Use Robotoff to prefill some nutrition fields

[alexfauquette]

What

• The ML server robotoff can extract some information from nutrition texts (not a lot)

Here is the PR that introduced it first time. All the useful information can be found here

• feat: (API) Integrate Robotoff API to pre-populate the nutrition game openfoodfacts-hungergames#403

Part of

• Nutrition Game (Tracker) #70

[raphael0202]

The nutrient extraction model was deployed and integrated to Robotoff. For every new image, we run the model on it and generate a prediction. An insight is generated if in the extracted nutrient values, at least one value is not present in the current nutrients.

To get the insights:

GET https://robotoff.openfoodfacts.org/api/v1/insights?insight_types=nutrient_extraction&order_by=popularity

There are currently no ordering on this endpoint, but I plan to add a order_by={random,popularity} option. Added and deployed

Nutrient values are in insight.data. It contains:

• entities: a subset of the extracted entities at different processing steps (raw, aggregated, postprocessed). We only have postprocessed here, it's more useful as debug information. We can ignore this field here.
• nutrients: a dictionary mapping nutrient name to a dict containing:
  • value: the value to add, without the unit
  • unit: the unit (can be g, mg, µg or null). If it's null, it's because we couldn't extract it from the image (either it's missing, the model was wrong or the OCR result was not good enough). In such case I think we can safely use the "default" unit, which depends on the nutrient (as it's done on Product Opener).
  • score: the entity score. Maybe not really relevant here, as this score is not calibrated (most values are > 0.98).
  • char_start, char_end: start and end character offsets in the original text
  • start, end: start and end word offset in the original text

[teolemon]

@alexfauquette @raphael0202 since we now have the Nutrition prediction route, I'm bumping this one to P0 (let's be a bit dramatic ;)

[teolemon]

Also, here's another route pour single barcode insights: openfoodfacts/openfoodfacts-server#10950