document_questioner_app.py

import openai
import os
import gradio as gr
import chromadb
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.indexes import VectorstoreIndexCreator
from langchain.chains import RetrievalQAWithSourcesChain
from langchain.prompts import PromptTemplate
from langchain.chat_models import ChatOpenAI

os.environ["OPENAI_API_KEY"] = "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"

def question_document(Document, Question):
    
    # loads a PDF document
    if not Document.name.endswith('.pdf'):
      return ("Le fichier doit être un document PDF")

    loader = PyPDFLoader(Document.name)
    docs = loader.load()
    
    # Create embeddings
    embeddings = OpenAIEmbeddings()
    
    # Write in DB
    docsearch = Chroma.from_documents(docs, embeddings, ids=["page" + str(d.metadata["page"]) for d in docs])

    # Define LLM
    llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.8)

    # Customize map_reduce prompts
    question_template = """{context}
    Precise the number starting the above text in your answer. It corresponds to its page number in the document it is from. Label this number as "page".
    Also make sure to answer in the same langage than the following question.
    QUESTION : {question}
    ANSWER : 
    """
    
    combine_template = """{summaries}
    Note that the above text is based on transient extracts from one source document.
    So make sure to not mention different documents or extracts or passages or portions or texts. There is only one, entire document. 
    Also make sure to answer in the same langage than the following question. 
    QUESTION : {question}.
    ANSWER : 
    """
    
    question_prompt = PromptTemplate(template = question_template, input_variables=['context', 'question'])
    combine_prompt = PromptTemplate(template = combine_template, input_variables=['summaries', 'question'])
    
    # Define chain  
    chain_type_kwargs = { "combine_prompt" : combine_prompt, "question_prompt" : question_prompt} #, "return_intermediate_steps" : True}
    qa = RetrievalQAWithSourcesChain.from_chain_type(llm = llm, chain_type = "map_reduce", chain_type_kwargs = chain_type_kwargs, retriever=docsearch.as_retriever(), return_source_documents = True)
   
    answer = qa({"question" : Question}, return_only_outputs = True)
    return answer["answer"] 

iface = gr.Interface(
    fn = question_document, 
    inputs= ["file","text"],
    outputs = gr.outputs.Textbox(label="Réponse"), 
    title="Interrogateur de PDF",
    description="par Nicolas \nPermet d'interroger un document PDF",
    allow_flagging = "never")

iface.launch()