Update app.py

app.py

@@ -536,67 +536,112 @@ def remove_incomplete_sentence(text):
     return text
 
 
+import traceback
+
 language_code = 1
 query_text = "recipes and meals for vegan diabetes headache fatigue"
 print(f"Generated query text: {query_text}")
 
-# Generate the query embedding
-query_embedding = embed_query_text(query_text)
-if query_embedding is None:
-    raise ValueError("Failed to generate query embedding.")
-
-# Load embeddings and retrieve initial results
-embeddings_data = load_recipes_embeddings()
-folder_path = 'downloaded_articles/downloaded_articles'
-initial_results = query_recipes_embeddings(query_embedding, embeddings_data, n_results=10)
-if not initial_results:
-    raise ValueError("No relevant recipes found.")
-print(initial_results)
-# Extract document IDs
-document_ids = [doc_id for doc_id, _ in initial_results]
-print(document_ids)
-# Retrieve document texts
-document_texts = retrieve_rec_texts(document_ids, folder_path)
-if not document_texts:
-    raise ValueError("Failed to retrieve document texts.")
-print(document_texts)
-# Load recipe metadata from DataFrame
-folder_path='downloaded_articles/downloaded_articles'
-file_path = 'recipes_metadata.xlsx'
-metadata_path = 'recipes_metadata.xlsx'
-metadata_df = pd.read_excel(file_path)
-relevant_portions = extract_relevant_portions(document_texts, query_text, max_portions=3, portion_size=1, min_query_words=1)
-print(relevant_portions)
-flattened_relevant_portions = []
-for doc_id, portions in relevant_portions.items():
-    flattened_relevant_portions.extend(portions)
-unique_selected_parts = remove_duplicates(flattened_relevant_portions)
-print(unique_selected_parts)
-combined_parts = " ".join(unique_selected_parts)
-print(combined_parts)
-context = [query_text] + unique_selected_parts
-print(context)
-entities = extract_entities(query_text)
-print(entities)
-passage = enhance_passage_with_entities(combined_parts, entities)
-print(passage)
-prompt = create_prompt(query_text, passage)
-print(prompt)
-answer = generate_answer(prompt)
-print(answer)
-answer_part = answer.split("Answer:")[-1].strip()
-print(answer_part)
-cleaned_answer = remove_answer_prefix(answer_part)
-print(cleaned_answer)
-final_answer = remove_incomplete_sentence(cleaned_answer)
-print(final_answer )
-if language_code == 0:
-    final_answer = translate_en_to_ar(final_answer)
-if final_answer:
-    print("Answer:")
-    print(final_answer)
-else:
-    print("Sorry, I can't help with that.")
+try:
+    # Generate the query embedding
+    print("Generating query embedding...")
+    query_embedding = embed_query_text(query_text)
+    if query_embedding is None:
+        raise ValueError("Failed to generate query embedding.")
+    print(f"Query embedding generated: {query_embedding}")
+
+    # Load embeddings and retrieve initial results
+    print("Loading recipe embeddings...")
+    embeddings_data = load_recipes_embeddings()
+    print("Embeddings loaded. Retrieving initial results...")
+    initial_results = query_recipes_embeddings(query_embedding, embeddings_data, n_results=10)
+    if not initial_results:
+        raise ValueError("No relevant recipes found.")
+    print(f"Initial results: {initial_results}")
+
+    # Extract document IDs
+    document_ids = [doc_id for doc_id, _ in initial_results]
+    print(f"Document IDs: {document_ids}")
+
+    # Retrieve document texts
+    folder_path = 'downloaded_articles/downloaded_articles'
+    print("Retrieving document texts...")
+    document_texts = retrieve_rec_texts(document_ids, folder_path)
+    if not document_texts:
+        raise ValueError("Failed to retrieve document texts.")
+    print(f"Document texts retrieved: {document_texts}")
+
+    # Load recipe metadata from DataFrame
+    file_path = 'recipes_metadata.xlsx'
+    print("Loading metadata from Excel...")
+    metadata_df = pd.read_excel(file_path)
+    print(f"Metadata loaded: {metadata_df.head()}")
+
+    # Extract relevant portions
+    print("Extracting relevant portions...")
+    relevant_portions = extract_relevant_portions(
+        document_texts, query_text, max_portions=3, portion_size=1, min_query_words=1
+    )
+    print(f"Relevant portions: {relevant_portions}")
+
+    # Flatten portions
+    print("Flattening relevant portions...")
+    flattened_relevant_portions = []
+    for doc_id, portions in relevant_portions.items():
+        flattened_relevant_portions.extend(portions)
+    unique_selected_parts = remove_duplicates(flattened_relevant_portions)
+    print(f"Unique selected parts: {unique_selected_parts}")
+
+    # Combine parts into a single context
+    combined_parts = " ".join(unique_selected_parts)
+    print(f"Combined parts: {combined_parts}")
+    context = [query_text] + unique_selected_parts
+    print(f"Context: {context}")
+
+    # Extract entities
+    print("Extracting entities...")
+    entities = extract_entities(query_text)
+    print(f"Entities: {entities}")
+
+    # Enhance passage with entities
+    print("Enhancing passage with entities...")
+    passage = enhance_passage_with_entities(combined_parts, entities)
+    print(f"Enhanced passage: {passage}")
+
+    # Create the prompt
+    print("Creating prompt...")
+    prompt = create_prompt(query_text, passage)
+    print(f"Prompt: {prompt}")
+
+    # Generate the answer
+    print("Generating answer...")
+    answer = generate_answer(prompt)
+    print(f"Answer: {answer}")
+    answer_part = answer.split("Answer:")[-1].strip()
+    print(f"Answer part: {answer_part}")
+
+    # Clean and finalize the answer
+    print("Cleaning answer...")
+    cleaned_answer = remove_answer_prefix(answer_part)
+    print(f"Cleaned answer: {cleaned_answer}")
+    final_answer = remove_incomplete_sentence(cleaned_answer)
+    print(f"Final answer: {final_answer}")
+
+    # Translate if needed
+    if language_code == 0:
+        print("Translating answer to Arabic...")
+        final_answer = translate_en_to_ar(final_answer)
+
+    # Display the answer
+    if final_answer:
+        print("Final Answer:")
+        print(final_answer)
+    else:
+        print("Sorry, I can't help with that.")
+except Exception as e:
+    print("An error occurred:")
+    print(traceback.format_exc())
+