Experiments/GenAI: Difference between revisions
(Created page with "=== From Open Food Facts === === From elsewhere === * [https://artsandculture.google.com/experiment/food-mood/HwHnGalZ3up0EA Google Experiment - Mix 2 cuisines together and cr...") |
|||
(14 intermediate revisions by 2 users not shown) | |||
Line 1: | Line 1: | ||
[https://en.wikipedia.org/wiki/Generative_artificial_intelligence Generative AI] is the field of Artificial intelligence that generates contents (text, images) from prompts or contents. | |||
[[Category:GenAI]] | |||
[[Category:Artificial Intelligence]] | |||
The resulting technologies might have interesting usage for Open Food Facts. | |||
This page list useful resources. | |||
=== From Open Food Facts === | === From Open Food Facts === | ||
=== From elsewhere === | * Describe me here: https://github.com/openfoodfacts/openfoodfacts-ai/issues/289 | ||
* Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1705611584634089 | |||
* Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1702632877529589 | |||
* Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1702322101115109 | |||
* Describe me here: https://openfoodfacts.slack.com/archives/C1UNFJVQV/p1712323105541929 - Henadzi Rabkin I have started fine tuning with LLaVA back then in February, then postponed the project. Here's a link on my colab <nowiki>https://colab.research.google.com/drive/1REw1PdZLg1Wy3MAGORIGVe1qIhxn_V2x?usp=sharing</nowiki> - TIMG: https://openfoodfacts.slack.com/archives/C1UNFJVQV/p1709093097394419 | |||
===From elsewhere=== | |||
==== Food ==== | |||
* [https://artsandculture.google.com/experiment/food-mood/HwHnGalZ3up0EA Google Experiment - Mix 2 cuisines together and create wacky recipes] | * [https://artsandculture.google.com/experiment/food-mood/HwHnGalZ3up0EA Google Experiment - Mix 2 cuisines together and create wacky recipes] | ||
* interesting concept, quite disruptive of Open Food Facts: https://foodanalyze.com/ - no permanent storage, no barcode orientation and the associated HackerNews thread: https://news.ycombinator.com/item?id=41259425 | |||
* https://openfoodfacts.slack.com/archives/C02VDSWHT/p1703301573620989 | |||
* https://engineering.hellofresh.com/recipes-and-generative-ai-6d74a107860c | |||
* OpenAI has deployed image input, and interesting use cases are emerging, https://twitter.com/jackloganjohns/status/1712600735366393912?t=R8PYuJuEPSPi9-s6JYj2mQ&s=19 | |||
* This dataset might be helpful (see "Intended use " section): https://agdatacommons.nal.usda.gov/articles/dataset/SNAPMe_A_Benchmark_Dataset_of_Food_Photos_with_Food_Records_for_Evaluation_of_Computer_Vision_Algorithms_in_the_Context_of_Dietary_Assessment/24856449 | |||
[[File:Open AI demo with Pasta - Be My Eyes.png|thumb]] | |||
* Carrefour playing with virtual avatars and ChatGPT for the Nutri-Score. https://lehub.laposte.fr/repere/chatgpt-carrefour-cree-son-premier-avatar-grace-intelligence-artificielle-generative | |||
* Interesting demo from Google about meal planning: https://youtu.be/XEzRZ35urlk?t=2852 | |||
* Circle to search on food: https://youtu.be/XEzRZ35urlk?t=4814 | |||
* a recap video with a Microwave meal planning on a budget (cc @Raphael Odini) https://youtu.be/XEzRZ35urlk?t=3219 and a Camera troubleshooting (Open Products Facts) | |||
* Climate Q&A chatGPT [[https://huggingface.co/spaces/Ekimetrics/climate-question-answering|https://huggingface.co/spaces/Ekimetrics/climate-question-answering]] [[File:Assistant Memory Peanuts.png|thumb]]Assistants are going to try and remember you are allergic to peanuts. | |||
==== Open Products Facts ==== | |||
* Interesting Demo from Google about troubleshooting a record player: https://youtu.be/XEzRZ35urlk?t=3031 | |||
=== Client side LLMs === | |||
* https://medium.com/@kavinask007/pitfalls-in-trying-to-run-mistral-7b-model-locally-in-browser-using-rust-wasm-4668c129abd0 | |||
* upcoming feature of the next version of Chrome: embedded local LLM: https://huggingface.co/blog/Xenova/run-gemini-nano-in-your-browser | |||
* https://developer.chrome.com/docs/ai | |||
* https://news.ycombinator.com/item?id=40834600 | |||
* 65% of the userbase worldwide will get it, so it might be worth investigating and see if it’s useful enough for spellcheck | |||
=== Opensource multimodal === | |||
* paligemma (opensource multimodal) | |||
* See https://llava.hliu.cc/ 2023 | |||
=== Prompt database === | |||
* Open Food Facts prompt database: https://docs.google.com/spreadsheets/d/1Iq4_vJcPEuCNQa9wa5aX3sES_67q5MJZT9-3E3SX8g4/edit?gid=808139179#gid=808139179 |
Latest revision as of 12:22, 27 August 2024
Generative AI is the field of Artificial intelligence that generates contents (text, images) from prompts or contents. The resulting technologies might have interesting usage for Open Food Facts.
