Spaces:
Sleeping
Sleeping
File size: 3,948 Bytes
3afac77 f9f7463 3afac77 a46e906 3afac77 1f8c1c6 3afac77 f9f7463 3afac77 f9f7463 3afac77 9b8c51b 3afac77 a46e906 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
import os
import chromadb
import gradio as gr
from dotenv import load_dotenv
from openai import OpenAI
from langchain_community.embeddings import AnyscaleEmbeddings
from langchain_community.vectorstores import Chroma
from typing import List
qna_system_message = """
You are an assistant to an insurance firm who answers customer queries based on their insurance policy documents.
User input will have the context required by you to answer customer questions.
This context will begin with the word: ###Context.
The context contains references to specific portions of a document relevant to the customer query.
Customer questions will begin with the word: ###Question.
Information about the customer will begin with the word: ###Customer Information
Please answer user questions ONLY using the context provided in the input and the customer information.
DO NOT mention anything about the context in your final answer.
Your response should only contain the answer to the question AND NOTHING ELSE.
If the answer is not found in the context, respond "Sorry, I cannot answer your question at this point. Please contact our hotline: 1-800-INSURANCE".
"""
qna_user_message_template = """
###Customer Information
Customer Name: John Doe
Username: johndoe
Policy Number: NBHTGBP22011V012223#
Bank Account Number: 424242424242
Premium Amount: $15000
Number of premium installments: 5
Number of installments paid: 3
Last Premium Paid: Yes
Last Premium Date: 2024-05-12
###Context
Here are some documents that are relevant to the question mentioned below.
{context}
###Question
{question}
"""
load_dotenv()
anyscale_api_key = os.environ['ANYSCALE_API_KEY']
client = OpenAI(
base_url="https://api.endpoints.anyscale.com/v1",
api_key=anyscale_api_key
)
qna_model = 'meta-llama/Meta-Llama-3-8B-Instruct'
embedding_model = AnyscaleEmbeddings(
client=client,
model='thenlper/gte-large'
)
chromadb_client = chromadb.PersistentClient(path='./health_policy_db')
vectorstore_persisted = Chroma(
client=chromadb_client,
collection_name="policy-text",
embedding_function=embedding_model
)
retriever = vectorstore_persisted.as_retriever(
search_type='similarity',
search_kwargs={'k': 5}
)
def predict(input: str, history):
"""
Predict the response of the chatbot and complete a running list of chat history.
"""
relevant_document_chunks = retriever.invoke(input)
context_list = [d.page_content for d in relevant_document_chunks]
context_for_query = "\n".join(context_list)
user_message = [{
'role': 'user',
'content': qna_user_message_template.format(
context=context_for_query,
question=input
)
}]
prompt = [{'role':'system', 'content': qna_system_message}]
for entry in history:
prompt += (
[{'role': 'user', 'content': entry[0]}] +
[{'role': 'assistant', 'content': entry[1]}]
)
final_prompt = prompt + user_message
try:
response = client.chat.completions.create(
model=qna_model,
messages=final_prompt,
temperature=0
)
prediction = response.choices[0].message.content.strip()
except Exception as e:
prediction = f"Sorry, I cannot answer your question at this point. Please contact our hotline: 1-800-INSURANCE"
return prediction
demo = gr.ChatInterface(
fn=predict,
examples=["Summarize key feaures of my policy",
"Did I pay my last installment? How many have I paid so far?",
"Are hospitalization charges included in my policy?"
],
cache_examples=False,
title="Know Your Health Insurance Policy Better",
description="Feel free to ask me any query you might have about your health insurance policy",
concurrency_limit=8,
show_progress="full"
)
demo.launch(auth=("johndoe", os.getenv('PASSWD'))) |