| 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") |
| |
| 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() |
