LocalAI

Run AI models locally with a self-hosted LocalAI instance.

AI and MLCredentials form2 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (2)
ask_localai
custom_api_call
Details

Connect

Auth type: Credentials form (custom_auth). Fill in the fields the provider needs (listed below). They are stored encrypted in the vault.

Field	Type	Description
`baseUrl`required	text	URL of your LocalAI instance (e.g. http://localhost:8080)

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("localai", "ask_localai", {
    "model": "<model>",
    "prompt": "<question>"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("LocalAI answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "localai-ask-localai",
  name: "LocalAI: Ask LocalAI",
  description: "Calls LocalAI when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("localai", {
      "action": "ask_localai",
      "model": "<model>",
      "prompt": "<question>"
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/localai/ask_localai" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"model":"<model>","prompt":"<question>"}}'

Actions

ask_localaiin catalog

Ask LocalAI. Ask LocalAI anything you want!

Input	Type	Description
`model`required	id (picked from your account)	The model which will generate the completion. Some models are suitable for natural language tasks, others specialize in code.
`prompt`required	long text	Question
`temperature`optional	number	Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.
`maxTokens`optional	number	The maximum number of tokens to generate. Requests can use up to 2,048 or 4,096 tokens shared between prompt and completion, don't set the value to maximum and leave some tokens for the input. The ex…
`topP`optional	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top …
`frequencyPenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
`presencePenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the mode's likelihood to talk about new topics.
`roles`optional	JSON	Array of roles to specify more accurate response

custom_api_call

Custom API Call. Make a custom API call to a specific endpoint

Input	Type	Description
`url`required	object (depends on other props)	url
`method`required	one of "GET" \| "POST" \| "PATCH" \| "PUT" \| "DELETE" \| "HEAD"	Method
`headers`required	object	Authorization headers are injected automatically from your connection.
`queryParams`required	object	Query Parameters
`body_type`optional	one of "none" \| "json" \| "form_data" \| "raw"	Body Type
`body`optional	object (depends on other props)	Body
`response_is_binary`optional	boolean	Enable for files like PDFs, images, etc.
`failsafe`optional	boolean	No Error on Failure
`timeout`optional	number	Timeout (in seconds)
`followRedirects`optional	boolean	Follow redirects

Details

Id: localai
Category: AI and ML
Tags: ai, local, self-hosted, open-source, llm
Package: @activepieces/piece-localai@0.1.5
Tier: Community