Update app.py

app.py

@@ -3,6 +3,7 @@ import PyPDF2
 import openai
 import faiss
 import os
+import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
@@ -21,7 +22,7 @@ def get_embeddings(text, model="text-embedding-ada-002"):
 
 # Function to search for similar content
 def search_similar(query_embedding, index, stored_texts, top_k=3):
-    distances, indices = index.search([query_embedding], top_k)
+    distances, indices = index.search(np.array([query_embedding]), top_k)
     results = [(stored_texts[i], distances[0][idx]) for idx, i in enumerate(indices[0])]
     return results
 
@@ -55,9 +56,12 @@ if openai_api_key:
         # Generate embeddings for all chunks
         embeddings = [get_embeddings(chunk) for chunk in chunks]
 
+        # Convert the list of embeddings into a NumPy array (shape: [num_chunks, embedding_size])
+        embeddings_np = np.array(embeddings).astype("float32")
+
         # Create a FAISS index for similarity search
-        index = faiss.IndexFlatL2(len(embeddings[0]))
-        index.add(embeddings)
+        index = faiss.IndexFlatL2(len(embeddings_np[0]))  # Use the length of the embedding vectors for the dimension
+        index.add(embeddings_np)
 
         st.write("Course materials have been processed and indexed.")