GroqBackendAdapter
Defined in: backend/src/providers/groq.ts:58
Backend adapter for Groq API.
Groq uses an OpenAI-compatible API with ultra-fast inference speeds. Known for extremely low latency responses.
Examples
Section titled “Examples”import { GroqBackendAdapter } from 'ai.matey';
const adapter = new GroqBackendAdapter({ apiKey: process.env.GROQ_API_KEY,});const adapter = new GroqBackendAdapter({ apiKey: process.env.GROQ_API_KEY,});
const response = await adapter.execute({ messages: [{ role: 'user', content: 'Hello!' }], parameters: { model: 'llama-3.3-70b-versatile', // Fast and capable },});const stream = adapter.executeStream({ messages: [{ role: 'user', content: 'Tell me a story' }], parameters: { model: 'llama-3.1-8b-instant', // Optimized for speed },});
for await (const chunk of stream) { if (chunk.type === 'content') { console.log(chunk.delta); }}Extends
Section titled “Extends”Implements
Section titled “Implements”Constructors
Section titled “Constructors”Constructor
Section titled “Constructor”new GroqBackendAdapter(
config):GroqBackendAdapter
Defined in: backend/src/providers/groq.ts:62
Parameters
Section titled “Parameters”config
Section titled “config”Returns
Section titled “Returns”GroqBackendAdapter
Overrides
Section titled “Overrides”OpenAIBackendAdapter.constructor
Properties
Section titled “Properties”baseURL
Section titled “baseURL”
protectedreadonlybaseURL:string
Defined in: backend/src/providers/openai.ts:162
Inherited from
Section titled “Inherited from”config
Section titled “config”
protectedreadonlyconfig:BackendAdapterConfig
Defined in: backend/src/providers/openai.ts:161
Inherited from
Section titled “Inherited from”metadata
Section titled “metadata”
readonlymetadata:AdapterMetadata
Defined in: backend/src/providers/openai.ts:160
Adapter metadata for identification and capabilities.
Implementation of
Section titled “Implementation of”Inherited from
Section titled “Inherited from”Methods
Section titled “Methods”estimateCost()
Section titled “estimateCost()”estimateCost(
request):Promise<number|null>
Defined in: backend/src/providers/groq.ts:119
Estimate cost for Groq (very low cost, optimized for speed).
Parameters
Section titled “Parameters”request
Section titled “request”Returns
Section titled “Returns”Promise<number | null>
Implementation of
Section titled “Implementation of”Overrides
Section titled “Overrides”OpenAIBackendAdapter.estimateCost
execute()
Section titled “execute()”execute(
request,signal?):Promise<IRChatResponse>
Defined in: backend/src/providers/openai.ts:221
Execute non-streaming chat completion request.
Parameters
Section titled “Parameters”request
Section titled “request”signal?
Section titled “signal?”AbortSignal
Returns
Section titled “Returns”Promise<IRChatResponse>
Implementation of
Section titled “Implementation of”Inherited from
Section titled “Inherited from”executeStream()
Section titled “executeStream()”executeStream(
request,signal?):IRChatStream
Defined in: backend/src/providers/openai.ts:260
Execute streaming chat completion request.
Parameters
Section titled “Parameters”request
Section titled “request”signal?
Section titled “signal?”AbortSignal
Returns
Section titled “Returns”Implementation of
Section titled “Implementation of”Inherited from
Section titled “Inherited from”OpenAIBackendAdapter.executeStream
fromIR()
Section titled “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
Section titled “Parameters”request
Section titled “request”Returns
Section titled “Returns”Implementation of
Section titled “Implementation of”Inherited from
Section titled “Inherited from”healthCheck()
Section titled “healthCheck()”healthCheck():
Promise<boolean>
Defined in: backend/src/providers/groq.ts:99
Health check for Groq API.
Returns
Section titled “Returns”Promise<boolean>
Implementation of
Section titled “Implementation of”Overrides
Section titled “Overrides”OpenAIBackendAdapter.healthCheck
invalidateModelCache()
Section titled “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
Section titled “Returns”This adapter for method chaining
Inherited from
Section titled “Inherited from”OpenAIBackendAdapter.invalidateModelCache
listModels()
Section titled “listModels()”listModels(
options?):Promise<ListModelsResult>
Defined in: backend/src/providers/openai.ts:501
List available models from OpenAI.
This method supports three sources:
- Static config (config.models) - highest priority
- Cache (if enabled and not expired)
- Remote API (/v1/models endpoint)
Parameters
Section titled “Parameters”options?
Section titled “options?”Returns
Section titled “Returns”Promise<ListModelsResult>
Implementation of
Section titled “Implementation of”Inherited from
Section titled “Inherited from”OpenAIBackendAdapter.listModels
toIR()
Section titled “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
Section titled “Parameters”response
Section titled “response”originalRequest
Section titled “originalRequest”latencyMs
Section titled “latencyMs”number