Update app.py

app.py

@@ -200,29 +200,34 @@ if len(ALL_FILES) > 0:
     # we will use batches of 64
     batch_size = 128
     # docs  = docs['documents']
-    with st.spinner(
-            "🧠    Performing indexing of uplaoded documents... \n "
-        ):
-        for i in range(0, len(docs), batch_size):
-            # find end of batch
-            i_end = min(i+batch_size, len(docs))
-            # extract batch
-            batch = [doc.content for doc in docs[i:i_end]]
-            # generate embeddings for batch
-            emb = sentence_encoder.encode(batch).tolist()
-            # get metadata
-            # meta = [doc.meta for doc in docs[i:i_end]]
-            meta = []
-            for doc in docs[i:i_end]:
-                meta_dict = doc.meta
-                meta_dict["text"] = doc.content
-                meta.append(meta_dict)
-            # create unique IDs
-            ids = [doc.id for doc in docs[i:i_end]]
-            # add all to upsert list
-            to_upsert = list(zip(ids, emb, meta))
-            # upsert/insert these records to pinecone
-            _ = index.upsert(vectors=to_upsert)
+    # with st.spinner(
+    #         "🧠    Performing indexing of uplaoded documents... \n "
+    #     ):
+    my_bar = st.progress(0)
+    upload_count = 0
+    for i in range(0, len(docs), batch_size):
+        # find end of batch
+        i_end = min(i+batch_size, len(docs))
+        # extract batch
+        batch = [doc.content for doc in docs[i:i_end]]
+        # generate embeddings for batch
+        emb = sentence_encoder.encode(batch).tolist()
+        # get metadata
+        # meta = [doc.meta for doc in docs[i:i_end]]
+        meta = []
+        for doc in docs[i:i_end]:
+            meta_dict = doc.meta
+            meta_dict["text"] = doc.content
+            meta.append(meta_dict)
+        # create unique IDs
+        ids = [doc.id for doc in docs[i:i_end]]
+        # add all to upsert list
+        to_upsert = list(zip(ids, emb, meta))
+        # upsert/insert these records to pinecone
+        _ = index.upsert(vectors=to_upsert)
+        upload_count+=batch_size
+        upload_percentage = int((upload_count/len(docs))*100)
+        my_bar.progress(percent_complete + upload_percentage)
     
 top_k_reader = st.sidebar.slider(
     "Max. number of answers",