ebm4subjects 0.4.1__tar.gz → 0.5.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/PKG-INFO +2 -3
- {ebm4subjects-0.4.1/docs/source → ebm4subjects-0.5.0}/README.md +1 -0
- ebm4subjects-0.5.0/ebm-sketch.svg +2315 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/pyproject.toml +1 -6
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/analyzer.py +3 -2
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/chunker.py +25 -20
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/duckdb_client.py +8 -8
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/ebm_logging.py +11 -8
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/ebm_model.py +104 -74
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/.gitignore +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/.python-version +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/LICENSE +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/docs/Makefile +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/docs/make.bat +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0/docs/source}/README.md +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/docs/source/conf.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/docs/source/ebm4subjects.rst +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/docs/source/index.rst +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/__init__.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/embedding_generator.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/src/ebm4subjects/prepare_data.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/tests/__init__.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/tests/data/vocab.ttl +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/tests/test_hello.py +0 -0
- {ebm4subjects-0.4.1 → ebm4subjects-0.5.0}/tests/test_prepare_data.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: ebm4subjects
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.5.0
|
|
4
4
|
Summary: Embedding Based Matching for Automated Subject Indexing
|
|
5
5
|
Author: Deutsche Nationalbibliothek
|
|
6
6
|
Maintainer-email: Clemens Rietdorf <c.rietdorf@dnb.de>, Maximilian Kähler <m.kaehler@dnb.de>
|
|
@@ -13,9 +13,7 @@ Classifier: Operating System :: OS Independent
|
|
|
13
13
|
Classifier: Programming Language :: Python :: 3
|
|
14
14
|
Requires-Python: >=3.10
|
|
15
15
|
Requires-Dist: duckdb>=1.3.0
|
|
16
|
-
Requires-Dist: flash-attn>=2.8.2
|
|
17
16
|
Requires-Dist: nltk~=3.9.1
|
|
18
|
-
Requires-Dist: pandas>=2.3.0
|
|
19
17
|
Requires-Dist: polars>=1.30.0
|
|
20
18
|
Requires-Dist: pyarrow>=21.0.0
|
|
21
19
|
Requires-Dist: pyoxigraph>=0.4.11
|
|
@@ -56,6 +54,7 @@ This design borrows a lot of ideas from lexical matching like Maui [1], Kea [2]
|
|
|
56
54
|
|
|
57
55
|
[2] Frank, E., Paynter, G. W., Witten, I. H., Gutwin, C., & Nevill-Manning, C. G. (1999). Domain-Specific Keyphrase Extraction. Proceedings of the 16 Th International Joint Conference on Artifical Intelligence (IJCAI99), 668–673.
|
|
58
56
|
|
|
57
|
+
|
|
59
58
|
|
|
60
59
|
## Why embedding based matching
|
|
61
60
|
|
|
@@ -30,6 +30,7 @@ This design borrows a lot of ideas from lexical matching like Maui [1], Kea [2]
|
|
|
30
30
|
|
|
31
31
|
[2] Frank, E., Paynter, G. W., Witten, I. H., Gutwin, C., & Nevill-Manning, C. G. (1999). Domain-Specific Keyphrase Extraction. Proceedings of the 16 Th International Joint Conference on Artifical Intelligence (IJCAI99), 668–673.
|
|
32
32
|
|
|
33
|
+
|
|
33
34
|
|
|
34
35
|
## Why embedding based matching
|
|
35
36
|
|