import os import sys import logging from pathlib import Path from json import JSONDecodeError import pandas as pd import streamlit as st from annotated_text import annotation from markdown import markdown import json from haystack import Document import pandas as pd from haystack.document_stores import PineconeDocumentStore from haystack.nodes import EmbeddingRetriever, FARMReader from haystack.pipelines import ExtractiveQAPipeline # @st.cache def create_doc_store(): document_store = PineconeDocumentStore( api_key= st.secrets["pinecone_apikey"], index='qa_demo', similarity="cosine", embedding_dim=768 ) return document_store # @st.cache def create_pipe(document_store): retriever = EmbeddingRetriever( document_store=document_store, embedding_model="sentence-transformers/multi-qa-mpnet-base-dot-v1", model_format="sentence_transformers", ) reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False) pipe = ExtractiveQAPipeline(reader, retriever) return pipe def query(pipe, question, top_k_reader, top_k_retriever): res = pipe.run( query=question, params={"Retriever": {"top_k": top_k_retriever}, "Reader": {"top_k": top_k_reader}} ) answer_df = [] # for r in res['answers']: # ans_dict = res['answers'][0].meta # ans_dict["answer"] = r.context # answer_df.append(ans_dict) # result = pd.DataFrame(answer_df) # result.columns = ["Source","Title","Year","Link","Answer"] # result[["Answer","Link","Source","Title","Year"]] return res document_store = create_doc_store() pipe = create_pipe(document_store) def set_state_if_absent(key, value): if key not in st.session_state: st.session_state[key] = value # Adjust to a question that you would like users to see in the search bar when they load the UI: DEFAULT_QUESTION_AT_STARTUP = os.getenv("DEFAULT_QUESTION_AT_STARTUP", "My blog post discusses remote work. Give me statistics.") DEFAULT_ANSWER_AT_STARTUP = os.getenv("DEFAULT_ANSWER_AT_STARTUP", "7% more remote workers have been at their current organization for 5 years or fewer") # Sliders DEFAULT_DOCS_FROM_RETRIEVER = int(os.getenv("DEFAULT_DOCS_FROM_RETRIEVER", "3")) DEFAULT_NUMBER_OF_ANSWERS = int(os.getenv("DEFAULT_NUMBER_OF_ANSWERS", "3")) st.set_page_config(page_title="Haystack Demo", page_icon="https://haystack.deepset.ai/img/HaystackIcon.png") # Persistent state set_state_if_absent("question", DEFAULT_QUESTION_AT_STARTUP) set_state_if_absent("answer", DEFAULT_ANSWER_AT_STARTUP) set_state_if_absent("results", None) # Small callback to reset the interface in case the text of the question changes def reset_results(*args): st.session_state.answer = None st.session_state.results = None st.session_state.raw_json = None # Title st.write("# Haystack Demo - Explore the world") st.markdown( """ This demo takes its data from two sample data csv with statistics on various topics Ask any question on this topic and see if Haystack can find the correct answer to your query! *Note: do not use keywords, but full-fledged questions.* The demo is not optimized to deal with keyword queries and might misunderstand you. """, unsafe_allow_html=True, ) # Sidebar st.sidebar.header("Options") top_k_reader = st.sidebar.slider( "Max. number of answers", min_value=1, max_value=10, value=DEFAULT_NUMBER_OF_ANSWERS, step=1, on_change=reset_results, ) top_k_retriever = st.sidebar.slider( "Max. number of documents from retriever", min_value=1, max_value=10, value=DEFAULT_DOCS_FROM_RETRIEVER, step=1, on_change=reset_results, ) # data_files = st.file_uploader( # "upload", type=["csv"], accept_multiple_files=True, label_visibility="hidden" # ) # for data_file in data_files: # # Upload file # if data_file: # raw_json = upload_doc(data_file) question = st.text_input( value=st.session_state.question, max_chars=100, on_change=reset_results, label="question", label_visibility="hidden", ) col1, col2 = st.columns(2) col1.markdown("", unsafe_allow_html=True) col2.markdown("", unsafe_allow_html=True) # Run button run_pressed = col1.button("Run") if run_pressed: run_query = ( run_pressed or question != st.session_state.question ) # Get results for query if run_query and question: reset_results() st.session_state.question = question with st.spinner( "🧠    Performing neural search on documents... \n " "Do you want to optimize speed or accuracy? \n" "Check out the docs: https://haystack.deepset.ai/usage/optimization " ): try: st.session_state.results = query( pipe, question, top_k_reader=top_k_reader, top_k_retriever=top_k_retriever ) except JSONDecodeError as je: st.error("👓    An error occurred reading the results. Is the document store working?") except Exception as e: logging.exception(e) if "The server is busy processing requests" in str(e) or "503" in str(e): st.error("🧑‍🌾    All our workers are busy! Try again later.") else: st.error(f"🐞    An error occurred during the request. {str(e)}") if st.session_state.results: st.write("## Results:") for count, result in enumerate(st.session_state.results['answers']): answer, context = result.answer, result.context start_idx = context.find(answer) end_idx = start_idx + len(answer) source = f"[{result.meta['Title']}]({result.meta['link']})" # Hack due to this bug: https://github.com/streamlit/streamlit/issues/3190 st.write( markdown(f'**Source:** {source} \n {context[:start_idx] } {str(annotation(answer, "ANSWER", "#8ef"))} {context[end_idx:]} \n '), unsafe_allow_html=True, )