This page list useful resources.
From Open Food Facts
- Describe me here: https://github.com/openfoodfacts/openfoodfacts-ai/issues/289
- Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1705611584634089
- Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1702632877529589
- Describe me here: https://openfoodfacts.slack.com/archives/CF0286BRQ/p1702322101115109
- Describe me here: https://openfoodfacts.slack.com/archives/C1UNFJVQV/p1712323105541929 - Henadzi Rabkin I have started fine tuning with LLaVA back then in February, then postponed the project. Here's a link on my colab https://colab.research.google.com/drive/1REw1PdZLg1Wy3MAGORIGVe1qIhxn_V2x?usp=sharing - TIMG: https://openfoodfacts.slack.com/archives/C1UNFJVQV/p1709093097394419
From elsewhere
Food
- Google Experiment - Mix 2 cuisines together and create wacky recipes
- interesting concept, quite disruptive of Open Food Facts: https://foodanalyze.com/ - no permanent storage, no barcode orientation and the associated HackerNews thread: https://news.ycombinator.com/item?id=41259425
- https://openfoodfacts.slack.com/archives/C02VDSWHT/p1703301573620989
- https://engineering.hellofresh.com/recipes-and-generative-ai-6d74a107860c
- OpenAI has deployed image input, and interesting use cases are emerging, https://twitter.com/jackloganjohns/status/1712600735366393912?t=R8PYuJuEPSPi9-s6JYj2mQ&s=19
- This dataset might be helpful (see "Intended use " section): https://agdatacommons.nal.usda.gov/articles/dataset/SNAPMe_A_Benchmark_Dataset_of_Food_Photos_with_Food_Records_for_Evaluation_of_Computer_Vision_Algorithms_in_the_Context_of_Dietary_Assessment/24856449
- Carrefour playing with virtual avatars and ChatGPT for the Nutri-Score. https://lehub.laposte.fr/repere/chatgpt-carrefour-cree-son-premier-avatar-grace-intelligence-artificielle-generative
- Interesting demo from Google about meal planning: https://youtu.be/XEzRZ35urlk?t=2852
- Circle to search on food: https://youtu.be/XEzRZ35urlk?t=4814
- a recap video with a Microwave meal planning on a budget (cc @Raphael Odini) https://youtu.be/XEzRZ35urlk?t=3219 and a Camera troubleshooting (Open Products Facts)
- Climate Q&A chatGPT [[1]] Assistants are going to try and remember you are allergic to peanuts.
Open Products Facts
- Interesting Demo from Google about troubleshooting a record player: https://youtu.be/XEzRZ35urlk?t=3031
Client side LLMs
- https://medium.com/@kavinask007/pitfalls-in-trying-to-run-mistral-7b-model-locally-in-browser-using-rust-wasm-4668c129abd0
- upcoming feature of the next version of Chrome: embedded local LLM: https://huggingface.co/blog/Xenova/run-gemini-nano-in-your-browser
- https://developer.chrome.com/docs/ai
- https://news.ycombinator.com/item?id=40834600
- 65% of the userbase worldwide will get it, so it might be worth investigating and see if it’s useful enough for spellcheck
Opensource multimodal
- paligemma (opensource multimodal)
- See https://llava.hliu.cc/ 2023
Prompt database
- Open Food Facts prompt database: https://docs.google.com/spreadsheets/d/1Iq4_vJcPEuCNQa9wa5aX3sES_67q5MJZT9-3E3SX8g4/edit?gid=808139179#gid=808139179