Update app.py

app.py

@@ -1,8 +1,11 @@
 import streamlit as st
 import os
 import requests
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+from datasets import load_dataset
 
-# Ensure that the Groq API key is set
+# Groq API key setup
 os.environ["GROQ_API_KEY"] = "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"
 
 # Groq API endpoint
@@ -33,14 +36,13 @@ def generate_response(context):
     return response.json()["text"]
 
 # Load the counseling conversations dataset
-from datasets import load_dataset
 dataset = load_dataset("Amod/mental_health_counseling_conversations")["train"]
 
 # Precompute embeddings for the dataset responses using Groq API
-@st.cache(allow_output_mutation=True)
-def embed_dataset(dataset):
+@st.cache_resource
+def embed_dataset(_dataset):
     embeddings = []
-    for entry in dataset:
+    for entry in _dataset:
         embedding = retrieve_embedding(entry["response"])
         embeddings.append(embedding)
     return embeddings
@@ -48,9 +50,6 @@ def embed_dataset(dataset):
 dataset_embeddings = embed_dataset(dataset)
 
 # Function to retrieve closest responses from the dataset using cosine similarity
-from sklearn.metrics.pairwise import cosine_similarity
-import numpy as np
-
 def retrieve_response(user_query, dataset, dataset_embeddings, k=5):
     query_embedding = retrieve_embedding(user_query)
     cos_scores = cosine_similarity([query_embedding], dataset_embeddings)[0]