Spaces:
Running
Running
| import gradio as gr | |
| docs = None | |
| def request_pathname(files): | |
| return [[file.name, file.name.split('/')[-1]] for file in files] | |
| def validate_dataset(dataset, openapi): | |
| docs_ready = dataset.iloc[-1, 0] != "" | |
| if docs_ready and type(openapi) is str and len(openapi) > 0: | |
| return "✨Ready✨" | |
| elif docs_ready: | |
| return "Waiting for key..." | |
| elif type(openapi) is str and len(openapi) > 0: | |
| return "Waiting for documents..." | |
| else: | |
| return "Waiting for documents and key..." | |
| def do_ask(question, button, openapi, dataset, progress=gr.Progress()): | |
| global docs | |
| docs_ready = dataset.iloc[-1, 0] != "" | |
| if button == "✨Ready✨" and openapi != "" and docs_ready: | |
| import os | |
| os.environ['OPENAI_API_KEY'] = openapi.strip() | |
| import paperqa | |
| docs = paperqa.Docs() | |
| # dataset is pandas dataframe | |
| for _, row in dataset.iterrows(): | |
| key = None | |
| if ',' not in row['citation string']: | |
| key = row['citation string'] | |
| docs.add(row['filepath'], row['citation string'], key=key) | |
| else: | |
| return "" | |
| if docs is None: | |
| return """**Error**: You must build the index first!""" | |
| progress(0, "Building Index...") | |
| docs._build_faiss_index() | |
| progress(0.25, "Querying...") | |
| result = docs.query(question) | |
| progress(1.0, "Done!") | |
| return result.formatted_answer, result.context | |
| with gr.Blocks() as demo: | |
| gr.Markdown(""" | |
| # Document Question and Answer | |
| This tool will enable asking questions of your uploaded text or PDF documents. | |
| It uses OpenAI's GPT models and thus you must enter your API key below. This | |
| tool is under active development and currently uses many tokens - up to 10,000 | |
| for a single query. That is $0.10-0.20 per query, so please be careful! | |
| * [PaperQA](https://github.com/whitead/paper-qa) is the code used to build this tool. | |
| * [langchain](https://github.com/hwchase17/langchain) is the main library this tool utilizes. | |
| ## Instructions | |
| 1. Enter API Key | |
| 2. Upload your documents and modify citation strings if you want (to look prettier) | |
| """) | |
| openai_api_key = gr.Textbox( | |
| label="OpenAI API Key", placeholder="sk-...", type="password") | |
| uploaded_files = gr.File( | |
| label="Your Documents Upload (PDF or txt)", file_count="multiple") | |
| dataset = gr.Dataframe( | |
| headers=["filepath", "citation string"], | |
| datatype=["str", "str"], | |
| col_count=(2, "fixed"), | |
| interactive=True, | |
| label="Documents and Citations" | |
| ) | |
| buildb = gr.Textbox("Waiting for documents and key...", | |
| label="Status", interactive=False, show_label=True) | |
| openai_api_key.change(validate_dataset, inputs=[ | |
| dataset, openai_api_key], outputs=[buildb]) | |
| dataset.change(validate_dataset, inputs=[ | |
| dataset, openai_api_key], outputs=[buildb]) | |
| uploaded_files.change(request_pathname, inputs=[ | |
| uploaded_files], outputs=[dataset]) | |
| query = gr.Textbox( | |
| placeholder="Enter your question here...", label="Question") | |
| ask = gr.Button("Ask Question") | |
| gr.Markdown("## Answer") | |
| answer = gr.Markdown(label="Answer") | |
| with gr.Accordion("Context", open=False): | |
| gr.Markdown( | |
| "### Context\n\nThe following context was used to generate the answer:") | |
| context = gr.Markdown(label="Context") | |
| ask.click(fn=do_ask, inputs=[query, buildb, | |
| openai_api_key, dataset], outputs=[answer, context]) | |
| demo.queue(concurrency_count=3) | |
| demo.launch() | |