Upload app.py

app.py

@@ -18,23 +18,6 @@ db_name = 'sample_mflix'
 collection_name = 'embedded_movies'
 collection = client[db_name][collection_name]
 
-## Create a vector search index
-print ('Creating vector search index')
-# collection.create_search_index(model={"definition": {"mappings":{
-#   "dynamic":True,
-#   "fields": {
-#     "plot_embedding": {
-#       "type": "knnVector",
-#       "dimensions": 1536,
-#       "similarity": "euclidean"
-#     }
-#   }
-# }}, "name":'default'})
-
-# sleep for minute
-# print ('Waiting for vector index on field "embedding" to be created')
-# time.sleep(60)
-
 try:
     vector_store = MongoDBAtlasVectorSearch(embedding=OpenAIEmbeddings(), collection=collection, index_name='vector_index', text_key='plot', embedding_key='plot_embedding')
 
@@ -44,9 +27,7 @@ except:
     vector_store = None
 
 def get_movies(message, history):
-    # Use AsyncIO to run the similarity search in the background
-   # movies =  vector_store.similarity_search(message, 3)
-    print ('Searching for: ' + message)
+
     try:
         movies =  vector_store.similarity_search(message, 3)
         retrun_text = ''
@@ -60,7 +41,7 @@ def get_movies(message, history):
         yield "Please clone the repo and add your open ai key as well as your MongoDB Atlas UR in the Secret Section of you Space\n OPENAI_API_KEY (your Open AI key) and MONGODB_ATLAS_CLUSTER_URI (0.0.0.0/0 whitelisted instance with Vector index created) \n\n For more information : https://mongodb.com/products/platform/atlas-vector-search"
     
 
-demo = gr.ChatInterface(get_movies, examples=["What movies are scary?", "Find me a comedy", "Movies for kids"], title="Movies Atlas Vector Search", submit_btn="Search").queue()
+demo = gr.ChatInterface(get_movies, examples=["What movies are scary?", "Find me a comedy", "Movies for kids"], title="Movies Atlas Vector Search",description="This small chat uses a similarity search to find relevant movies, it uses an MongoDB Atlase Vector Search read more here: https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-tutorial" submit_btn="Search").queue()
 
 if __name__ == "__main__":
     demo.launch()