About Yandex Foundation Models
Yandex Foundation Models is at the Preview stage.
Yandex Foundation Models comprises several large generative neural networks and allows you to leverage their capabilities for your business development.
The YandexGPT neural network is geared to address various needs related to creating text content. YandexGPT API can generate product descriptions, articles, news stories, newsletters, blog posts, and many other types of texts. The quality of the neural network's response depends directly on the accuracy of the instructions you provide. With a more specific request, you are more likely to get the result you expect.
Foundation Models provides the API to work with embeddings, i.e., vector representations of text. It can be used to classify information, compare and match texts, or search through a knowledge base of your own. For more information on embeddings and the Embeddings API, see Text vectorization.
The YandexART neural network will help you create detailed and realistic images based on a text request. You can see request examples in YandexART prompt library.
Foundation Models provides the API to work with embeddings, i.e., vector representations of text. It can be used to classify information, compare and match texts, or search through a knowledge base of your own. For more information on embeddings and the Embeddings API, see Text vectorization.
The YandexART neural network will help you create detailed and realistic images based on a text request. You can see request examples in YandexART prompt library.
The service is dynamically evolving with constant enhancements and refinements to its functionality.
For information on Foundation Models restrictions, refer to Quotas and limits in Yandex Foundation Models.
Foundation Models working modes
In Foundation Models, you can use models in either synchronous or asynchronous mode. In synchronous mode, the model will process your request and respond to it directly upon receipt. You may opt for this mode if you need to maintain a chatbot dialog. In asynchronous mode, the model will receive your request and return its ID, which you can later use to get your response. In asynchronous mode, the result usually takes longer to generate, but the responses are cheaper and better quality. Use asynchronous mode if you do not need an urgent response.
Different models support different operating modes.
Generative models are managed using prompts. A good prompt should contain the context of your request to the model (instruction) and the actual task the model should complete based on the provided context. The more specific your prompt, the more accurate will be the results returned by the model.
Apart from the prompt, other request parameters will impact the model's output too. Use Foundation Models Playground in the management console