Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from langchain.document_loaders import OnlinePDFLoader | |
| from langchain.text_splitter import CharacterTextSplitter | |
| from langchain.llms import HuggingFaceHub | |
| from langchain.embeddings import HuggingFaceHubEmbeddings | |
| from langchain.vectorstores import Chroma | |
| from langchain.chains import RetrievalQA | |
| def loading_pdf(): | |
| return "Loading..." | |
| def pdf_changes(pdf_doc, repo_id): | |
| loader = OnlinePDFLoader(pdf_doc.name) | |
| documents = loader.load() | |
| text_splitter = CharacterTextSplitter(chunk_size=300, chunk_overlap=0) | |
| texts = text_splitter.split_documents(documents) | |
| embeddings = HuggingFaceHubEmbeddings() | |
| db = Chroma.from_documents(texts, embeddings) | |
| retriever = db.as_retriever() | |
| llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature":0.1, "max_new_tokens":250}) | |
| global qa | |
| qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True) | |
| return "Ready" | |
| def add_text(history, text): | |
| history = history + [(text, None)] | |
| return history, "" | |
| def bot(history): | |
| response = infer(history[-1][0]) | |
| history[-1][1] = response['result'] | |
| return history | |
| def infer(question): | |
| query = question | |
| result = qa({"query": query}) | |
| return result | |
| 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</h1> | |
| <p style="text-align: center;">Upload a .PDF from your computer, click the "Load PDF to LangChain" button, <br /> | |
| when everything is ready, you can start asking questions about the pdf ;)</p> | |
| <a style="display:inline-block; margin-left: 1em" href="https://huggingface.co/spaces/fffiloni/langchain-chat-with-pdf?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space%20to%20skip%20the%20queue-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a> | |
| </div> | |
| """ | |
| with gr.Blocks(css=css) as demo: | |
| with gr.Column(elem_id="col-container"): | |
| gr.HTML(title) | |
| with gr.Column(): | |
| pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="file") | |
| repo_id = gr.Dropdown(label="LLM", choices=["google/flan-ul2", "OpenAssistant/oasst-sft-1-pythia-12b", "bigscience/bloomz"], value="google/flan-ul2") | |
| with gr.Row(): | |
| langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False) | |
| load_pdf = gr.Button("Load pdf 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_pdf.click(loading_pdf, None, langchain_status, queue=False) | |
| repo_id.change(pdf_changes, inputs=[pdf_doc, repo_id], outputs=[langchain_status], queue=False) | |
| load_pdf.click(pdf_changes, inputs=[pdf_doc, repo_id], 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() |