import os; import json; import requests
import streamlit as st
ES_URL = os.environ.get("ES_URL")

question = 'What is the capital of Netherlands?'
query_text = 'Query used for keyword search (you can also edit, and experiment with the responses)'
written_question = st.text_input(query_text, question)
if written_question:
    question = written_question
if st.button('Run keyword search'):
    if question:
        try:
            url = f"{ES_URL}/document/_search?pretty"
            # payload = json.dumps({"query":{"match":{"content":"moldova"}}})
            payload = json.dumps({"query": {
                "more_like_this": { "like": question, # "What is the capital city of Netherlands?"
                "fields": ["content"], "min_term_freq": 1.9, "min_doc_freq": 4, "max_query_terms": 50
            }}})
            headers = {'Content-Type': 'application/json'}
            response = requests.request("GET", url, headers=headers, data=payload) 
            kws_result = response.json() # print(response.text)
            # qa_result = pipe_exqa(question=question, context=paragraph)
            
        except Exception as e:
            qa_result = str(e)

        top_5_hits = kws_result['hits']['hits'][:5] # print("First 5 results:")
        top_5_text = [{'text': hit['_source']['content'][:500],
                       'confidence': hit['_score']} for hit in top_5_hits ]

        for i, doc_hit in enumerate(top_5_text):
            st.subheader(f'Search result #{i+1} (and score):')
            st.write(f'<em>{doc_hit["text"]}...</em>', unsafe_allow_html = True)
            st.markdown(f'> (*confidence score*: **{format(doc_hit["confidence"], ".3f")}**)')
            
        st.write(f'Answer JSON: '); st.write(top_5_text) # st.write(qa_result)
    else:
        st.write('Write a query to submit your keyword search'); st.stop()


# if "answer" in qa_result.keys():
#     answer_span, answer_score = qa_result["answer"], qa_result["score"]
#     st.write(f'Answer: **{answer_span}**')
#     start_par, stop_para = max(0, qa_result["start"]-86), min(qa_result["end"]+90, len(paragraph))
#     answer_context = paragraph[start_par:stop_para].replace(answer_span, f'**{answer_span}**')
#     st.write(f'Answer context (and score): ... _{answer_context}_ ... (score: {format(answer_score, ".3f")})')

# question_similarity = [ (hit['_score'], hit['_source']['content'][:200])
#     for hit in result_first_two_hits ] # print(question_similarity)

# top_hit = result['hits']['hits'][0]
# context = top_hit['_source']['content']
# # context = r" Extractive Question Answering is the task of extracting   
# # an answer from a text given a question. An example of a question  
# # answering dataset is the SQuAD dataset, which is entirely based   
# # on that task. If you would like to fine-tune a model on a SQuAD task,  
# # you may leverage the `examples/pytorch/question-answering/run_squad.py` script."
# question = input # "What is extractive question answering?" 
# # "What is a good example of a question answering dataset?"
# print(question)
# context = context[:5000]
# print(context)
# try:
#     qa_result = pipe_exqa(question=question, context=context)
# except Exception as e:
#     return {"output": str(e)}

# return {"output": str(qa_result)}
    
# answer = qa_result['answer']
# score = round(qa_result['score'], 4)
# span = f"start: {qa_result['start']}, end: {qa_result['end']}"
# # st.write(answer); st.write(f"score: {score}"); st.write(f"span: {span}")
# output = f"{str(answer)} \n {str(score)} \n {str(span)}"

# return {"output": output} or {"output": str(question_similarity)} or result or {"Hello": "World!"}