embeddings-from-first-principles examples on Programmer.ie: Modern AI programming

The same cosine means two different things in two spaces

Mon, 01 Jan 0001 00:00:00 +0000

A cosine of 0.4 is a number. What it means depends on the space it was measured in, and the chapter’s claim is that you cannot read a cosine without the geometry of the space it came from. The benchmark here makes that concrete with three seeded spaces that differ in nothing but their shape.

Run it

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/geometry/run.py --check

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/geometry/run.py --check

--check is the important flag: it verifies the run reproduces the frozen artifacts byte-for-byte instead of overwriting them. Python 3.10 or later, NumPy only, no model download, no network.

The nearest neighbour can be wrong, and a readout can be right

Mon, 01 Jan 0001 00:00:00 +0000

The nearest neighbour is a guess made with a metric that was never asked what the relation was. The chapter’s claim is that a supervised readout over the same vectors finds the relation the metric is blind to, and that a benchmark which mines its negatives adversarially is the honest way to see the gap.

Run it

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/hard-negatives/run.py --check

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/hard-negatives/run.py --check

--check verifies the frozen artifacts instead of overwriting them. Python 3.10 or later. No model download, no network.

A threshold calibrated on one domain does not transfer to another

Mon, 01 Jan 0001 00:00:00 +0000

A threshold is a number, and the chapter’s claim is that a number is only meaningful next to the distribution it was chosen on. The benchmark here calibrates on two domains and then reports what a staleness check notices when the inputs move.

Run it

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/calibration/run.py --check

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/calibration/run.py --check

--check verifies the frozen artifacts instead of overwriting them. Python 3.10 or later, NumPy only, no model download, no network.

Turn a delta into an operator, and measure what it costs

Mon, 01 Jan 0001 00:00:00 +0000

A delta between two embeddings is not a transformation. The chapter’s claim is that to act on a difference you need an operator, and that choosing one is a decision with a measurable cost. The benchmark here fits four candidate operators per transformation class and records which one was selected and what each scored.

Run it

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/operators/run.py --check

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python benchmarks/operators/run.py --check

--check verifies the frozen artifacts instead of overwriting them. Python 3.10 or later, NumPy only, no model download, no network.

Walk the whole embedding runtime in one command

Mon, 01 Jan 0001 00:00:00 +0000

The last chapter of the book assembles a runtime rather than a claim. This command walks the whole path: it registers two spaces, compares them natively, fits a bridge, derives a third space, judges the derivation, compresses it, applies an operator and explains the lineage.

Run it

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python -m relate.cli demo

git clone https://github.com/ernanhughes/relate.git
cd relate
git checkout 1de8c95b3995791042d6eb1c150c64c7cdb3492f
python -m venv venv
venv/Scripts/pip install -e ".[dev]"
venv/Scripts/python -m relate.cli demo

Python 3.10 or later, NumPy only. No model download, no network, no service.