# Description of Data Exchange with Yandex Vision Service

The diagram shows the process of data exchange with the Yandex Vision service using the Sherpa RPA platform, which includes sending images and receiving processed data. The entire process is organized as follows:

## Preparing Data for Sending

The RPA robot converts images to base64 format. This format allows for efficient transmission of binary data (images) in text form, simplifying the sending process via the HTTP protocol.

## Sending Data to Yandex Vision

The converted images in base64 format are sent to Yandex Vision over a secure HTTPS protocol. This ensures that the data is transmitted in an encrypted form, providing security and confidentiality of information during transmission.

## Processing Data in Yandex Vision

Yandex Vision receives the images and performs necessary operations such as object recognition, image analysis, and other processing. After processing is complete, Yandex Vision generates a response with the results.

## Receiving Processed Data

The processed data is returned to the RPA robot in JSON format over the same HTTPS protocol.

## Entering Processed Data into the Client's Target System

After receiving the data in JSON format, the RPA robot analyzes the content and enters the processed data into the Client's target system. This may include updating databases, sending notifications, or performing other actions depending on the business logic.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sherparpa.ru/en/bezopasnost/opisanie-obmena-dannymi-s-servisom-yandex-vision.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.