File size: 3,444 Bytes
b125eed ffd98eb 90f16ce ffd98eb b125eed 0a16a11 b125eed 0a16a11 b125eed ffd98eb b125eed ffd98eb b125eed |
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 |
import os
# import json
import numpy as np
import pandas as pd
import openai
from haystack.schema import Document
import streamlit as st
from tenacity import retry, stop_after_attempt, wait_random_exponential
# Get openai API key
openai.api_key = os.environ["OPENAI_API_KEY"]
model_select = "gpt-3.5-turbo-1106"
# define a special function for putting the prompt together (as we can't use haystack)
def get_prompt(context, label):
base_prompt="Summarize the following context efficiently in bullet points, the less the better- but keep concrete goals. \
Summarize only activities that address the vulnerability of "+label+" to climate change. \
Formatting example: \
- Bullet point 1 \
- Bullet point 2 \
"
# Add the meta data for references
# context = ' - '.join([d.content for d in docs])
prompt = base_prompt+"; Context: "+context+"; Answer:"
return prompt
# base_prompt="Summarize the following context efficiently in bullet points, the less the better- but keep concrete goals. \
# Summarize only activities that address the vulnerability of "+label+" to climate change. \
# Formatting example: \
# - Collect and utilize gender-disaggregated data to inform and improve climate change adaptation efforts. \
# - Prioritize gender sensitivity in adaptation options, ensuring participation and benefits for women, who are more vulnerable to climate impacts. \
# "
# # convert df rows to Document object so we can feed it into the summarizer easily
# def get_document(df):
# # we take a list of each extract
# ls_dict = []
# for index, row in df.iterrows():
# # Create a Document object for each row (we only need the text)
# doc = Document(
# row['text'],
# meta={
# 'label': row['Vulnerability Label']}
# )
# # Append the Document object to the documents list
# ls_dict.append(doc)
# return ls_dict
# exception handling for issuing multiple API calls to openai (exponential backoff)
@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
def completion_with_backoff(**kwargs):
return openai.ChatCompletion.create(**kwargs)
# construct RAG query, send to openai and process response
def run_query(context, label):
'''
For non-streamed completion, enable the following 2 lines and comment out the code below
'''
# res = openai.ChatCompletion.create(model=model_select, messages=[{"role": "user", "content": get_prompt(docs)}])
# result = res.choices[0].message.content
# instantiate ChatCompletion as a generator object (stream is set to True)
response = completion_with_backoff(model=model_select, messages=[{"role": "user", "content": get_prompt(context, label)}], stream=True)
# iterate through the streamed output
report = []
res_box = st.empty()
for chunk in response:
# extract the object containing the text (totally different structure when streaming)
chunk_message = chunk['choices'][0]['delta']
# test to make sure there is text in the object (some don't have)
if 'content' in chunk_message:
report.append(chunk_message.content) # extract the message
# add the latest text and merge it with all previous
result = "".join(report).strip()
# res_box.success(result) # output to response text box
res_box.success(result)
|