For the given query including a meal description, calculate the amount of carbohydrates in grams. If the serving size of any item in the
meal is not specified, assume it is a single standard serving based on common nutritional guidelines (e.g., USDA).
Respond with a dictionary object containing the total carbohydrates in grams as follows:
{{"total_carbohydrates": total grams of carbohydrates for the serving}}
For the total carbohydrates, respond with just the numeric amount of carbohydrates without extra text. If you don't know the answer,
respond with:
{{"total_carbohydrates": -1}}.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // app.tsx — LLM Response Annotation Tool | |
| // bun run app.tsx | |
| const html = `<!DOCTYPE html> | |
| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8" /> | |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> | |
| <title>Annotate</title> | |
| <link href="https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;500;600&family=IBM+Plex+Sans:wght@400;500;600&display=swap" rel="stylesheet" /> |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # /// script | |
| # dependencies = [ | |
| # "sentence-transformers", | |
| # "torch", | |
| # "scikit-learn", | |
| # "numpy<2", | |
| # "polars[pyarrow]", | |
| # "pyarrow", | |
| # "huggingface_hub", | |
| # ] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # /// script | |
| # dependencies = [ | |
| # "sentence-transformers", | |
| # "torch", | |
| # "scikit-learn", | |
| # "numpy<2", | |
| # "polars[pyarrow]", | |
| # "pyarrow", | |
| # "huggingface_hub", | |
| # ] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # /// script | |
| # dependencies = [ | |
| # "sentence-transformers", | |
| # "torch", | |
| # "scikit-learn", | |
| # "numpy<2", | |
| # "polars[pyarrow]", | |
| # "pyarrow", | |
| # "huggingface_hub", | |
| # ] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # /// script | |
| # requires-python = ">=3.11" | |
| # dependencies = ["httpx"] | |
| # /// | |
| """Lookup a GND person record via lobid.org and return enriched info (VIAF, coordinates, etc). | |
| Usage: | |
| uv run scripts/lookup_gnd.py <gnd_id> | |
| uv run scripts/lookup_gnd.py 110952928 |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # requires-python = ">=3.13" | |
| # /// script | |
| # dependencies = [ | |
| # "pydantic", | |
| # "feedparser", | |
| # "tqdm", | |
| # "litellm", | |
| # ] | |
| # /// |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # /// script | |
| # dependencies = [ | |
| # "transformers", | |
| # "torch", | |
| # "accelerate", | |
| # "matplotlib", | |
| # ] | |
| # /// | |
| # Notes: Mostly stolen from https://github.com/open-thought/tiny-grpo | |
| # Run with uv run gpt_grpo.py |
- Most things by Jason Liu are great
- Arcturus labs has some good writing on the topic
- Simon Willison's entries are always worth a skim/read
- LLM Engineer's handbook from Paul Iusztin and Maxime Labonne
- I'm currently reading relevant search
- Handling vision in RAG
- This talk by Ben Clavié
- Most of these talks from Parlance labs
- Evaluate rag with RAGAS
- This blog post by Goku Mohandas
NewerOlder