Duplicate from jaimin/LongAnswer

Co-authored-by: Jaimin Mungalpara <[email protected]>

.gitattributes

@@ -0,0 +1,31 @@
+*.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
+*.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
+*.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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb 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
+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: LongAnswer
+emoji: 🐠
+colorFrom: yellow
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.10.0
+app_file: app.py
+pinned: false
+duplicated_from: jaimin/LongAnswer
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,80 @@
+import pinecone
+import streamlit as st
+from transformers import pipeline
+from sentence_transformers import SentenceTransformer
+
+PINECONE_KEY = 'b2aaea5e-1395-4270-8c6b-2c89ff1d0a13'
+
+@st.experimental_singleton
+def init_pinecone():
+    pinecone.init(api_key=PINECONE_KEY, environment="us-west1-gcp")  # get a free api key from app.pinecone.io
+    return pinecone.Index("extractive-question-answering")
+    
+@st.experimental_singleton
+def init_models():
+    retriever = SentenceTransformer("multi-qa-MiniLM-L6-cos-v1")
+    model_name = 'jaimin/bert-large-squad'
+    reader = pipeline(tokenizer=model_name, model=model_name, task='question-answering')
+    return retriever, reader
+
+st.session_state.index = init_pinecone()
+retriever, reader = init_models()
+
+
+def card(title, context, score):
+    return st.markdown(f"""
+    <div class="container-fluid">
+        <div class="row align-items-start">
+             <div  class="col-md-12 col-sm-12">
+                 <b>{title}</b>
+                 <br>
+                 <span style="color: #808080;">
+                     <small>{context}</small>
+                     [<b>Score: </b>{score}]
+                 </span>
+             </div>
+        </div>
+     </div>
+        """, unsafe_allow_html=True)
+
+st.title("")
+
+st.write("""
+# Extractive Question Answering
+Ask me a question!
+""")
+
+st.markdown("""
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" integrity="sha384-Gn5384xqQ1aoWXA+058RXPxPg6fy4IWvTNh0E263XmFcJlSAwiGgFAW/dAiS6JXm" crossorigin="anonymous">
+""", unsafe_allow_html=True)
+
+def run_query(query):
+    xq = retriever.encode([query]).tolist()
+    try:
+        xc = st.session_state.index.query(xq, top_k=3, include_metadata=True)
+    except:
+        # force reload
+        pinecone.init(api_key=PINECONE_KEY, environment="us-west1-gcp")
+        st.session_state.index = pinecone.Index("extractive-question-answering")
+        xc = st.session_state.index.query(xq, top_k=3, include_metadata=True)
+
+    results = []
+    for match in xc['matches']:
+        answer = reader(question=query, context=match["metadata"]['context'])
+        answer["title"] = match["metadata"]['title']
+        answer["context"] = match["metadata"]['context']
+        results.append(answer)
+
+    sorted_result = sorted(results, key=lambda x: x['score'], reverse=True)
+
+    for r in sorted_result:
+        answer = r["answer"]
+        context = r["context"].replace(answer, f"<mark>{answer}</mark>")
+        title = r["title"].replace("_", " ")
+        score = round(r["score"], 4)
+        card(title, context, score)
+
+query = st.text_input("Search!", "")
+
+if query != "":
+    run_query(query)

requirements.txt

@@ -0,0 +1,2 @@
+pinecone-client
+sentence_transformers