XRequest

Fetch request for LLMs

Import

Source

components/x-request

Docs

Edit this page

When To Use#

Initiate a fetch request to LLMs that comply with OpenAI standards.

Examples#

Request Log

Status -

Update Times 0

Basic

This example illustrates how to use XRequest to initiate a fetch request to LLMs that comply with OpenAI standards. Please copy the code and replace BASE_URL, PATH, MODEL, and API_KEY with actual values in the DEV environment to use it.

      Loading...

Request Log

Status -

Update Times 0

Custom RequestParams

Customize the menu RequestParams, can send request to intelligent agents, etc.

      Loading...

Mock Custom Protocol Log

Custom Transformer

Configure a custom transformStream for XRequest. The following example demonstrates how to handle application/x-ndjson data format.

      Loading...

baseURL: https://api.example.com/chat

model: gpt-3.5-turbo

dangerouslyApiKey: Bearer sk-your-dangerouslyApiKey

Request Log

Status -

Update Times 0

Control XRequestOptions

Control change XRequestOptions，dynamically modify configuration items such as baseURL, model, and API key.

      Loading...

Request Log request null

Status -

Update Times 0

Model Access

Access to cloud service platform, send messages, process data, abort stream.

      Loading...

API#

XRequestOptions#

Property	Description	Type	Default
`baseURL`	Base URL for the API request	`string`	-
`model`	Model name, e.g., `'gpt-3.5-turbo'`	`string`	-
`dangerouslyApiKey`	Note: `dangerouslyApiKey` presents security risks	`string`	-
`fetch`	Optional custom fetch function for making requests	`fetch`	-

XRequestFunction#

type XRequestFunction<Input = Record<PropertyKey, any>, Output = Record<string, string>> = (
  params: XRequestParams & Input,
  callbacks: XRequestCallbacks<Output>,
  transformStream?: XStreamOptions<Output>['transformStream']
) => Promise<void>;

XRequestParams#

Property	Description	Type	Default
`model`	The model to be used for generating responses	`string`	-
`messages`	An array of message objects, each containing a role and content	`Record<PropertyKey, any>[]`	-
`stream`	Indicates whether to use streaming for the response	`boolean`	`false`

XRequestCallbacks#

Property	Description	Type	Default
`onSuccess`	Callback for successful	`(messages: Output[]) => void`	-
`onError`	Callback for error handling	`(error: Error) => void`	-
`onUpdate`	Callback for message updates	`(message: Output) => void`	-
`onStream`	Callback for stream controller	`(controller: AbortController) => void`	-
`transformStream`	Optional transform function for processing stream data	`XStreamOptions<Output>['transformStream']`	-