help

app.py

@@ -53,7 +53,9 @@ def preprocess_text(text):
   return cleaned_chunks
 
 # Call the preprocess_text function and store the result in a cleaned_chunks variable
-cleaned_chunks = preprocess_text(slang_text) # Complete this line
+cleaned_slang_chunks = preprocess_text(slang_text) # Complete this line
+cleaned_sejal_chunks = preprocess_text(sejal_text) 
+cleaned_shanvi_chunks = preprocess_text(shanvi_text) 
 
 #STEP 4 FROM SEMANTIC SEARCH
 
@@ -74,13 +76,14 @@ def create_embeddings(text_chunks):
   return chunk_embeddings
 
 # Call the create_embeddings function and store the result in a new chunk_embeddings variable
-chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line
-
+chunk_embeddings_slang_text = create_embeddings(cleaned_slang_chunks)
+chunk_embeddings_sejal_text = create_embeddings(cleaned_sejal_chunks)
+chunk_embeddings_shanvi_text = create_embeddings(cleaned_shanvi_chunks)
 
 #STEP 5 FROM SEMANTIC SEARCH
 
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
-def get_top_chunks(query, chunk_embeddings, text_chunks):
+def get_slang_top_chunks(query, chunk_embeddings, text_chunks):
   # Convert the query text into a vector embedding
   query_embedding = model.encode(query, convert_to_tensor=True) # Complete this line
 
@@ -112,11 +115,13 @@ def get_top_chunks(query, chunk_embeddings, text_chunks):
     top_chunks.append(relevant_chunk)
 
   # Return the list of most relevant chunks
-  return top_chunks
+  return top_slang_chunks
+
+
 
 #STEP 6 FROM SEMANTIC SEARCH
 # Call the get_top_chunks function with the original query
-top_results = get_top_chunks("How does water get into the sky?", chunk_embeddings, cleaned_chunks) # Complete this line
+top_results = get_top_slang_chunks("How does water get into the sky?", chunk_embeddings_slang_text, cleaned_chunks) # Complete this line
 
 # Print the top results
 print(top_results)