Download app.py from wiwide/pdforurl: direct link, hf CLI and curl.
- Browser
- Download file 4.08 kB
-
https://huggingface.co/spaces/wiwide/pdforurl/resolve/main/app.py
- Command line
-
hf download hf://spaces/wiwide/pdforurl/app.py
-
curl -L -o app.py https://huggingface.co/spaces/wiwide/pdforurl/resolve/main/app.py
4.08 kB
| 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() |