|
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 match'): |
|
if question: |
|
try: |
|
url = f"{ES_URL}/document/_search?pretty" |
|
payload = json.dumps({"query":{"match":{"content": question}}}) |
|
headers = {'Content-Type': 'application/json'} |
|
response = requests.request("GET", url, headers=headers, data=payload) |
|
kws_result = response.json() |
|
|
|
except Exception as e: |
|
qa_result = str(e) |
|
|
|
top_5_hits = kws_result['hits']['hits'][:5] |
|
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) |
|
else: |
|
st.write('Write a query to submit your keyword search'); st.stop() |
|
|
|
if st.button('Run keyword search'): |
|
if question: |
|
try: |
|
url = f"{ES_URL}/document/_search?pretty" |
|
payload = json.dumps({"query": { |
|
"more_like_this": { "like": question, |
|
"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() |
|
|
|
except Exception as e: |
|
qa_result = str(e) |
|
|
|
top_5_hits = kws_result['hits']['hits'][:5] |
|
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) |
|
else: |
|
st.write('Write a query to submit your keyword search'); st.stop() |
|
|
|
|
