chain(query)
-    st.write("Answer:", answer)
-
 !pip install gradio
 
 import gradio as gr
 
-# State of Union Text
+#State of Union Text
 #state_of_the_union = """ data"""
 
 # Environment Vars
@@ -720,7 +637,7 @@ def run_app(input):
 
 gr.Interface(fn=run_app, inputs=inputs, outputs=outputs, title="The following is a conversation with a human called Shegardi. Shegardi is helpful, precise, truthful, and very friendly. Also, Shegardi is an employee of Warba Bank, located in Kuwait. Shegardi will only use the information provided to him.").launch(share=True)
 
-query
+