Spaces:
Sleeping
Sleeping
File size: 4,178 Bytes
40d903c |
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
import os
import streamlit as st
import openai
from elasticsearch import Elasticsearch
import os
os.environ['openai_api'] = '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'
os.environ['cloud_id'] = 'lab-10:YXVzdHJhbGlhLXNvdXRoZWFzdDEuZ2NwLmVsYXN0aWMtY2xvdWQuY29tOjQ0MyQ2NjkxZjk3NjU1MzY0OTYxODgyYzNjOWY1MGVlNTBhNSQ4MjQyZTI3NTcxYzc0YjMxYjIyOWU4OThkNGYxM2JjZg=='
os.environ['cloud_user'] = 'elastic1'
os.environ['cloud_pass'] = 'elastic1'
# This code is part of an Elastic Blog showing how to combine
# Elasticsearch's search relevancy power with
# OpenAI's GPT's Question Answering power
# https://www.elastic.co/blog/chatgpt-elasticsearch-openai-meets-private-data
# Code is presented for demo purposes but should not be used in production
# You may encounter exceptions which are not handled in the code
# Required Environment Variables
# openai_api - OpenAI API Key
# cloud_id - Elastic Cloud Deployment ID
# cloud_user - Elasticsearch Cluster User
# cloud_pass - Elasticsearch User Password
openai.api_key = os.environ['openai_api']
model = "gpt-3.5-turbo-0301"
# Connect to Elastic Cloud cluster
def es_connect(cid, user, passwd):
es = Elasticsearch(cloud_id=cid, http_auth=(user, passwd))
return es
# Search ElasticSearch index and return body and URL of the result
def search(query_text):
cid = os.environ['cloud_id']
cp = os.environ['cloud_pass']
cu = os.environ['cloud_user']
es = es_connect(cid, cu, cp)
# Elasticsearch query (BM25) and kNN configuration for hybrid search
query = {
"bool": {
"must": [{
"match": {
"title": {
"query": query_text,
"boost": 1
}
}
}],
"filter": [{
"exists": {
"field": "title-vector"
}
}]
}
}
knn = {
"field": "title-vector",
"k": 1,
"num_candidates": 20,
"query_vector_builder": {
"text_embedding": {
"model_id": "sentence-transformers__all-distilroberta-v1",
"model_text": query_text
}
},
"boost": 24
}
fields = ["title", "body_content", "url"]
index = 'search-elastic-docs'
resp = es.search(index=index,
query=query,
knn=knn,
fields=fields,
size=1,
source=False)
body = resp['hits']['hits'][0]['fields']['body_content'][0]
url = resp['hits']['hits'][0]['fields']['url'][0]
return body, url
def truncate_text(text, max_tokens):
tokens = text.split()
if len(tokens) <= max_tokens:
return text
return ' '.join(tokens[:max_tokens])
# Generate a response from ChatGPT based on the given prompt
def chat_gpt(prompt, model="gpt-3.5-turbo", max_tokens=1024, max_context_tokens=4000, safety_margin=5):
# Truncate the prompt content to fit within the model's context length
truncated_prompt = truncate_text(prompt, max_context_tokens - max_tokens - safety_margin)
response = openai.ChatCompletion.create(model=model,
messages=[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": truncated_prompt}])
return response["choices"][0]["message"]["content"]
st.title("ElasticDocs GPT")
# Main chat form
with st.form("chat_form"):
query = st.text_input("You: ")
submit_button = st.form_submit_button("Send")
# Generate and display response on form submission
negResponse = "I'm unable to answer the question based on the information I have from Elastic Docs."
if submit_button:
resp, url = search(query)
prompt = f"Answer this question: {query}\nUsing only the information from this Elastic Doc: {resp}\nIf the answer is not contained in the supplied doc reply '{negResponse}' and nothing else"
answer = chat_gpt(prompt)
if negResponse in answer:
st.write(f"ChatGPT: {answer.strip()}")
else:
st.write(f"ChatGPT: {answer.strip()}\n\nDocs: {url}")
|