Hello, I often want the API to send back a response that is something I can parse programmatically. For example, I want it to summarize a passage of text, providing comments, where each comment is a member of a JSON array. It’s frustrating. Something the response will have “JSON:” prepended to i…

Some things you might try: Provide your answer in JSON form. Reply with only the answer in JSON form and include no other commentary: Another thing you might try adding to the very end of your prompt is \n```json to indicate the beginning of a JSON object in markdown format.

Telling the model what to do(prompting) only 60% success rate or poor reliability. Give a few examples of your output style, you improve it to 90%. If you need 100% reliability in achieving JSON output and wish to parse it error-free, use 2 API calls, first one gets the text, and 2nd call formats th…

As mentioned, a few shot example works wonders. Depending on how large and nested your JSON object is, you will continuously run into issues. You would have a better time if you were to train a model, or simplify it with token classification and use that to logically create your object.

@RonaldGRuckus , that is interesting. I could train my own custom model to understand JSON output, and then use that model going forward. Is that possible with the chat endpoint? Seems like it’s not, or not yet: https://platform.openai.com/docs/api-reference/chat/create#chat/create-model What d…

[image] ScottFennell: A pretty common feature of API’s is to be able to specify a response format. It would make things much more usable for developers here. The response is actually in JSON format, it just so happens that the text of the response is a text JSON value, so the completion respo…

[image] EricGT: Have you tried adding a few-shot examples ? For those who may have noticed the earlier link for this was broken, it has now been corrected.

I have had reasonable success with asking ChatGPT to create/improve the questions that you ask it e.g. “Can you modify the question I asked you so that next time I ask it you will…” then, for example “… provide the answer in JSON format”. You can also ask chatGPT to compress the question. Here is an…

I personally found few-shot examples and English description of the schema to be unreliable for my use case. Specifying the schema as a TypeScript interface finally did the trick for me. You can see some examples at ResuLLMe/__init__.py at main · IvanIsCoding/ResuLLMe · GitHub In general, I recomme…

Typescript is the way to go. I also find using zod works really well too because you can validate the outputs at runtime and if there is an error feed it back in and let GPT reflect on it’s mistake. Zod Validation – Nextra Nextra: the next docs builder

Ensure JSON response format

API

ScottFennell March 12, 2023, 1:36pm 11

I think you may be right. I’ve had more consistent luck asking it to respond in a numerical list, with each list item on it’s own line. That’s easy enough to parse into JSON with a little string hackery.

Topic		Replies	Views
Fine tuning models to generate JSON response Prompting codex , chatgpt , fine-tuning , api	6	6426	November 9, 2023
Valid json every time? Prompting	16	12549	March 27, 2023
Prompt integrating JSON, or JSON request after the prompt API chatgpt , api , json	4	21412	May 29, 2023
I want to get json format response which I can pass using gpt-4 model. Also I want to give my prompt to get json data Prompting gpt-4	14	21798	October 26, 2023
Is there any better approach to get a Json from gpt? API gpt-4 , api	6	4876	March 27, 2024

Ensure JSON response format

Related topics