API Usage

Warning

This service is currently in beta phase and is updated regularly. The same applies to the documentation.

The Arcana Manager exposes and api endpoint for you to use. With the api endpoint you can perform all the actions that the frontend Arcana Manager is capable of.

To use the API, you’ll first need an API key, which you can request on our website. This key works across all our services. If you’re already using the LLMs via the api, you can use the same key. Otherwise you can request your key following this documentation.

Info

If you want to chat with an Arcana using the LLM Chat completions API refer to this section in the SAIA-Documentation

Base Route

All Routes for the RAG/Arcana-API start with https://chat-ai.academiccloud.de/v1/arcanas/api/v1/

Note that every api request needs to start with https://chat-ai.academiccloud.de/v1/. Routes that start with https://chat-ai.academiccloud.de/arcanas/ are not compatible with API keys.

See below for a full list of API routes.

API Minimal Example

Here is a minimal working example of how use the API.

curl \
  --url https://chat-ai.academiccloud.de/v1/arcanas/api/v1/ \
  --header 'Accept: application/json' \
  --header 'Authorization: <api_key>'

Response

{
    "message":"Welcome to the SAIA RAG Web API",
    "docs_url":"http://chat-ai.academiccloud.de/arcanas/api/v1/docs"
}

Examples and API Documentation

Get All Your Arcanas

curl \
  --url https://chat-ai.academiccloud.de/v1/arcanas/api/v1/arcana/ \
  --header 'Accept: application/json' \
  --header 'Authorization: <api_key>'

Get a Specific Arcana

curl \
  --url https://chat-ai.academiccloud.de/v1/arcanas/api/v1/arcana/<arcana-name> \
  --header 'Accept: application/json' \
  --header 'Authorization: <api_key>'

Add a new File to your Arcana

Every new file needs to be send in its own request.

curl -i -X POST "https://chat-ai.academiccloud.de/v1/arcanas/api/v1/arcana/<arcana-name>/files/" \
    -H "accept: application/json" \
    -H 'Authorization: <api_key>' \
    -H "Content-Type: multipart/form-data" \
    -F "file=@<filename>"

The response will be null with a status code of 200 if the upload worked

Index an Arcana

Index generation is synchronous i.e. the HTTP request only responds once the index has been created. If the request is canceled, the index generation will finish in the background.

Full List of Routes

The list of all available routes can be found under:

  • In Web-Browser: https://chat-ai.academiccloud.de/arcanas/api/v1/docs
  • Via API: https://chat-ai.academiccloud.de/v1/arcanas/api/v1/openapi.json

Note that the routes are relative i.e. they need to be prefixed with https://chat-ai.academiccloud.de/v1/arcanas/api/v1.