![]() ![]() Imitate someone’s writing style to generate emails – Use Azure OpenAI GPT3.5 with few shot learning to imitate someone’s writing style. User’s Question to JSON - create a prompt to extract entities by turning a user’s question into a JSON object that can be used to search in a Database.įood orders – speech to text to JSON – get a food order, use Azure AI Speech SDK to transform speech to text and then use Azure OpenAI GPT3.5 to extract a JSON object that represents the order and can be used to search in a Database. Few-shot learning can help improve the accuracy of the model’s responses and make it more versatile. ![]() This can be useful when working with limited data or when trying to train the model for a specific task. This technique involves training the model on a small number of examples rather than a large dataset. To avoid this, it is important to create exact prompts that provide the AI with clear instructions on what to generate.ĭue to the way the instruction-following models are trained or the data they are trained on, there are specific prompt formats that work particularly well and align better with the tasks at hand. Best practices for prompt engineering with OpenAI API include using the latest model for best results, putting instructions at the beginning of the prompt and using # or """ to separate the instruction and context, being specific, descriptive and as detailed as possible about the desired context, outcome, length, format, style, etc., articulating the desired output format through examples starting with zero-shot, then few-shot.įew-shot learning is another important aspect of using OpenAI. However, if the prompt is not specific enough, the AI may generate irrelevant or even harmful responses. Prompts are used to provide the AI with the context it needs to generate a response. Most of us know that one of the secrets of getting the results we need with LLMs is creating effective prompts. Let’s start from the beginning – The prompts I have created a public GitHub repository with many examples that showcase all of the above and I will explain each one of the examples and what it solves and how.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |