Spaces:
Runtime error
Runtime error
File size: 3,422 Bytes
fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 ee09d2c fdf7fb5 dd797b5 fdf7fb5 dd797b5 fdf7fb5 ee09d2c fdf7fb5 |
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 |
import gradio as gr
docs = None
def request_pathname(files):
if files is None:
return [[]]
return [[file.name, file.name.split('/')[-1]] for file in files]
def validate_dataset(dataset):
global docs
docs = None # clear it out if dataset is modified
docs_ready = dataset.iloc[-1, 0] != ""
if docs_ready:
return "✨Listo✨"
else:
return "⚠️Waiting for documents..."
def do_ask(question, button, dataset, progress=gr.Progress()):
global docs
docs_ready = dataset.iloc[-1, 0] != ""
if button == "✨Listo✨" and docs_ready:
if docs is None: # don't want to rebuild index if it's already built
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 ""
progress(0, "Construyendo índices...")
docs._build_faiss_index()
progress(0.25, "Encolando...")
result = docs.query(question)
progress(1.0, "¡Hecho!")
return result.formatted_answer, result.context
with gr.Blocks() as demo:
gr.Markdown("""
# Document Question and Answer adaptado al castellano por Pablo Ascorbe.
Este espacio ha sido clonado y adaptado de: https://huggingface.co/spaces/whitead/paper-qa
- Texto original:
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.
## Instrucciones:
Adjunte su documento, ya sea en formato .txt o .pdf, y pregunte lo que desee.
""")
uploaded_files = gr.File(
label="Sus documentos subidos (PDF o 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("⚠️Esperando documentos...",
label="Status", interactive=False, show_label=True)
dataset.change(validate_dataset, inputs=[
dataset], outputs=[buildb])
uploaded_files.change(request_pathname, inputs=[
uploaded_files], outputs=[dataset])
query = gr.Textbox(
placeholder="Introduzca su pregunta aquí...", label="Pregunta")
ask = gr.Button("Pregunte")
gr.Markdown("## Respuesta")
answer = gr.Markdown(label="Respuesta")
with gr.Accordion("Contexto", open=False):
gr.Markdown(
"### Contexto\n\nEl siguiente contexto ha sido utilizado para generar la respuesta:")
context = gr.Markdown(label="Contexto")
ask.click(fn=do_ask, inputs=[query, buildb,
dataset], outputs=[answer, context])
demo.queue(concurrency_count=20)
demo.launch(show_error=True)
|