strapi-plugin-open-ai
strapi-plugin-open-ai copied to clipboard
strapi
The official plugin that allows you to create Open AI completion from a prompt
const response = await fetch(`${strapi .plugin('open-ai') .config('BASE_URL')}/v1/completions`, { method: 'POST', headers: { 'Content-Type': 'application/json', Authorization: `Bearer ${strapi .plugin('open-ai') .config('API_TOKEN')}`, }, body: JSON.stringify({ model, prompt, temperature, max_tokens: maxTokens }), });
The /v1/completions is now legacy, we should use /v1/chat/completions
Hello Please update the library to to use v1/chat/completions instead of v1/completions We are encountering the following error : `{ "error": { "message": "This is a chat model and not...
HI there. I have installed and rebuilt as per docs. I have downloaded latest models and selected gpt-3.5-turbo, temp 1, max tokens 1000. When I try and submit a prompt...
When I click download models: request has been sent to wrong place Dependencies ```json { "dependencies": { "@strapi/plugin-i18n": "4.10.5", "@strapi/plugin-open-ai": "^1.0.1", "@strapi/plugin-users-permissions": "4.10.5", "@strapi/strapi": "4.10.5", "pg": "8.8.0" } } ```...
When "Generate" has been clicked nothing happens. I've set OPEN_AI key on my build and re-build the admin panel. Instructions followed [from here](https://market.strapi.io/plugins/@strapi-plugin-open-ai) https://github.com/strapi/strapi-plugin-open-ai/assets/7689820/9f72c907-375a-4c0a-aa58-6bfef9f699b3
Not a bug, a suggestion. When you make a request to openAi in a content type, sometimes you have to prompt with two different elements: a context and a request....
Open API input correctly. Logs download the model. When we try to generate a completion from a prompt, it gets a 200 response from the Open AI server, but nothing...
