LMStudioBackendAdapter

Defined in: backend/src/providers/lmstudio.ts:58

Backend adapter for LM Studio local API.

LM Studio provides a local OpenAI-compatible API server for running models on your own hardware. Perfect for privacy, development, and cost savings.

Examples

import { LMStudioBackendAdapter } from 'ai.matey';

const adapter = new LMStudioBackendAdapter({
  baseURL: 'http://localhost:1234/v1', // Default LM Studio port
});

const adapter = new LMStudioBackendAdapter({
  baseURL: 'http://localhost:1234/v1',
});

const response = await adapter.execute({
  messages: [{ role: 'user', content: 'Hello!' }],
  parameters: {
    model: 'local-model', // Use whatever model is loaded in LM Studio
  },
});

import { createBridge } from 'ai.matey';

const bridge = createBridge({
  backend: new LMStudioBackendAdapter({
    baseURL: 'http://localhost:1234/v1',
  }),
});

// All requests stay on your local machine
const response = await bridge.chat({
  messages: [{ role: 'user', content: 'Sensitive data here' }],
});

Extends

• OpenAIBackendAdapter

Implements

• BackendAdapter<OpenAIRequest, OpenAIResponse>

Constructors

Constructor

new LMStudioBackendAdapter(config): LMStudioBackendAdapter

Defined in: backend/src/providers/lmstudio.ts:62

Parameters

config

BackendAdapterConfig

Returns

LMStudioBackendAdapter

Overrides

OpenAIBackendAdapter.constructor

Properties

baseURL

protected readonly baseURL: string

Defined in: backend/src/providers/openai.ts:162

Inherited from

OpenAIBackendAdapter.baseURL

---

config

protected readonly config: BackendAdapterConfig

Defined in: backend/src/providers/openai.ts:161

Inherited from

OpenAIBackendAdapter.config

---

metadata

readonly metadata: AdapterMetadata

Defined in: backend/src/providers/openai.ts:160

Adapter metadata for identification and capabilities.

Implementation of

BackendAdapter.metadata

Inherited from

OpenAIBackendAdapter.metadata

Methods

estimateCost()

estimateCost(_request): Promise<number | null>

Defined in: backend/src/providers/lmstudio.ts:119

Estimate cost for LM Studio (always $0 - local inference).

Parameters

_request

IRChatRequest

Returns

Promise<number | null>

Implementation of

BackendAdapter.estimateCost

Overrides

OpenAIBackendAdapter.estimateCost

---

execute()

execute(request, signal?): Promise<IRChatResponse>

Defined in: backend/src/providers/openai.ts:221

Execute non-streaming chat completion request.

Parameters

request

IRChatRequest

signal?

AbortSignal

Returns

Promise<IRChatResponse>

Implementation of

BackendAdapter.execute

Inherited from

OpenAIBackendAdapter.execute

---

executeStream()

executeStream(request, signal?): IRChatStream

Defined in: backend/src/providers/openai.ts:260

Execute streaming chat completion request.

Parameters

request

IRChatRequest

signal?

AbortSignal

Returns

IRChatStream

Implementation of

BackendAdapter.executeStream

Inherited from

OpenAIBackendAdapter.executeStream

---

fromIR()

fromIR(request): OpenAIRequest

Defined in: backend/src/providers/openai.ts:605

Convert IR request to OpenAI format.

Public method for testing and debugging - see what will be sent to OpenAI.

Parameters

request

IRChatRequest

Returns

OpenAIRequest

Implementation of

BackendAdapter.fromIR

Inherited from

OpenAIBackendAdapter.fromIR

---

healthCheck()

healthCheck(): Promise<boolean>

Defined in: backend/src/providers/lmstudio.ts:100

Health check for LM Studio.

Returns

Promise<boolean>

Implementation of

BackendAdapter.healthCheck

Overrides

OpenAIBackendAdapter.healthCheck

---

invalidateModelCache()

invalidateModelCache(): OpenAIBackendAdapter

Defined in: backend/src/providers/openai.ts:591

Invalidate the cached model list.

Forces the next listModels() call to fetch fresh data from the API (unless static models are configured).

Returns

OpenAIBackendAdapter

This adapter for method chaining

Inherited from

OpenAIBackendAdapter.invalidateModelCache

---

listModels()

listModels(options?): Promise<ListModelsResult>

Defined in: backend/src/providers/openai.ts:501

List available models from OpenAI.

This method supports three sources:

1. Static config (config.models) - highest priority
2. Cache (if enabled and not expired)
3. Remote API (/v1/models endpoint)

Parameters

options?

ListModelsOptions

Returns

Promise<ListModelsResult>

Implementation of

BackendAdapter.listModels

Inherited from

OpenAIBackendAdapter.listModels

---

toIR()

toIR(response, originalRequest, latencyMs): IRChatResponse

Defined in: backend/src/providers/openai.ts:652

Convert OpenAI response to IR format.

Public method for testing and debugging - parse OpenAI responses manually.

Parameters

response

OpenAIResponse

originalRequest

IRChatRequest

latencyMs

number

Returns

IRChatResponse

Implementation of

BackendAdapter.toIR

Inherited from

OpenAIBackendAdapter.toIR