Inference
Modalities
Completion API
Just like OpenAI, AnotherAI supports passing images and audio to the completion endpoint.
const response = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [
{
role: "user",
content: [{ type: "image_url", image_url: { url: "https://example.com/image.png" } }]
}
]
});Handling Audio URLs
AnotherAI supports passing audio URLs as opposed to base64 encoded audio data. Simply pass the URL in the data field and the format will be ignored.
const response = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [
{
role: "user",
content: [{ type: "input_audio", input_audio: {
data: "https://example.com/audio.mp3", // just pass a URL in the data field
format: "mp3" // when the data field is a URL, the format is ignored
} }]
}
]
});Usage in templates
As described in the Input Variables section, it is possible to separate static instructions from dynamic data by using Jinja2 variables in the text content of messages.
However it is not currently possible to use input variables to represent image or audio data or URLs. Image and audio payloads should always be passed in the content of messages, in their respective fields.
// ✅ Do: Pass the image URL as a image URL content
const response = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [
{
role: "user",
content: [
{
type: "image_url",
image_url: {
url: "https://example.com/audio.mp3",
},
},
],
},
],
});
// ❌ Don't: Pass the image URL in an input variable
const response = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [
{
role: "user",
// Here the image URL will be treated as a string by the LLM
content: "{{ image_url}}"
},
],
extra_body: {
input: {
variables: {
image_url: "https://example.com/image.png",
},
},
},
});How is this guide?