Analysis Methods - IMG Processing

classify

Classifies an image using a pre-trained model (ResNet50). Returns a list of labels and their probabilities.

classify(imageID: string, options?: RequestOptions): APIPromise<ImageClassifyResponse>;

Show classifyOptions

imageID

string

required

The unique identifier of the image to classify.

Show Examples

const response = await client.images.classify('image_etm0g3x5iap4cld1qcfsjvo2');

extractFormattedText

Extracts text from an image and returns it in plain text or markdown format.

extractFormattedText(imageID: string, body: ImageExtractFormattedTextParams | null | undefined = {}, options?: RequestOptions): APIPromise<ImageExtractFormattedTextResponse>;

Show extractFormattedTextOptions

imageID

string

required

The unique identifier of the image to extract text from.

body

object

The body parameters for extracting formatted text.

Show ImageExtractFormattedTextParams

format

string

The format of the extracted text (markdown or plain). Defaults to plain.

Show Examples

const response = await client.images.extractFormattedText('image_etm0g3x5iap4cld1qcfsjvo2');

visualize

Generates a response based on the content of an image and a text prompt using AI models.

visualize(imageID: string, body: ImageVisualizeParams, options?: RequestOptions): APIPromise<ImageVisualizeResponse>;

Show visualizeOptions

imageID

string

required

The unique identifier of the image to visualize.

body

object

required

The body parameters for visualizing an image.

Show ImageVisualizeParams

prompt

string

required

The prompt for the image.

model

string

The model to use for the visualization (uform-gen, llava, or gemini).

Show Examples

const response = await client.images.visualize('image_etm0g3x5iap4cld1qcfsjvo2', { prompt: 'What is in this image?' });

classify

Classifies an image using a pre-trained model (ResNet50). Returns a list of labels and their probabilities.

classify(imageID: string, options?: RequestOptions): APIPromise<ImageClassifyResponse>;

Show classifyOptions

imageID

string

required

The unique identifier of the image to classify.

Show Examples

const response = await client.images.classify('image_etm0g3x5iap4cld1qcfsjvo2');

extractFormattedText

Extracts text from an image and returns it in plain text or markdown format.

extractFormattedText(imageID: string, body: ImageExtractFormattedTextParams | null | undefined = {}, options?: RequestOptions): APIPromise<ImageExtractFormattedTextResponse>;

Show extractFormattedTextOptions

imageID

string

required

The unique identifier of the image to extract text from.

body

object

The body parameters for extracting formatted text.

Show ImageExtractFormattedTextParams

format

string

The format of the extracted text (markdown or plain). Defaults to plain.

Show Examples

const response = await client.images.extractFormattedText('image_etm0g3x5iap4cld1qcfsjvo2');

visualize

Generates a response based on the content of an image and a text prompt using AI models.

visualize(imageID: string, body: ImageVisualizeParams, options?: RequestOptions): APIPromise<ImageVisualizeResponse>;

Show visualizeOptions

imageID

string

required

The unique identifier of the image to visualize.

body

object

required

The body parameters for visualizing an image.

Show ImageVisualizeParams

prompt

string

required

The prompt for the image.

model

string

The model to use for the visualization (uform-gen, llava, or gemini).

Show Examples

const response = await client.images.visualize('image_etm0g3x5iap4cld1qcfsjvo2', { prompt: 'What is in this image?' });