llm-interpolate
LLM plugin for interpolating between embeddings
Installation
Install this plugin in the same environment as LLM.
llm install llm-interpolate
Usage
The plugin adds a new command, llm interpolate. This command takes the name of an
embedding collection
and two ids from that collection that will act as start and end points.
First, populate a collection. In this case we are embedding a song library using the CLAP model.
llm embed-multi -m clap songs --files mysongs "*.wav"
Now we can interpolate between those song embeddings with five intermediate points:
llm interpolate songs "MyRapSong.wav" "MyContrySong.wav" -n 5
You can use the -d option to use a different embeddings database.
What this will do is try and find points in the embedding space in-between the given points.
The output should look something like this (truncated):
[
"MyRapSong.wav",
"HipHopMeetsCountry.wav",
"SmoothCountryRap.wav",
"CountryVibes.wav",
"MyCountrySong.wav"
]
This output can then be used to build a cohesive playlist using only a starting and ending song.
llm interpolate songs "MyRapSong.wav" "MyContrySong.wav" -n 5 | jq .[] > playlist.m3u
Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
cd llm-interpolate
python3 -m venv venv
source venv/bin/activate
Now install the dependencies and test dependencies:
pip install -e '.[test]'
To run the tests:
pytest
Metadata
Release files for llm-interpolate 0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llm_interpolate-0.1.tar.gz | 7.8 kB | Without provenance | Details for llm_interpolate-0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_interpolate-0.1-py3-none-any.whl | Python 3 | none | any | Details for llm_interpolate-0.1-py3-none-any.whl |
Total release size: 15.6 kB
Release files / llm_interpolate-0.1.tar.gz
| Download URL | llm_interpolate-0.1.tar.gz |
|---|---|
| Size | 7.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
66afa94cb47ed8a802aa69a80e9bb856feeccd51a71eeeff0b6b4d90252fb591
|
|
BLAKE2b-256 checksum How to use checksums |
d1247bab499ad0566871c7a6ca2ba857a95a3dbd8572de2071846a8699a6fc29
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
Release files / llm_interpolate-0.1-py3-none-any.whl
| Download URL | llm_interpolate-0.1-py3-none-any.whl |
|---|---|
| Size | 7.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
660927154908fec5d1505c963bb68738184022c5e31254e59b2d3f71bc1bca95
|
|
BLAKE2b-256 checksum How to use checksums |
748c0af55208e2c51625482a9b8c8af012a991c089112ddfd8251a2a725697b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.9
|
Security for llm-interpolate 0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.