Update app.py

app.py

@@ -38,10 +38,10 @@ def compute_embeddings(text_chunks):
             messages=[{"role": "user", "content": chunk}],
             model="llama3-70b-8192"
         )
-        # Convert response to NumPy array
-        embedding_str = response['choices'][0]['message']['content']
-        embedding = np.fromstring(embedding_str, sep=",")
-        embeddings.append(embedding)
+        # Access the embedding content from the response
+        embedding = response.choices[0].message.content
+        embedding_array = np.fromstring(embedding, sep=",")  # Convert string to NumPy array
+        embeddings.append(embedding_array)
     return np.array(embeddings)
 
 # Function to build FAISS index
@@ -62,7 +62,8 @@ def generate_professional_content_groq(topic):
         messages=[{"role": "user", "content": f"Explain '{topic}' in bullet points, highlighting key concepts, examples, and applications for electrical engineering students."}],
         model="llama3-70b-8192"
     )
-    return response['choices'][0]['message']['content'].strip()
+    # Access content from the response
+    return response.choices[0].message.content.strip()
 
 # Function to compute query embedding using Groq's Llama3-70B-8192 model
 def compute_query_embedding(query):
@@ -70,9 +71,9 @@ def compute_query_embedding(query):
         messages=[{"role": "user", "content": query}],
         model="llama3-70b-8192"
     )
-    # Convert to NumPy array
-    embedding_str = response['choices'][0]['message']['content']
-    return np.fromstring(embedding_str, sep=",").reshape(1, -1)
+    # Access embedding content and convert it to a NumPy array
+    embedding = response.choices[0].message.content
+    return np.fromstring(embedding, sep=",").reshape(1, -1)
 
 # Streamlit app
 st.title("Generative AI for Electrical Engineering Education with FAISS and Groq")