# Deployment Diagram of Sherpa AI Server with Robots

<figure><img src="https://3237142148-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FscP4BXwl9ufpJr5mfVln%2Fuploads%2Fgit-blob-c39dfef27e963cac0a12abd9ba720d9858b6f908%2F2025-04-10_14-36-15.png?alt=media" alt=""><figcaption></figcaption></figure>

You can download it in good quality here:

The extension of the deployment scheme of the Sherpa RPA platform describes the use of the Sherpa AI Server component as part of the robotic platform to implement scenarios using artificial intelligence and\
large language models.

All components of Sherpa AI Server are installed locally within the Client's network, without connection to external servers or SaaS services. The deployment of Sherpa AI Server is carried out using a Docker container.

## Solution Composition

1. Web user interface for direct interaction with the large language model
2. Vector-semantic storage
3. Inference server for the large language model
4. Embedding server for the large language model

## Network Configuration

The port configuration and network protocols of Sherpa AI Server can be configured to support all common firewall requirements. HTTPS is used for interaction with the web server, and HTTP is optionally available. When installed using TLS, the client must provide the necessary certificates by placing them in the path /opt/app/config/certs/, renaming them to aiserver.crt and aiserver.key.

## Authentication Mechanisms

Web user authentication in Sherpa AI Server is performed using a username and password. Authentication of external applications, including robots of the Sherpa RPA platform, is performed using an API token.


---

# 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/sherpa-ai/sherpa-ai-server/diagramma-razvertyvaniya-sherpa-ai-server-v-svyazke-s-robotami.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.