File size: 2,494 Bytes
2b0a298
 
 
 
 
 
 
 
92a96a7
2b0a298
 
 
06a82b5
2b0a298
 
 
 
 
 
 
 
 
 
 
 
e977a64
2b0a298
92a96a7
2b0a298
 
 
 
 
 
1d13553
 
de0c29d
06a82b5
11f2063
06a82b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2b0a298
 
06a82b5
de0c29d
06a82b5
 
2b0a298
bb56ef0
06a82b5
 
2b0a298
 
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
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)


def load_pdf(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
        pdf_qa = RetrievalQA.from_chain_type(ChatOpenAI(temperature=0, model_name="gpt-4"), vectordb.as_retriever(), 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)

    
html = """
<div style="text-align:center; max width: 700px;">
    <h1>ChatPDF</h1>
    <p> Upload a PDF File, then click on Load PDF File <br>
    Once the document has been loaded you can begin chatting with the PDF =)
</div>"""
css = """container{max-width:700px; margin-left:auto; margin-right:auto,padding:20px}"""
with gr.Blocks(css=css,theme=gr.themes.Monochrome()) as demo:
    gr.HTML(html)
    with gr.Column():
        gr.Markdown('ChatPDF')
        pdf_doc = gr.File(label="Load a pdf",file_types=['.pdf','.docx'],type='file')
        with gr.Row():
            load_pdf = gr.Button('Load pdf file')
            status = gr.Textbox(label="Status",placeholder='',interactive=False)


        with gr.Row():
            input = gr.Textbox(label="Type in your question")
            output = gr.Textbox(label="output")
        submit_query = gr.Button("submit")

        load_pdf.click(load_pdf,inputs=[pdf_doc, openai_key],outputs=status)

        submit_query.click(answer_query,input,output)

demo.launch()