Update app.py

app.py

@@ -115,8 +115,9 @@ class Chatbot():
         print('Calculating embeddings')
         openai.api_key = os.getenv('OPENAI_API_KEY')
         embedding_model = "text-embedding-ada-002"
-        # This is going to create embeddings for subsets of the PDF
-        embeddings = np.vstack(df[df['text'].apply(lambda x: isinstance(x, str))]['text'].apply(lambda x: get_embedding(x, engine=embedding_model)))
+        # Get the embeddings for each text element in the dataframe
+        embeddings = df.text.apply([lambda x: get_embedding(x, engine=embedding_model)])
+        embeddings = np.array(embeddings, dtype=np.float32)
         return embeddings    
 
     def search_embeddings(self, embeddings, df, query, n=3, pprint=True):
@@ -126,6 +127,7 @@ class Chatbot():
             query,
             engine="text-embedding-ada-002"
         )
+        query_embedding = np.array(query_embedding, dtype=np.float32)
         # Step 2. Create a FAISS index and add the embeddings
         d = embeddings.shape[1]
         # Use the L2 distance metric