CWCloud AI

Purpose

This feature aims to expose AI¹ models such as LLM² to be exposed as a normalized endpoint.

Here's a quick demo of what you can achieve with this API:

Enabling this API

In the SaaS version, you can ask to be granted using the support system.

If you're admin of the instance, you can grant users like this:

UI chat

Once you're enabled, you can try the CWAI api using this chat web UI:

Use the API

Of course, the main purpose is to be able to interact with those adapteurs using very simple http endpoints:

Here's how to get all the available adapters:

curl -X 'GET' 'https://api.cwcloud.tech/v1/ai/adapters' -H 'accept: application/json' -H 'X-Auth-Token: XXXXXX'

Result:

{
  "adapters": [
    "openmistral",
    "mistral",
    "claude3",
    "deepseek",
    "gpt4o",
    "gpt4omini",
    "gemini",
    "log"
  ],
  "status": "ok"
}

Then prompting with one of the available adapters:

curl -X 'POST' \
  'https://api.cwcloud.tech/v1/ai/prompt' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'X-Auth-Token: XXXXXX' \
  -d '{
  "adapter": "gpt4o",
  "message": "Hey",
  "settings": {}
}'

The answer would be:

{
  "response": [
    "Hello! How can I assist you today with cloud automation or deployment using CWCloud?"
  ],
  "status": "ok"
}

Notes:

• you have to replace the XXXXXX value with your own token generated with this procedure.
• you can replace https://api.cwcloud.tech by the API's instance URL you're using, with the CWAI_API_URL environment variable. For the Tunisian customers for example, it would be https://api.cwcloud.tn.
• it's possible to pass multiple prompts associated with roles (system and user) like this:

curl -X 'POST' \
  'https://api.cwcloud.tech/v1/ai/prompt' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'X-Auth-Token: XXXXXX' \
  -d '{
  "adapter": "gpt4o",
  "messages": [
    {
      "role": "system",
      "message": "You're a tech assistant"
    },
    {
      "role": "user",
      "message": "I need help"
    }
  ],
  "settings": {}
}'

Use the CLI

You can use the cwc CLI which provide a subcommand ai:

cwc ai
This command lets you call the CWAI endpoints

Usage:
  cwc ai
  cwc ai [command]

Available Commands:
  adapters    Get the available adapters
  prompt      Send a prompt

Flags:
  -h, --help   help for ai

Use "cwc ai [command] --help" for more information about a command.

List the available adapters

cwc ai adapters
openmistral
mistral
claude3
deepsick
gpt4o
gpt4omini
log

Send a prompt to an available adapter

$ cwc ai prompt
Error: required flag(s) "adapter", "message" not set
Usage:
  cwc ai prompt [flags]
  cwc ai prompt [command]

Available Commands:
  details     Get details about a prompt list
  history     Get prompt history

Flags:
  -a, --adapter string   The chosen adapter
  -h, --help             help for prompt
  -l, --list string      Optional list ID
  -m, --message string   The message input
  -t, --adapter string   The chosen adapter
  -l, --list    string   The list id (optional)
cwc ai prompt --adapter gpt4o --message "Hey"
Status  Response        ListId
ok      Hello! How can I assist you today?      d4248b8e-84d5-40cf-8ca8-b6375fc731ee

View prompt history

cwc ai prompt history
ID                                    Title  Updated At                      Created At
f81f6dc5-e023-4bc9-9f43-5283f0b6d749  hey     2025-03-18T10:33:07.030558     2025-03-18T10:33:07.030543

You can customize it more with the following flags:

cwc ai prompt history --max 10 --start 0 --pretty
+--------------------------------------+-------+----------------------------+----------------------------+
|                  ID                  | TITLE |         UPDATED AT         |         CREATED AT         |
+--------------------------------------+-------+----------------------------+----------------------------+
| d4248b8e-84d5-40cf-8ca8-b6375fc731ee | Hey   | 2025-03-18T14:40:33.439588 | 2025-03-18T14:40:33.439578 |
| 94693bdb-c4bf-48e2-bb6e-385cfe017197 | Hey   | 2025-03-18T14:38:55.739063 | 2025-03-18T14:38:55.739054 |
| f81f6dc5-e023-4bc9-9f43-5283f0b6d749 | hi    | 2025-03-18T10:33:07.030558 | 2025-03-18T10:33:07.030543 |
| 08e99e78-0fe3-45c5-ada7-94c0a3fd0a2c | hello | 2025-03-18T10:16:10.271032 | 2025-03-18T10:16:10.271018 |
+--------------------------------------+-------+----------------------------+----------------------------+

View prompt list details

go run main.go ai prompt details --list f81f6dc5-e023-4bc9-9f43-5283f0b6d749
7a1a0f48-50c9-4cda-b4fc-e06056e73c97    hi      Hello! How can I assist you today?

You can make it more humanly readable with the pretty flag:

cwc ai prompt details --list f81f6dc5-e023-4bc9-9f43-5283f0b6d749 --pretty
Prompt List: hi
ID: f81f6dc5-e023-4bc9-9f43-5283f0b6d749
Created: 2025-03-18T10:33:07.030543
Updated: 2025-03-18T10:33:07.030558

Prompts (1):

--- Prompt 1 ---
ID: 7a1a0f48-50c9-4cda-b4fc-e06056e73c97
Adapter: gpt4o
Created: 2025-03-18T10:33:07.335824
Message: hi
Response: Hello! How can I assist you today?
Usage: 18 tokens (Prompt: 8, Completion: 10)

Using the FaaS engine

You can use the FaaS/low code engine to expose an AI assistant as a service like this:

Then invoke you're FaaS function as usual:

External adapter interface

An external adapter is a microservice which is the interface with your own LLMs you can deploy anywhere you want and CWCloud.

Those LLMs will be useable via the CWAI API, the chat or the serverless engine like those available by default but at your own infrastructure costs (for example you can use cwcloud instances to deploy it).

You external adapter will have to expose an http POST endpoint and be able to take this kind of json payload as body:

{
  "adapter": "test",
  "settings": {
    "max_tokens": 500
  },
  "message": "A prompt",
  "regenerate": false,
  "enable_history": true
}

Or this kind of payload with multiple prompts associated with roles:

{
  "adapter": "test",
  "settings": {
    "max_tokens": 500
  },
  "messages": [
    {
      "role": "system",
      "message": "You're a tech assistant"
    },
    {
      "role": "user",
      "message": "I need help"
    }
  ],
  "regenerate": false,
  "enable_history": true
}

Then it has to be exposed to CWCloud in order to be associated with this interface:

Note: you can configure an http basic authentication or pass custom header including Authorization header.

Footnotes

1. Artificial intelligence ↩

2. Large language model ↩