AI Assistant API
The AI Assistant API feature is at the Preview stage.
AI Assistant API is a tool for creating AI assistants. These personalized assistants are proficient with generative response scenarios that adapt based on external information (known as retrieval augmented generation, or RAG), along with maintaining the query context.
Create your AI assistant using Yandex Cloud ML SDK or by means of API requests in a programming language.
Assistant components
AI Assistant API offers a number of abstractions for building a custom chatbot or AI assistant.
Assistant determines which model to use and what parameters and instructions to apply. This enables you to configure the model just once and use those settings in the future without needing to provide them every time.
Threads are used to maintain the historical context of user communication. Each user chat makes an individual thread. By running your assistant for a specific thread, you call the model and provide it with all the context stored in the thread. Listen the current run for intermediate generation results; the final response, once generated, will become part of the thread.
Tip
By default, each time the model starts running, it will reprocess the content of the thread. If a thread holds some large context and you start the assistant after each user message, running it can grow rather expensive. To optimize costs, consider limiting the size of the context to provide: set the customPromptTruncationOptions parameter when starting your assistant.
For detailed costs of running an assistant, see Assistant pricing policy.
Handling external information sources
To enable your model to leverage external information sources for answering queries, upload supplementary files through the Files API and create an associated search index. You can upload up to 1,000 files, with maximum size of 128 MB per file. A single file can be included in multiple search indexes at the same time. Currently, a search index can include up to 100 files.
For all AI Assistant API limitations, see Quotas and limits in Yandex Foundation Models.
The upload feature supports the following MIME types:
application/jsonapplication/mswordapplication/pdfapplication/vnd.ms-excelapplication/vnd.ms-excel.sheet.2application/vnd.ms-excel.sheet.3application/vnd.ms-excel.sheet.4application/vnd.ms-excel.workspace.3application/vnd.ms-excel.workspace.4application/vnd.ms-outlookapplication/vnd.ms-powerpointapplication/vnd.ms-projectapplication/vnd.ms-word2006mlapplication/vnd.openxmlformats-officedocument.spreadsheetml.sheetapplication/vnd.openxmlformats-officedocument.wordprocessingml.documentapplication/x-latexapplication/x-ms-ownerapplication/xhtml+xmltext/csvtext/htmltext/markdowntext/plaintext/xmlapplication/rtf
Note
All uploaded files and search indexes are subject to expiration. When uploading a file, use the ExpirationConfig parameter to configure the expiration period. By default, a file not used for seven days is deleted.
When you create a search index, you define the type of search it will support, with options for both full-text and vector searches. The indexing speed can vary based on the file types, their sizes, and the system load, taking from a few seconds to several hours. Files are indexed asynchronously. When requested to create a search index, the service will return an Operation object. You can use that object to check the status of the index creation operation.
Once a search index is created, you can configure an assistant to utilize it. In this case, the model will consider the contents of that search index and will primarily use information from it to generate responses.