Synced repo using 'sync_with_huggingface' Github Action

CHANGELOG.md

@@ -1,5 +1,7 @@
 # Changelog
 
+## [0.1.3] - Unrelease
+
 ## [0.1.2] - 2024-08-19
 - Encode granular features with base64
 - Refactor result format to generic ISCC data model

iscc_sct/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.1.2"
+__version__ = "0.1.3"
 from iscc_sct.options import *
 from iscc_sct.utils import *
 from iscc_sct.code_semantic_text import *

iscc_sct/demo.py

@@ -443,9 +443,8 @@ with gr.Blocks(css=custom_css, theme=iscc_theme) as demo:
     )
 
     with gr.Row(variant="panel"):
-        with gr.Column(variant="panel"):
-            gr.Markdown(
-                """
+        gr.Markdown(
+            """
 ## Understanding ISCC Semantic Text-Codes
 
 ### What is an ISCC Semantic Text-Code?
@@ -476,7 +475,11 @@ document-embedding.
 The similarity shown is calculated by comparing the ISCC codes, not the original texts. This
 allows for efficient and privacy-preserving comparisons, as only the codes need to be shared
 or stored.
+"""
+        )
 
+        gr.Markdown(
+            """
 ### Why is this useful?
 - **Content creators**: Find similar content across languages.
 - **Researchers**: Quickly compare documents or find related texts in different languages.
@@ -490,20 +493,30 @@ language barriers!
 The "Explore Details & Advanced Options" section provides additional tools and information:
 
 1. **ISCC Bit-Length**: Adjust the precision of the ISCC code. Higher values provide more detailed
-   comparisons but may be more sensitive to minor differences.
+comparisons but may be more sensitive to minor differences.
 
 2. **Max Tokens**: Set the maximum number of tokens per chunk. This affects how the text is split
-   for processing.
+for processing.
 
 3. **Chunked Text**: View how each input text is divided into chunks for processing. Each chunk is
-   color-coded and labeled with its size and simprint (a similarity preserving fingerprint).
+color-coded and labeled with its size and simprint (a similarity preserving fingerprint).
 
 4. **Granular Matches**: See a detailed comparison of individual chunks between Text A and Text B.
-   This table shows which specific parts of the texts are most similar, along with their approximate
-   cosine similarity (scaled -100% to +100%).
+This table shows which specific parts of the texts are most similar (above 80%), along with their
+approximate cosine similarity (scaled -100% to +100%).
+
+For more information about the **ISCC** see:
+- https://github.com/iscc
+- https://iscc.codes
+- https://iscc.io
+- [ISO 24138:2024](https://www.iso.org/standard/77899.html)
 """
-            )
-
+        )
+    with gr.Row():
+        gr.Markdown(
+            f"iscc-sct v{sct.__version__} | Source Code: https://github.com/iscc/iscc-sct",
+            elem_classes="footer",
+        )
 
 if __name__ == "__main__":  # pragma: no cover
     demo.launch()

poetry.lock

@@ -755,13 +755,13 @@ files = [
 
 [[package]]
 name = "importlib-metadata"
-version = "8.2.0"
+version = "8.3.0"
 description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "importlib_metadata-8.2.0-py3-none-any.whl", hash = "sha256:11901fa0c2f97919b288679932bb64febaeacf289d18ac84dd68cb2e74213369"},
-    {file = "importlib_metadata-8.2.0.tar.gz", hash = "sha256:72e8d4399996132204f9a16dcc751af254a48f8d1b20b9ff0f98d4a8f901e73d"},
+    {file = "importlib_metadata-8.3.0-py3-none-any.whl", hash = "sha256:42817a4a0be5845d22c6e212db66a94ad261e2318d80b3e0d363894a79df2b67"},
+    {file = "importlib_metadata-8.3.0.tar.gz", hash = "sha256:9c8fa6e8ea0f9516ad5c8db9246a731c948193c7754d3babb0114a05b27dd364"},
 ]
 
 [package.dependencies]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "iscc-sct"
-version = "0.1.2"
+version = "0.1.3"
 description = "ISCC - Semantic Code Text"
 authors = ["Titusz <tp@py7.de>"]
 license = "CC-BY-NC-SA-4.0"

tests/test_iscc_sct.py

@@ -31,7 +31,7 @@ be matched based on lexical similarity.
 
 
 def test_version():
-    assert sct.__version__ == "0.1.2"
+    assert sct.__version__ == "0.1.3"
 
 
 def test_code_text_semantic_default():