File size: 3,864 Bytes
73f994d 705accd ab57a2b 1d92ef6 73f994d f416fa2 ab57a2b 43c0772 ab57a2b 73f994d 81d7443 73f994d 81d7443 73f994d 81d7443 73f994d 81d7443 22e1df4 587fe25 ab57a2b 587fe25 6df6129 73f994d 81d7443 73f994d 81d7443 9fdd6f5 73f994d |
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 |
import pandas as pd
import gradio as gr
from datasets import load_dataset
from langchain.document_loaders import DataFrameLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings
from langchain.chains import RetrievalQA
from langchain.chat_models import ChatOpenAI
dataset_names = ["zelros/pj-ca", "zelros/pj-ce", "zelros/pj-da",
"zelros/pj-groupama", "zelros/pj-sg", "zelros/pj-lbp"]
insurers = ["Crédit Agricole","Caisse d'Epargne","Direct Assurance","Groupama","Société Générale","La Banque Postale"]
db_dict = {}
def llm_response(insurer1, insurer2, question, gpt):
llm1 = ChatOpenAI(model_name=gpt)
llm2 = ChatOpenAI(model_name=gpt)
qa_chain1 = RetrievalQA.from_chain_type(llm1, retriever=db_dict[insurer1].as_retriever(search_kwargs={'k': 8}))
qa_chain2 = RetrievalQA.from_chain_type(llm2, retriever=db_dict[insurer2].as_retriever(search_kwargs={'k': 8}))
return qa_chain1({"query": question})['result'], qa_chain2({"query": question})['result']
examples = [
[None, None, "Est-il possible de choisir son avocat ?"],
[None, None, "Les problèmes de divorce sont-ils couverts ?"],
[None, None, "En cas violences conjugales, puis-je être assisté ?"],
[None, None, "Les problèmes d'usurpation d'identité sont-ils couverts ?"],
[None, None, "Quel est le montant maximum couvert pour un litige ?"],
[None, None, "Quels frais sont pris en charges, et quels frais ne sont pas pris en charge ?"],
[None, None, "En tant que membre d'une association, suis-je couvert ?"],
[None, None, "J'ai un litige concernant un brevet et un sujet de propriété intellectuelle, suis-je couvert ?"],
[None, None, "Quels sont les moments où le contrat peut être résilié ?"]
]
for i, name in enumerate(dataset_names):
dataset = load_dataset(name)
df = dataset['train'].to_pandas()
df['text'] = df["title"] + df["content"]
loader = DataFrameLoader(df, 'text')
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=5000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
db = FAISS.from_documents(texts, embeddings)
db_dict[insurers[i]] = db
demo = gr.Interface(llm_response,
inputs=[
gr.Dropdown(choices=insurers,
label="Insurer 1",
value="Société Générale",
info="More insurers available soon !"),
gr.Dropdown(choices=insurers,
label="Insurer 2",
value="La Banque Postale"),
gr.Textbox(label="Question",
info="More examples below :)",
value="Quel est le montant maximum couvert pour un litige ?"),
gr.Dropdown(choices=["gpt-3.5-turbo","gpt-4-1106-preview"],
label="LLM",
value="gpt-4-1106-preview",
info="gpt-4 is more accurate, but a few seconds longer thant gpt-3"),
],
outputs=[gr.Textbox(label="Answer insurer 1"),
gr.Textbox(label="Answer insurer 2")
],
title='Towards more accessible and inclusive insurances',
description='### <center>Compare french legal protection insurances - Research project, non-binding information - Please refer to a professional for advice.',
examples=examples,
cache_examples=False)
demo.launch() |