File size: 1,680 Bytes
31c9ea0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
from sentence_transformers import SentenceTransformer
import pinecone
from openai import OpenAI
import os
from dotenv import find_dotenv, load_dotenv
load_dotenv(find_dotenv())
client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
import streamlit as st
model = SentenceTransformer('all-MiniLM-L6-v2')
pinecone.init(api_key=os.environ["PINECONE_API_KEY"], environment='gcp-starter')
index = pinecone.Index('langchain-chatbot')
# Find the most relevant documents that match the user's query
def find_match(input):
input_em = model.encode(input).tolist()
result = index.query(input_em, top_k=2, includeMetadata=True)
return result['matches'][0]['metadata']['text']+"\n"+result['matches'][1]['metadata']['text']
# Take the user's query and refine it to ensure it's optimal for providing a relevant answer
def query_refiner(conversation, query):
response = client.completions.create(model="text-davinci-003",
prompt=f"Given the following user query and conversation log, formulate a question that would be the most relevant to provide the user with an answer from a knowledge base.\n\nCONVERSATION LOG: \n{conversation}\n\nQuery: {query}\n\nRefined Query:",
temperature=0.7,
max_tokens=256,
top_p=1,
frequency_penalty=0,
presence_penalty=0)
return response.choices[0].text
# Keep track of the ongoing conversation
def get_conversation_string():
conversation_string = ""
for i in range(len(st.session_state['responses'])-1):
conversation_string += "Human: "+st.session_state['requests'][i] + "\n"
conversation_string += "Bot: "+ st.session_state['responses'][i+1] + "\n"
return conversation_string |