Hugging Face's logo

Spaces:
binqiangliu
/
NewPDFChatbot
Paused

App Files Community
NewPDFChatbot
File size: 5,159 Bytes
359ae65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
befcc2d
 
 
 
68d11c4
befcc2d
359ae65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
#完整代码：https://www.analyticsvidhya.com/blog/2023/05/build-a-chatgpt-for-pdfs-with-langchain/

#import csv
import gradio as gr
#在Gradio deploy到Huggingface的时候遇到问题（Traceback (most recent call last):   File "/home/user/app/fullcode.py", line 5, in <module> from langchain.embeddings.openai import OpenAIEmbeddings ModuleNotFoundError: No module named 'langchain'），所以尝试增加下面的代码import langchain
import langchain
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma

from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI

from langchain.document_loaders import PyPDFLoader
import os

import openai
import chromadb
import tiktoken
import pypdf
#import pymupdf

import fitz
from PIL import Image

# Global variables
COUNT, N = 0, 0
chat_history = []
chain = ''
enable_box = gr.Textbox.update(value=None, 
                          placeholder='Upload your OpenAI API key', interactive=True)
disable_box = gr.Textbox.update(value='OpenAI API key is Set', interactive=False)

# Function to set the OpenAI API key
def set_apikey(api_key):
    os.environ['OPENAI_API_KEY'] = api_key
    return disable_box

# Function to enable the API key input box
def enable_api_box():
    return enable_box

# Function to add text to the chat history
def add_text(history, text):
    if not text:
        raise gr.Error('Enter text')
    history = history + [(text, '')]
    return history

# Function to process the PDF file and create a conversation chain
def process_file(file):
    if 'OPENAI_API_KEY' not in os.environ:
        raise gr.Error('Upload your OpenAI API key')

    loader = PyPDFLoader(file.name)
    documents = loader.load()

    embeddings = OpenAIEmbeddings()
    
    pdfsearch = Chroma.from_documents(documents, embeddings)

    chain = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0.3), 
                                   retriever=pdfsearch.as_retriever(search_kwargs={"k": 1}),
                                   return_source_documents=True)
    return chain

# Function to generate a response based on the chat history and query
def generate_response(history, query, btn):
    global COUNT, N, chat_history, chain
    
    if not btn:
        raise gr.Error(message='Upload a PDF')
    if COUNT == 0:
        chain = process_file(btn)
        COUNT += 1
    
    result = chain({"question": query, 'chat_history': chat_history}, return_only_outputs=True)
    chat_history += [(query, result["answer"])]
    N = list(result['source_documents'][0])[1][1]['page']

    for char in result['answer']:
        history[-1][-1] += char
        yield history, ''

# Function to render a specific page of a PDF file as an image
def render_file(file):
    global N
    doc = fitz.open(file.name)
    page = doc[N]
    # Render the page as a PNG image with a resolution of 300 DPI
    pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72))
    image = Image.frombytes('RGB', [pix.width, pix.height], pix.samples)
    return image

# Gradio application setup
with gr.Blocks() as demo:
    # Create a Gradio block

    with gr.Column():
        with gr.Row():
            with gr.Column(scale=0.8):
                api_key = gr.Textbox(
                    placeholder='Enter OpenAI API key',
                    show_label=False,
                    interactive=True
                ).style(container=False)
            with gr.Column(scale=0.2):
                change_api_key = gr.Button('Change Key')

        with gr.Row():
            chatbot = gr.Chatbot(value=[], elem_id='chatbot').style(height=650)
            show_img = gr.Image(label='Upload PDF', tool='select').style(height=680)

    with gr.Row():
        with gr.Column(scale=0.70):
            txt = gr.Textbox(
                show_label=False,
                placeholder="Enter text and press enter"
            ).style(container=False)

        with gr.Column(scale=0.15):
            submit_btn = gr.Button('Submit')

        with gr.Column(scale=0.15):
            btn = gr.UploadButton("📁 Upload a PDF", file_types=[".pdf"]).style()

    # Set up event handlers

    # Event handler for submitting the OpenAI API key
    api_key.submit(fn=set_apikey, inputs=[api_key], outputs=[api_key])

    # Event handler for changing the API key
    change_api_key.click(fn=enable_api_box, outputs=[api_key])

    # Event handler for uploading a PDF
    btn.upload(fn=render_file, inputs=[btn], outputs=[show_img])

    # Event handler for submitting text and generating response
    submit_btn.click(
        fn=add_text,
        inputs=[chatbot, txt],
        outputs=[chatbot],
        queue=False
    ).success(
        fn=generate_response,
        inputs=[chatbot, txt, btn],
        outputs=[chatbot, txt]
    ).success(
        fn=render_file,
        inputs=[btn],
        outputs=[show_img]
    )
demo.queue()
if __name__ == "__main__":
#为了测试将app部署到Hugginface上，临时将下面的外链共享关闭！
#    demo.launch(share=True)
    demo.launch()