Requesty

Requesty

Properties used to connect to Requesty.

requesty

• Type: true | {
       model?: string,
       max_tokens?: number,
       system_prompt?: string,
       tools?: RequestyTool[],
       function_handler?: FunctionHandler
  }
• Default: {model: "openai/gpt-4o"}

Connect to Requesty's Chat Completion API. Requesty is an OpenAI-compatible LLM gateway, so models are referenced using the provider/model naming convention. You can set this property to true or configure it using an object:
model is the name of the model to be used by the API (e.g., "openai/gpt-4o-mini").
max_tokens limits the maximum number of tokens in the generated response.
system_prompt provides behavioral context and instructions to the model.
tools defines available function declarations for the model to call.
function_handler enables function calling capabilities for tool use.

Example

Sample code

<deep-chat
  directConnection='{
    "requesty": {
      "key": "placeholder key",
      "model": "openai/gpt-4o-mini"
    }
  }'
></deep-chat>

Full code

<!-- This example is for Vanilla JS and should be tailored to your framework (see Examples) -->

<deep-chat
  directConnection='{
    "requesty": {
      "key": "placeholder key",
      "model": "openai/gpt-4o-mini"
    }
  }'
  style="border-radius: 8px"
></deep-chat>

info

Use stream to stream the AI responses.

Vision Example

Upload images alongside your text prompts for visual understanding. You must use a model with vision capabilities.

Sample code

<deep-chat
  directConnection='{
    "requesty": {
      "key": "placeholder key",
      "model": "openai/gpt-4o"
    }
  }'
  images="true"
  camera="true"
></deep-chat>

Full code

<!-- This example is for Vanilla JS and should be tailored to your framework (see Examples) -->

<deep-chat
  directConnection='{
    "requesty": {
      "key": "placeholder key",
      "model": "openai/gpt-4o"
    }
  }'
  images="true"
  camera="true"
  style="border-radius: 8px"
  textInput='{"styles": {"container": {"width": "77%"}}}'
></deep-chat>

tip

When sending images we advise you to set maxMessages to 1 to send less data and reduce costs.

Types

Objects used for the requesty property:

RequestyTool

• Type: {type: 'function', function: {name: string, description: string, parameters: object}}

Defines a function that the model is able to call. See the Function calling section for more.

FunctionHandler

• Type: (functionsDetails: FunctionsDetails) => {response: string}[] | {text: string}

The function used to handle the tool calls requested by the model. See tools for the related configuration.