Comments (1)
Successful test on structured parsing with romanian language:
Parse the ingredient lists in JSON format.
[INGREDIENTS] Potato, vegetable oils (corn, sunflower, rapeseed in varying proportions), seasoning with chicken with spices flavour [maltodextrin, salt, flavourings (contain onion powder, garlic powder, chicken meat powder 0,03%), sugar, spices (paprika powder 0,3%, cayenne pepper powder 0,06%, black pepper), potassium chloride, herbs (parsley 0,06%, thyme 0,06%, basil 0,03%), acid (citric acid), colour (paprika extract)]
[RESULT] [{"text":"Potato"},{"ingredients":[{"text":"corn"},{"text":"sunflower"},{"text":"rapeseed in varying proportions"}],"text":"vegetable oils"},{"ingredients":[{"text":"maltodextrin"},{"text":"salt"},{"ingredients":[{"text":"contain onion"},{"text":"garlic powder"},{"text":"chicken meat"}],"text":"flavourings"},{"text":"sugar"},{"ingredients":[{"percent":0.3,"text":"paprika powder"},{"percent":0.06,"processing":"en:powder","text":"cayenne pepper"},{"text":"black pepper"}],"text":"spices"},{"text":"potassium chloride"},{"ingredients":[{"percent":0.06,"text":"parsley"},{"percent":0.06,"text":"thyme"},{"percent":0.03,"text":"basil"}],"text":"herbs"},{"ingredients":[{"text":"citric acid"}],"text":"acid"},{"ingredients":[{"text":"paprika extract"}],"text":"colour"}],"text":"seasoning with chicken with spices flavour"}]
[INGREDIENTS] Cartofi, uleiuri vegetale (porumb, floarea soarelui, rapiță, în proporţii variabile), mix de ingrediente cu gust de pui cu mirodenii [maltodextrină, sare, arome (conțin ceapă pudră, usturoi pudră, carne de pui pudră 0,03%), zahăr, condimente (paprica pudră 0,3%), ardei cayenne pudră 0,06%, piper negru), clorură de potasiu, plante aromatice (pătrunjel 0,06%, cimbru 0,06%, busuioc 0,03%), acidifiant (citric acid), colorant (extract de ardei roşu)].
[RESULTS]
ChatGPT (3.5) result:
[
{
"text": "Cartofi"
},
{
"ingredients": [
{
"text": "porumb"
},
{
"text": "floarea soarelui"
},
{
"text": "rapiță"
},
{
"text": "în proporţii variabile"
}
],
"text": "uleiuri vegetale"
},
{
"ingredients": [
{
"text": "maltodextrină"
},
{
"text": "sare"
},
{
"ingredients": [
{
"text": "conțin ceapă pudră"
},
{
"text": "usturoi pudră"
},
{
"percent": 0.03,
"text": "carne de pui pudră"
}
],
"text": "arome"
},
{
"text": "zahăr"
},
{
"ingredients": [
{
"percent": 0.3,
"text": "paprica pudră"
},
{
"percent": 0.06,
"processing": "en:powder",
"text": "ardei cayenne"
},
{
"text": "piper negru"
}
],
"text": "condimente"
},
{
"text": "clorură de potasiu"
},
{
"ingredients": [
{
"percent": 0.06,
"text": "pătrunjel"
},
{
"percent": 0.06,
"text": "cimbru"
},
{
"percent": 0.03,
"text": "busuioc"
}
],
"text": "plante aromatice"
},
{
"ingredients": [
{
"text": "citric acid"
}
],
"text": "acidifiant"
},
{
"ingredients": [
{
"text": "extract de ardei roşu"
}
],
"text": "colorant"
}
],
"text": "mix de ingrediente cu gust de pui cu mirodenii"
}
]
from openfoodfacts-ai.
Related Issues (20)
- Use LLMs to create properly formatted taxonomy entries
- Use LLMs to find subcategories for taxonomies
- Use LLMs to create data models for Open Products Facts categories
- Use LLMs to spellcheck/lowercase ingredient lists HOT 1
- Use LLMs to retrieve properties on ingredients/additives
- Use LLMs to generate tweets based on specific categories / tags…
- Use LLMs to generate tweets based on specific categories / tags…
- Use LLMs in Odoo Connect
- Use LLMs in Odoo Connect
- Use LLMs to summarise long texts about Quality Schemes
- Use LLMs to parse a natural language complex meal into foods with nutritional values for nutrition/environment tracking
- Use LLMs to retrieve food wine pairings
- Recognize Nutrition tables using multimodal models (GPT4) HOT 4
- Turbocharge the mobile app using LLMs and Multimodal models
- Use LLMs to extract ingredient lists from raw text HOT 3
- Improve image resolution
- Predict an image crop of nutrition tables HOT 1
- Use LLMs to detect origin of ingredients
- Extract nutrients data from US products nutrients table photos
- Use large language models (LLM) to perform ingredient list spellcheck
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openfoodfacts-ai.