Generate a visual document analysis

This public endpoint handles chat interactions with images, enabling AI-powered visual analysis and conversation. Users can submit queries about specific documents containing images. Parameters:

• query (required): The user’s question or prompt about the image(s). This text will be used to analyze and generate responses about the visual content.
• document_ids (required): List of document IDs containing images to analyze (min: 1, max: 5 documents). These documents must be accessible to the user.
• model (optional): Specific vision-language model to use for analysis. If not provided, the system will use the default configured model.
• private (optional): Specifies whether this chat interaction is private. Response:
• answer: The AI-generated response analyzing the images based on the user’s query. The system will process the specified documents, analyze their visual content in relation to the query, and provide relevant insights and answers.

POST /api/v2/chat/image-analysis

Try it

Generate a visual document analysis

cURL

curl --request POST \
  --url https://paradigm.lighton.ai/api/v2/chat/image-analysis \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "document_ids": [
    "<unknown>"
  ],
  "model": "<string>",
  "private": false
}
'

200

{
  "answer": "<string>"
}

Authorizations

Authorization · string · header · required

Bearer token authentication

Body

Request serializer for chat image analysis.

query · string · required

The user's question or prompt about the image(s) for AI-powered visual analysis

document_ids · any[] · required

List of document IDs containing images to analyze (1-5 documents)

Required array length: 1 - 5 elements

model · string

Specific vision-language model to use for analysis (optional)

private · boolean · default: false

Specifies whether this chat interaction is private

Response

200

application/json

Image analysis output

Response serializer for chat image analysis results.

answer · string · required

The AI-generated response analyzing the images based on the user's query