Spaces:
Sleeping
Sleeping
File size: 2,087 Bytes
3a6ebd0 16e395a 3a6ebd0 |
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 |
import gradio as gr
from haystack.nodes import FARMReader, PreProcessor, PDFToTextConverter, TfidfRetriever
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
document_store = InMemoryDocumentStore()
model = "Saturdays/mdeberta-v3-base-squad2_refugees_dataset"
reader = FARMReader(model_name_or_path=model)
preprocessor = PreProcessor(
clean_empty_lines=True,
clean_whitespace=True,
clean_header_footer=True,
split_by="word",
split_length=100,
split_respect_sentence_boundary=True,
split_overlap=3
)
def print_answers(results):
fields = ["answer", "score"] # "context",
answers = results["answers"]
filtered_answers = []
for ans in answers:
filtered_ans = {
field: getattr(ans, field)
for field in fields
if getattr(ans, field) is not None
}
filtered_answers.append(filtered_ans)
return filtered_answers
def pdf_to_document_store(pdf_file):
document_store.delete_documents()
converter = PDFToTextConverter(
remove_numeric_tables=True, valid_languages=["es"])
documents = [converter.convert(file_path=pdf_file, meta=None)[0]]
preprocessed_docs = preprocessor.process(documents)
document_store.write_documents(preprocessed_docs)
return None
def predict(question):
pdf_to_document_store("data.pdf")
retriever = TfidfRetriever(document_store=document_store)
pipe = ExtractiveQAPipeline(reader, retriever)
result = pipe.run(query=question, params={"Retriever": {
"top_k": 5}, "Reader": {"top_k": 3}})
answers = print_answers(result)
return answers
title = "Chatbot Refugiados"
iface = gr.Interface(fn=predict,
inputs=[gr.inputs.Textbox(lines=3, label='Haz una pregunta')],
outputs="text",
title=title,
theme="huggingface",
examples=['Dónde pedir ayuda?', 'qué hacer al llegar a España?']
)
iface.launch() |