import gradio as gr import os import time from langchain.document_loaders import OnlinePDFLoader #for laoding the pdf from langchain.embeddings import OpenAIEmbeddings # for creating embeddings from langchain.vectorstores import Chroma # for the vectorization part from langchain.chains import RetrievalQA # for conversing with chatGPT from langchain.chat_models import ChatOpenAI # the LLM model we'll use (ChatGPT) from langchain import PromptTemplate def load_doc(pdf_doc, open_ai_key): if openai_key is not None: os.environ['OPENAI_API_KEY'] = open_ai_key #Load the pdf file loader = OnlinePDFLoader(pdf_doc.name) pages = loader.load_and_split() #Create an instance of OpenAIEmbeddings, which is responsible for generating embeddings for text embeddings = OpenAIEmbeddings() #To create a vector store, we use the Chroma class, which takes the documents (pages in our case), the embeddings instance, and a directory to store the vector data vectordb = Chroma.from_documents(pages, embedding=embeddings) #Finally, we create the bot using the RetrievalQAChain class global pdf_qa prompt_template = """Use the following pieces of context to answer the question at the end. If you do not know the answer, just return the question followed by N/A. If you encounter a date, return it in mm/dd/yyyy format. {context} Question: {question} Return the key fields from the question followed by the answer :""" PROMPT = PromptTemplate(template=prompt_template, input_variables=["context", "question"]) chain_type_kwargs = {"prompt": PROMPT} pdf_qa = RetrievalQA.from_chain_type(llm=ChatOpenAI(temperature=0, model_name="gpt-4"),chain_type="stuff", retriever=vectordb.as_retriever(), chain_type_kwargs=chain_type_kwargs, return_source_documents=False) return "Ready" else: return "Please provide an OpenAI API key" def answer_query(query): question = query return pdf_qa.run(question) css=""" #col-container {max-width: 700px; margin-left: auto; margin-right: auto;} """ title = """

Chatbot for PDFs - GPT-4

Upload a .PDF, click the "Load PDF to LangChain" button,
Wait for the Status to show Ready, start typing your questions.
The app is built on GPT-4

""" with gr.Blocks(css=css,theme=gr.themes.Monochrome()) as demo: with gr.Column(elem_id="col-container"): gr.HTML(title) with gr.Column(): openai_key = gr.Textbox(label="Your GPT-4 OpenAI API key", type="password") pdf_doc = gr.File(label="Load a pdf",file_types=['.pdf'],type='file') with gr.Row(): status = gr.Textbox(label="Status", placeholder="", interactive=False) load_pdf = gr.Button("Load PDF to LangChain") with gr.Row(): input = gr.Textbox(label="Type in your question") output = gr.Textbox(label="Answer") submit_query = gr.Button("Submit") load_pdf.click(load_doc, inputs=[pdf_doc, openai_key], outputs=status) submit_query.click(answer_query,input,output) #forcing a save in order to re-build the container. demo.launch()