> ## Documentation Index
> Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Image metadata enrichment use case
> In the image metadata enrichment use case, the LLM ingests a text containing either a base64-encoded image or a public HTTP/HTTPS or Google Cloud Storage (`gs://`) image link and routes the image to a multimodal model. A JSON response is returned that contains an `imageMetadata` dictionary with a list of keywords, subcategories, and keyword synonyms.
The POST request obtains and indexes prediction information related to the specified use case, and returns a unique `predictionId` and `status` of the request. The `predictionId` can be used later in the GET request to retrieve the results.
## OpenAPI
````yaml /api-reference/saas/machine-learning-platform-async-prediction.json post /ai/async-prediction/image-metadata-enrichment/{MODEL_ID}
openapi: 3.0.1
info:
title: Lucidworks AI Async Prediction API
version: v0
description: >-
The Lucidworks AI Async Prediction API contains two requests:
* POST Request: This request is used to submit a prediction task for a
specific `useCase` and `modelId`. Upon submission, the API responds with the
following information:
* `predictionId` that is a unique UUID for the submitted prediction task, and can be used later to retrieve the results.
* `status` that indicates the current state of the prediction task.
* GET Request: This request is used to retrieve the results of a
previously-submitted prediction request. You must provide the unique
`predictionId` received from the POST request. The API then returns the
results of the prediction request associated with that `predictionId`.
The Use Case API returns a list of all supported models.
The `async-prediction` endpoints require an authentication token with scope
`machinelearning.predict`.
contact:
name: Lucidworks
url: https://lucidworks.com/
email: support@lucidworks.com
termsOfService: https://lucidworks.com/legal/developer-license-agreement/
license:
name: Lucidworks
url: https://lucidworks.com/legal/developer-license-agreement/
servers:
- url: https://APPLICATION_ID.applications.lucidworks.com
description: Production
security: []
tags:
- name: Create predictions
description: Submit prediction tasks to Lucidworks AI.
- name: Fetch predictions
description: Get the results of a prediction task from Lucidworks AI.
paths:
/ai/async-prediction/image-metadata-enrichment/{MODEL_ID}:
parameters:
- schema:
type: string
name: MODEL_ID
in: path
required: true
description: >-
Unique identifier for the model. Must be a multimodal model capable of
processing images, such as `gemini-2.5-flash-lite`.
example: gemini-2.5-flash-lite
post:
tags:
- Create predictions
summary: Image metadata enrichment use case
description: >-
In the image metadata enrichment use case, the LLM ingests a text
containing either a base64-encoded image or a public HTTP/HTTPS or
Google Cloud Storage (`gs://`) image link and routes the image to a
multimodal model. A JSON response is returned that contains an
`imageMetadata` dictionary with a list of keywords, subcategories, and
keyword synonyms.
The POST request obtains and indexes prediction information related to
the specified use case, and returns a unique `predictionId` and `status`
of the request. The `predictionId` can be used later in the GET request
to retrieve the results.
operationId: post-ai-async-prediction-image-metadata-enrichment-modelId
parameters:
- in: header
name: Authorization
schema:
type: string
required: true
description: >-
Bearer token used for authentication. Format: `Authorization: Bearer
ACCESS_TOKEN`.
example: Bearer abc123def456
- schema:
type: string
example: application/json
in: header
name: Content-Type
description: application/json
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ImageMetadataEnrichmentRequest'
example:
batch:
- imageLink: https://i.postimg.cc/T3Gggmrx/blushing-happymushroom.png
useCaseConfig:
title: blushing-happy-mushroom
categories:
- fungi
- cute
- jubilant
- embarrassed
maxKeywords: 3
maxSynonyms: 2
maxSubcategories: 2
locale: en-US
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/POSTresponse'
example:
predictionId: a1b2c3d4-e5f6-7890-abcd-ef1234567890
status: SUBMITTED
4XX:
$ref: '#/components/responses/Error'
components:
schemas:
ImageMetadataEnrichmentRequest:
title: ImageMetadataEnrichmentRequest
type: object
required:
- batch
properties:
batch:
type: array
description: >-
An array of request items. Each item must contain exactly one of
`text`, `image`, or `imageLink`.
items:
type: object
properties:
text:
type: string
description: >-
Freeform content that contains either a base64-encoded image
or an image link. The value is parsed to the correct field
automatically. Use this field when passing image data from
Fusion.
image:
type: string
description: >-
A base64-encoded string of the image. If included, `imageLink`
may not be included.
imageLink:
type: string
description: >-
A public HTTP/HTTPS or Google Cloud Storage (`gs://`) image
URL. If included, `image` may not be included.
example: https://example.com/product-image.png
useCaseConfig:
$ref: '#/components/schemas/UseCaseConfigImageMetadataEnrichment'
modelConfig:
$ref: '#/components/schemas/ModelConfig'
POSTresponse:
title: POST response
type: object
description: >-
This is the response to the POST prediction request submitted for a
specific `useCase` and `modelId`.
properties:
predictionId:
type: string
format: uuid
description: >-
The universal unique identifier (UUID) returned in the POST request.
This UUID is required in the GET request to retrieve results.
status:
type: string
example: SUBMITTED
description: >-
The current status of the prediction. Allowed values are:
* SUBMITTED - The POST request was successful and the response has
returned the `predictionId` and `status` that is used by the GET
request.
* ERROR - An error was generated when the GET request was sent.
* READY - The results associated with the `predictionId` are
available and ready to be retrieved.
* RETRIEVED - The results associated with the `predictionId` are
returned successfully when the GET request was sent.
