complete new structure

app.py

@@ -196,6 +196,7 @@ def main():
         json_files_dir=JSON_FILES_DIR,
         table_data_dir=TABLE_DATA_DIR,
         image_data_dir=IMAGE_DATA_DIR,
+        use_json_instead_csv=True,
     )
     
     if query_engine:

index_retriever.py

@@ -6,7 +6,7 @@ from llama_index.core.prompts import PromptTemplate
 from llama_index.retrievers.bm25 import BM25Retriever
 from llama_index.core.retrievers import QueryFusionRetriever
 from my_logging import log_message
-from config import CUSTOM_PROMPT
+from config import CUSTOM_PROMPT, PROMPT_SIMPLE_POISK
 
 def create_vector_index(documents):
     log_message("Строю векторный индекс")
@@ -31,7 +31,7 @@ def create_query_engine(vector_index):
             num_queries=1
         )
         
-        custom_prompt_template = PromptTemplate(CUSTOM_PROMPT)
+        custom_prompt_template = PromptTemplate(PROMPT_SIMPLE_POISK)
         response_synthesizer = get_response_synthesizer(
             response_mode=ResponseMode.TREE_SUMMARIZE,
             text_qa_template=custom_prompt_template

utils.py

@@ -8,6 +8,7 @@ from config import AVAILABLE_MODELS, DEFAULT_MODEL, GOOGLE_API_KEY
 import time
 from index_retriever import rerank_nodes
 from my_logging import log_message
+from utils import PROMPT_SIMPLE_POISK
 
 def get_llm_model(model_name):
     try:
@@ -91,6 +92,7 @@ def answer_question(question, query_engine, reranker, current_model, chunks_df=N
     try:
         log_message(f"Получен вопрос: {question}")
         log_message(f"Используется модель: {current_model}")
+        log_message(f"Используется промпт: {PROMPT_SIMPLE_POISK[:200]}...")
         start_time = time.time()
         
         log_message("Извлекаю релевантные узлы")