diff --git a/.changeset/embedding-clustering-rapidfuzz.md b/.changeset/embedding-clustering-rapidfuzz.md new file mode 100644 index 0000000..bab824e --- /dev/null +++ b/.changeset/embedding-clustering-rapidfuzz.md @@ -0,0 +1,6 @@ +--- +'@platforma-open/milaboratories.runenv-python-3.12.10-embedding-clustering': minor +'@platforma-open/milaboratories.runenv-python-3': minor +--- + +Add `rapidfuzz` 3.14.6 to the Embedding Clustering run environment, for string distances such as normalized Levenshtein. It has no required dependencies and is installed with `noDeps`, like the rest of the pinned set. diff --git a/python-3.12.10-embedding-clustering/README.md b/python-3.12.10-embedding-clustering/README.md index a6b1fa1..ef96386 100644 --- a/python-3.12.10-embedding-clustering/README.md +++ b/python-3.12.10-embedding-clustering/README.md @@ -1,4 +1,4 @@ -Python 3.12.10 run environment for the Embedding Clustering block (`embedding-clustering`): `fast_hdbscan` and `pynndescent` on `numba`, plus `scikit-learn` (PCA, medoid distances), `polars` and `pyarrow` (Parquet loading and output) and `pandas`. +Python 3.12.10 run environment for the Embedding Clustering block (`embedding-clustering`): `fast_hdbscan` and `pynndescent` on `numba`, plus `scikit-learn` (PCA, medoid distances), `polars` and `pyarrow` (Parquet loading and output), `pandas` and `rapidfuzz` (string distances such as normalized Levenshtein). The set is pinned flat and matches the block's `requirements.txt`. The block installs it with `pip --no-index --find-links `, so each pin in the block must exist here as a wheel. Change the pins here and in the block together. diff --git a/python-3.12.10-embedding-clustering/config.json b/python-3.12.10-embedding-clustering/config.json index e0de46e..6969fc9 100644 --- a/python-3.12.10-embedding-clustering/config.json +++ b/python-3.12.10-embedding-clustering/config.json @@ -14,7 +14,8 @@ "polars-lts-cpu==1.33.1", "pyarrow==24.0.0", "pynndescent==0.6.0", - "fast_hdbscan==0.3.2" + "fast_hdbscan==0.3.2", + "rapidfuzz==3.14.6" ], "noDeps": [ "numpy", @@ -32,7 +33,8 @@ "numba", "llvmlite", "pynndescent", - "fast_hdbscan" + "fast_hdbscan", + "rapidfuzz" ], "skip": {}, "overrides": {},