Duplicate from stmnk/mlrefkws

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Mlrefkws
+emoji: 💻
+colorFrom: purple
+colorTo: green
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+duplicated_from: stmnk/mlrefkws
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,39 @@
+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()
+