Rename clqna.py to demo.py

clqna.py

@@ -1,35 +0,0 @@
-import streamlit as st
-
-from transformers import pipeline
-from pinecone import Pinecone, ServerlessSpec
-from sentence_transformers import SentenceTransformer, util
-
-
-bi_encoder = SentenceTransformer('msmarco-distilbert-base-v4')
-bi_encoder.max_seq_length = 256     # Truncate long documents to 256 tokens
-
-# Store the index as a variable
-INDEX_NAME = 'cl-search-idx'
-NAMESPACE = 'webpages'
-
-index = pc.Index(name=INDEX_NAME)
-
-def query_from_pinecone(index, question_embedding, top_k=3):
-    # get embedding from THE SAME embedder as the documents
-
-    return index.query(
-      vector=question_embedding,
-      top_k=top_k,
-      namespace=NAMESPACE,
-      include_metadata=True   # gets the metadata (dates, text, etc)
-    ).get('matches')
-
-
-QUESTION=st.text_area('Ask a question -e.g How to prepare for Verbal section for CAT?')  ##' How to prepare for Verbal section ?'
-question_embedding = bi_encoder.encode(QUESTION, convert_to_tensor=True)
-resp= query_from_pinecone(question_embedding.tolist(), 3)
-docresult= resp[0]['metadata']['text'] 
-#+ '\n*************\n'+  resp[1]['metadata']['text'] + '\n*************\n'+ resp[2]['metadata']['text']
-
-st.json(out)
-

demo.py

@@ -0,0 +1,11 @@
+import streamlit as st
+import transformers
+from transformers import pipeline
+
+pipe= pipeline('sentiment-analysis')
+
+text = st.text_area('Enter some text')
+
+if text:
+    out= pipe(text)
+    st.json(out)