UseCaseConfigImageMetadataEnrichment:
title: UseCaseConfigImageMetadataEnrichment
type: object
description: >-
Optional object to control metadata generation. The image must be
provided in the `batch` item as `useCaseConfig` only tunes the output.
properties:
title:
type: string
description: >-
The title of the image or other details to include for the generated
metadata items.
example: blushing-happy-mushroom
categories:
type: array
description: >-
The current categories for the item. Used as the basis for the
subcategories generated.
items:
type: string
example:
- fungi
- cute
- jubilant
maxKeywords:
type: integer
description: The maximum number of keywords the model generates.
default: 15
example: 3
maxSubcategories:
type: integer
description: The maximum number of subcategories the model generates.
default: 5
example: 2
maxSynonyms:
type: integer
description: The maximum number of synonyms the model generates per keyword.
default: 5
example: 2
locale:
type: string
description: The locale used when generating targeted vernacular.
default: en-US
example: en-US
ModelConfig:
title: ModelConfig
type: object
description: >-
Provides fields and values that specify ranges for tokens. Fields used
for specific use cases and models are specified. The default values are
used if other values are not specified.
properties:
temperature:
type: number
format: float
example: 0.8
minimum: 0
maximum: 2
description: >-
A sampling temperature between 0 and 2. A higher sampling
temperature such as 0.8, results in more random (creative) output. A
lower value such as 0.2 results in more focused (conservative)
output. A lower value does not guarantee the model returns the same
response for the same input. We recommend staying at or below a
temperature of 1.0. Values above 1.0 might return nonsense unless
the topP value is lowered to be more deterministic.
topP:
type: number
format: float
example: 1
minimum: 1
maximum: 1
description: >-
A floating-point number that controls the cumulative probability of
the top tokens to consider. Required range is [0, 1]. Set topP to 1
to consider all tokens.
topK:
type: integer
example: -1
description: >-
An integer that controls the number of top tokens to consider. Set
topK to -1 to consider all tokens.
presencePenalty:
type: number
format: float
minimum: -2
maximum: 2
description: >-
A floating-point number that penalizes new tokens based on whether
they have already appeared in the text. Required range is [-2, 2]. A
value greater than zero (0) encourages the model to use new tokens.
A value less than zero (0) encourages the model to repeat existing
tokens. This is applicable for all OpenAI and Llama models.
example: 2
frequencyPenalty:
type: number
format: float
minimum: -2
maximum: 2
example: 1
description: >-
A floating-point number that penalizes new tokens based on their
frequency in the generated text. Required range is [-2, 2]. A value
greater than zero (0) encourages the model to use new tokens. A
value less than zero (0) encourages the model to repeat existing
tokens. This is applicable for all OpenAI and Llama models.
maxTokens:
type: integer
format: int32
example: 1
description: The maximum number of tokens to generate per output sequence.
apiKey:
type: string
description: >-
This optional parameter is only required when using the model for
prediction. You can find this value in your model's settings:
* **OpenAI**: Copy and paste the API key found in your
organization's settings. For more information, see OpenAI
Authentication API keys.
* **Azure OpenAI**: Copy and paste the API key found in your Azure
portal. See Authenticate
with API key.
* **Anthropic**: Copy and paste the API key found in your Anthropic
console or by using the Anthropic
API.
* **Google Vertex AI**: Copy and paste the base64-encoded service
account key JSON found in your Google
Cloud console. This service account key must have the Vertex
AI user role enabled. For more information, see generate
service account key.
example: API key specific to use case and model
azureDeployment:
type: string
description: >-
This optional parameter is the name of the deployed Azure OpenAI
model and is only required when a deployed Azure OpenAI model is
used for prediction.
example: DEPLOYMENT_NAME
azureEndpoint:
type: string
description: >-
This optional parameter is the URL endpoint of the deployed Azure
OpenAI model and is only required when a deployed Azure OpenAI model
is used for prediction.
example: https://azure.endpoint.com
googleProjectId:
type: string
example: '[GOOGLE_PROJECT_ID]'
description: >-
This parameter is optional, and is only required when a Google
Vertex AI model is used for prediction.
googleRegion:
type: string
description: >-
This parameter is optional, and is only required when a Google
Vertex AI model is used for prediction. A value of `global` routes
the query to any available region. Other possible region values are:
* us-central1
* us-west4
* northamerica-northeast1
* us-east4
* us-west1
* asia-northeast3
* asia-southeast1
* asia-northeast
example: '[GOOGLE_PROJECT_REGION_OF_MODEL_ACCESS]'
predictionId:
title: predictionId
type: string
description: >-
The universal unique identifier (UUID) returned in the POST request.
This UUID is required in the GET request to retrieve results.
format: uuid
example: fd110486-f168-47c0-a419-1518a4840589
status:
title: status
type: string
description: >-
The current status of the prediction. Allowed values are:
* `SUBMITTED` - The POST request was successful and the response has
returned the `predictionId` and `status` that is used by the GET
request.
* `READY` - The results associated with the `predictionId` are available
and ready to be retrieved.
* `ERROR` - An error was generated when the GET request was sent.
* `RETRIEVED` - The results associated with the `predictionId` are
returned successfully when the GET request was sent.
example: READY
responses:
Error:
description: >-
The error varies based on the issue encountered regarding the
`predictionId` or related information.
content:
application/json:
schema:
type: object
properties:
predictionId:
$ref: '#/components/schemas/predictionId'
status:
$ref: '#/components/schemas/status'
message:
type: string
description: >-
The error generated if the `predictionId` cannot be located or
the related information cannot be retrieved. For example,
"System prompt exceeded the maximum number of allowed input
tokens."
````