app.py

import streamlit as st
import pandas as pd

from haystack.schema import Answer
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipeline import FAQPipeline
from haystack.retriever.dense import EmbeddingRetriever
import logging

#Haystack function calls - streamlit structure from Tuana GoT QA Haystack demo
@st.cache(hash_funcs={"builtins.SwigPyObject": lambda _: None},allow_output_mutation=True) # use streamlit cache

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)
 
pipeline = start_haystack()
 
 # Streamlit App section
 
def set_state_if_absent(key, value):
    if key not in st.session_state:
        st.session_state[key] = value
        
def reset_results(*args):
    st.session_state.results = None

set_state_if_absent("question", "how much money should each player have at the beginning?")
set_state_if_absent("results", None)
 
 
st.markdown( """
Haystack FAQ Semantic Search Pipeline
""", unsafe_allow_html=True)

question = st.text_input("", value=st.session_state.question, max_chars=100, on_change=reset_results)

def ask_question(question):
    prediction = pipeline.run(query=question)
    results = []
    for answer in prediction["answers"]:
        answer = answer.to_dict()
        if answer["answer"]:
            results.append(
                {
                    "context": "..." + answer["context"] + "...",
                    "answer": answer["answer"],
                    "relevance": round(answer["score"] * 100, 2),
                    "offset_start_in_doc": answer["offsets_in_document"][0]["start"],
                }
            )
        else:
            results.append(
                {
                    "context": None,
                    "answer": None,
                    "relevance": round(answer["score"] * 100, 2),
                }
            )
    return results

if question:
    with st.spinner("👑    Performing semantic search on FAQ Database..."):
        try:
            msg = 'Asked ' + question
            logging.info(msg)
            st.session_state.results = ask_question(question)    
        except Exception as e:
            logging.exception(e)
    


if st.session_state.results:
    st.write('## Top Results')
    for count, result in enumerate(st.session_state.results):
        if result["answer"]:
            answer, context = result["answer"], result["context"]
            start_idx = context.find(answer)
            end_idx = start_idx + len(answer)
            st.write(
                markdown(context[:start_idx] + str(annotation(body=answer, label="ANSWER", background="#964448", color='#ffffff')) + context[end_idx:]),
                unsafe_allow_html=True,
            )
            st.markdown(f"**Relevance:** {result['relevance']}")
        else:
            st.info(
                "🤔    Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
            )