File size: 4,078 Bytes
7c5b75d 8bb9144 7c5b75d 8bb9144 7c5b75d 8bb9144 ea8b785 8bb9144 ea8b785 8bb9144 7c5b75d 8bb9144 7c5b75d 8bb9144 7c5b75d 8bb9144 7c5b75d 8bb9144 7c5b75d ea8b785 7c5b75d 8bb9144 ea8b785 8bb9144 ea8b785 | 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 | import gradio as gr
import os
import time
import requests
from bs4 import BeautifulSoup
from langchain.document_loaders import OnlinePDFLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.chains import ConversationalRetrievalChain
def loading_pdf():
return "Loading..."
def changes(document, open_ai_key):
if open_ai_key is not None:
os.environ['OPENAI_API_KEY'] = open_ai_key
if isinstance(document, str): # URL
text = download_and_convert_url_to_text(document)
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_text(text)
else: # PDF
loader = OnlinePDFLoader(document.name)
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
db = Chroma.from_documents(texts, embeddings)
retriever = db.as_retriever()
global qa
qa = ConversationalRetrievalChain.from_llm(
llm=OpenAI(temperature=0.5),
retriever=retriever,
return_source_documents=False)
return "Ready"
else:
return "You forgot OpenAI API key"
def add_text(history, text):
history = history + [(text, None)]
return history, ""
def bot(history):
response = infer(history[-1][0], history)
history[-1][1] = ""
for character in response:
history[-1][1] += character
time.sleep(0.05)
yield history
def infer(question, history):
res = []
for human, ai in history[:-1]:
pair = (human, ai)
res.append(pair)
chat_history = res
query = question
result = qa({"question": query, "chat_history": chat_history})
return result["answer"]
def download_and_convert_url_to_text(url):
html = requests.get(url).text
soup = BeautifulSoup(html, features="html.parser")
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
return '\n'.join(line for line in lines if line)
css="""
#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
"""
title = """
<div style="text-align: center;max-width: 700px;">
<h1>Chat with PDF or URL • OpenAI</h1>
<p style="text-align: center;">Upload a .PDF from your computer or insert a URL, click the "Load to LangChain" button, <br />
when everything is ready, you can start asking questions about the pdf or URL ;) <br />
This version is set to store chat history, and uses OpenAI as LLM, don't forget to copy/paste your OpenAI API key</p>
</div>
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.HTML(title)
with gr.Column():
openai_key = gr.Textbox(label="You OpenAI API key", type="password")
pdf_doc = gr.File(label="Upload a pdf", type="file")
url = gr.Textbox(label="Or insert a URL")
with gr.Row():
langchain_status = gr.Textbox(label="Langchain Status", placeholder="Loading...", interactive=False)
load = gr.Button("Load to LangChain")
chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
submit_btn = gr.Button("Send Message")
load.click(loading_pdf, None, langchain_status, queue=False)
load.click(changes, inputs=[pdf_doc, url, openai_key], outputs=[langchain_status], queue=False)
question.submit(add_text, [chatbot, question], [chatbot, question]).then(
bot, chatbot, chatbot
)
submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
bot, chatbot, chatbot)
demo.launch() |