Gateway Class
The main class for interacting with LLMs through the Adaline Gateway.
Constructor
import { Gateway } from "@adaline/gateway";
const gateway = new Gateway({
cache: myCache, // optional: pluggable cache backend
httpClient: myClient, // optional: custom HTTP client
logger: myLogger, // optional: custom logger
});
Parameters
Optional configuration for plugins.
A pluggable cache backend implementing the Cache interface.
A custom HTTP client implementing the HttpClient interface.
A custom logger implementing the Logger interface.
Methods
completeChat
Non-streaming chat completion. Sends messages to an LLM and returns the full response.
const response = await gateway.completeChat({
model: gpt4o,
config: Config().parse({ temperature: 0.7, maxTokens: 500 }),
messages: [
{ role: "system", content: [{ modality: "text", value: "You are a helpful assistant." }] },
{ role: "user", content: [{ modality: "text", value: "Explain quantum computing." }] },
],
tools: [],
});
request
GatewayCompleteChatRequestType
required
The model instance from a provider (e.g., openai.chatModel({ modelName: "gpt-4o" })).
Model configuration parsed via Config().parse({...}). See Config Type. Array of tool definitions (can be empty). See Tool Types. CompleteChatHandlerResponseType
streamChat
Streaming chat completion. Returns an async generator that yields response chunks.
for await (const chunk of gateway.streamChat({
model: gpt4o,
config: Config().parse({ temperature: 0.7, maxTokens: 500 }),
messages: [
{ role: "user", content: [{ modality: "text", value: "Write a poem." }] },
],
tools: [],
})) {
process.stdout.write(chunk.response);
}
request
GatewayStreamChatRequestType
required
Same shape as completeChat request. See above.
AsyncGenerator<StreamChatHandlerResponseType>
getEmbeddings
Generate embeddings for text or other modalities.
const embeddings = await gateway.getEmbeddings({
model: textEmbedding3Large,
config: Config().parse({ encodingFormat: "float", dimensions: 256 }),
embeddingRequests: {
modality: "text",
requests: ["Hello world", "How are you?"],
},
});
request
GatewayGetEmbeddingsRequestType
required
The embedding model instance from a provider.
Embedding model configuration.
embeddingRequests
EmbeddingRequestType
required
The input data to embed.
GetEmbeddingsHandlerResponseType
Execute tool calls returned by an LLM.
const toolResponses = await gateway.getToolResponses({
tools: myToolDefinitions,
toolCalls: response.toolCalls,
});
request
GatewayGetToolResponsesRequestType
required
The tool definitions that match the tool calls.
Tool calls returned from a chat completion response.
GetToolResponsesHandlerResponseType
getChatUsageCost (static)
Calculate the cost of a chat completion based on token usage.
const cost = Gateway.getChatUsageCost({
model: gpt4o,
usage: response.usage,
});
GetChatUsageCostHandlerResponseType
