Update app.py

app.py

@@ -20,8 +20,21 @@ def retrieve_embedding(user_query):
     headers = {
         "Authorization": f"Bearer {os.getenv('GROQ_API_KEY')}"
     }
+    
+    # Make the API request
     response = requests.post(f"{GROQ_API_URL}/embedding", json=payload, headers=headers)
-    return response.json()["embedding"]
+    
+    # Check for errors and return the embedding if available
+    if response.status_code == 200:
+        json_response = response.json()
+        if "embedding" in json_response:
+            return json_response["embedding"]
+        else:
+            st.error("The response from the API did not contain an embedding. Please check the API.")
+            return None
+    else:
+        st.error(f"Failed to retrieve embedding. Status code: {response.status_code}")
+        return None
 
 # Function to perform response generation using FLAN-T5 via Groq API
 def generate_response(context):
@@ -32,8 +45,21 @@ def generate_response(context):
     headers = {
         "Authorization": f"Bearer {os.getenv('GROQ_API_KEY')}"
     }
+    
+    # Make the API request
     response = requests.post(f"{GROQ_API_URL}/generate", json=payload, headers=headers)
-    return response.json()["text"]
+    
+    # Check for errors and return the response text if available
+    if response.status_code == 200:
+        json_response = response.json()
+        if "text" in json_response:
+            return json_response["text"]
+        else:
+            st.error("The response from the API did not contain a 'text' key.")
+            return None
+    else:
+        st.error(f"Failed to generate response. Status code: {response.status_code}")
+        return None
 
 # Load the counseling conversations dataset
 dataset = load_dataset("Amod/mental_health_counseling_conversations")["train"]
@@ -43,8 +69,9 @@ dataset = load_dataset("Amod/mental_health_counseling_conversations")["train"]
 def embed_dataset(_dataset):
     embeddings = []
     for entry in _dataset:
-        embedding = retrieve_embedding(entry["Response"])
-        embeddings.append(embedding)
+        embedding = retrieve_embedding(entry["response"])
+        if embedding is not None:
+            embeddings.append(embedding)
     return embeddings
 
 dataset_embeddings = embed_dataset(dataset)
@@ -52,12 +79,16 @@ dataset_embeddings = embed_dataset(dataset)
 # Function to retrieve closest responses from the dataset using cosine similarity
 def retrieve_response(user_query, dataset, dataset_embeddings, k=5):
     query_embedding = retrieve_embedding(user_query)
+    if query_embedding is None:
+        st.error("Could not retrieve an embedding for the query.")
+        return []
+    
     cos_scores = cosine_similarity([query_embedding], dataset_embeddings)[0]
     top_indices = np.argsort(cos_scores)[-k:][::-1]
 
     retrieved_responses = []
     for idx in top_indices:
-        retrieved_responses.append(dataset[idx]["Response"])
+        retrieved_responses.append(dataset[idx]["response"])
     return retrieved_responses
 
 # Streamlit app UI
@@ -71,11 +102,17 @@ if user_query:
     # Retrieve similar responses from the dataset
     retrieved_responses = retrieve_response(user_query, dataset, dataset_embeddings)
     
-    # Join retrieved responses to create a supportive context
-    context = " ".join(retrieved_responses)
-    
-    # Generate a supportive response using FLAN-T5 via Groq API
-    supportive_response = generate_response(context)
-    
-    st.write("Here's some advice or support for you:")
-    st.write(supportive_response)
+    if retrieved_responses:
+        # Join retrieved responses to create a supportive context
+        context = " ".join(retrieved_responses)
+        
+        # Generate a supportive response using FLAN-T5 via Groq API
+        supportive_response = generate_response(context)
+        
+        if supportive_response:
+            st.write("Here's some advice or support for you:")
+            st.write(supportive_response)
+        else:
+            st.write("Sorry, I couldn't generate a response at the moment.")
+    else:
+        st.write("Sorry, I couldn't find any relevant responses.")