I have created an index.Json file using Llamaindex. Everything is working great BUT unfortunately, the cost of every query is very expensive!!. I have changed the gpt model : llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.7, model_name=“text-ada-001”, max_tokens=num_outputs))
Cost didnt changed. How can I reduce costs querying local index file ?