Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import pandas as pd | |
| from haystack.schema import Answer | |
| from haystack.document_stores import InMemoryDocumentStore | |
| from haystack.pipelines import FAQPipeline, ExtractiveQAPipeline | |
| from haystack.nodes import EmbeddingRetriever, TfidfRetriever, FARMReader, TextConverter, PreProcessor | |
| from haystack.utils import print_answers | |
| from haystack.utils import convert_files_to_docs | |
| import logging | |
| # FAQ Haystack function calls | |
| def start_haystack(): | |
| document_store = InMemoryDocumentStore(index="document", embedding_field='embedding', embedding_dim=384, similarity='cosine') | |
| retriever = EmbeddingRetriever(document_store=document_store, embedding_model='sentence-transformers/all-MiniLM-L6-v2', use_gpu=True, top_k=1) | |
| load_data_to_store(document_store,retriever) | |
| pipeline = FAQPipeline(retriever=retriever) | |
| return pipeline | |
| def load_data_to_store(document_store, retriever): | |
| df = pd.read_csv('monopoly_qa-v1.csv') | |
| questions = list(df.Question) | |
| df['embedding'] = retriever.embed_queries(texts=questions) | |
| df = df.rename(columns={"Question":"content","Answer":"answer"}) | |
| df.drop('link to source (to prevent duplicate sources)',axis=1, inplace=True) | |
| dicts = df.to_dict(orient="records") | |
| document_store.write_documents(dicts) | |
| faq_pipeline = start_haystack() | |
| def predict_faq(question): | |
| prediction = faq_pipeline.run(question) | |
| answer = prediction["answers"][0].meta | |
| faq_response = "FAQ Question: " + answer["query"] + "\n"+"Answer: " + answer["answer"] | |
| return faq_response | |
| # Extractive QA functions | |
| ## preprocess monopoly rules | |
| def preprocess_txt_doc(fpath): | |
| converter = TextConverter(remove_numeric_tables=True, valid_languages=["en"]) | |
| doc_txt = converter.convert(file_path=fpath, meta=None)[0] | |
| preprocessor = PreProcessor( | |
| clean_empty_lines=True, | |
| clean_whitespace=True, | |
| clean_header_footer=False, | |
| split_by="word", | |
| split_length=100, | |
| split_respect_sentence_boundary=True,) | |
| docs = preprocessor.process([doc_txt]) | |
| return docs | |
| def start_ex_haystack(documents): | |
| ex_document_store = InMemoryDocumentStore() | |
| ex_document_store.write_documents(documents) | |
| retriever = TfidfRetriever(document_store=ex_document_store) | |
| reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False) | |
| pipe = ExtractiveQAPipeline(reader, retriever) | |
| return pipe | |
| docs = preprocess_txt_doc("monopoly_text_v1.txt") | |
| ex_pipeline = start_ex_haystack(docs) | |
| def predict_extract(question): | |
| prediction = ex_pipeline.run(question) | |
| possible_answers = "" | |
| for i,a in enumerate(prediction["answers"]): | |
| possible_answers = possible_answers +str(i) + ":" + a.answer + "\n" | |
| return possible_answers | |
| # Gradio App section | |
| input_question =gr.inputs.Textbox(label="enter your monopoly question here") | |
| response = "text" | |
| examples = ["how much cash do we get to start with?", "at what point can I buy houses?", "what happens when I land on free parking?"] | |
| mon_faq = gr.Interface( | |
| fn=predict_faq, | |
| inputs=input_question, | |
| outputs=response, | |
| examples=examples, | |
| title="Monopoly FAQ Semantic Search") | |
| # extractive interface | |
| mon_ex = gr.Interface( | |
| fn=predict_extract, | |
| inputs=input_question, | |
| outputs=response, | |
| examples=examples, | |
| title="Monopoly Extractive QA Search") | |
| gr.TabbedInterface([mon_faq,mon_ex],["FAQ Search","Extractive QA"]).launch() |