Decode Sensory API

Endpoint

Inputs

• foodText, foodImage or foodVoice
• sensoryOutput for the requested sensory view

Returns

• 202 queued response with job_id and status_url
• Status response with result or error
• Per-food and/or whole-meal sensory interpretation

Request details

• Provide at least one of foodText, foodImage or foodVoice.
• sensoryOutput is optional and must be per_food, whole_meal or per_food_and_whole_meal when provided.
• foodImage and foodVoice must be base64 data URLs; text input is capped for concise meal descriptions.

Response details

• Poll GET /functions/v1/decode_sensory?job_id=... until status is completed or failed.
• The completed result follows the requested sensoryOutput mode.
• Queued or processing jobs return result: null and error: null.

Operational notes

• Requires x-api-key with the edge:decode_sensory scope.
• POST usage is counted and X-Usage-Count is returned.
• Unsupported fields are rejected, so keep request bodies limited to the documented fields.

Examples

{
  "foodText": "Tomato soup with basil and olive oil",
  "sensoryOutput": "per_food_and_whole_meal"
}

{
  "job_id": "49ad2c...",
  "status": "queued",
  "status_url": "https://tirqjzahcinadeulfylj.supabase.co/functions/v1/decode_sensory?job_id=49ad2c..."
}

Code examples

curl -X POST 'https://tirqjzahcinadeulfylj.supabase.co/functions/v1/decode_sensory' \
  -H 'x-api-key: $MYMOLECULES_API_KEY' \
  -H 'Content-Type: application/json' \
  --data '{  "foodText": "Tomato soup with basil and olive oil",  "sensoryOutput": "per_food_and_whole_meal"}'