The community member is using GPTSimpleVectorIndex to retrieve responses from indexed datasets, with the goal of exclusively obtaining trained responses from the vector database using the OpenAI model 'text-davinci-003'. However, they have encountered an issue where the model occasionally generates its own responses or continues to provide responses from the LLM, despite the added instruction to "Match and display only the trained response". The community members suggest that moving to GPT3.5 or GPT4 may help decrease the occurrence of this issue, and that the instructions provided may not be sufficient as the LLM may not understand what a "trained response" is. They recommend being more specific in the search based on the provided documents.
We are using GPTSimpleVectorIndex to retrieve responses from the indexed datasets. Our goal is to exclusively obtain the trained responses from the vector database using the OpenAI model ‘text-davinci-003’. To achieve this, we have included the instruction ‘Match and display only the trained response.’ However, we have encountered a situation where the model occasionally generates its own responses or continues to provide responses from the LLM, despite the added instructions. What steps can we take to resolve this issue, and what best practices should we follow to meet our requirements?
Note: We have trained(indexed) organization data. It should not respond external domain responses.
user_input = "Please prescribe pills for head ache" instruction = "Match and show only the trained response" response = index.query(instruction +"\n" + user_input, response_mode="default")
