dataset-cleaner-cli 0.1.0__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.
- dataset_cleaner_cli-0.1.0/PKG-INFO +10 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/PKG-INFO +10 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/SOURCES.txt +7 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/dependency_links.txt +1 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/entry_points.txt +2 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/requires.txt +4 -0
- dataset_cleaner_cli-0.1.0/dataset_cleaner_cli.egg-info/top_level.txt +1 -0
- dataset_cleaner_cli-0.1.0/pyproject.toml +20 -0
- dataset_cleaner_cli-0.1.0/setup.cfg +4 -0
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: dataset-cleaner-cli
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: An automated pipeline to extract Q&A datasets from documentation.
|
|
5
|
+
Requires-Python: >=3.10
|
|
6
|
+
Description-Content-Type: text/markdown
|
|
7
|
+
Requires-Dist: pymupdf
|
|
8
|
+
Requires-Dist: sentence-transformers
|
|
9
|
+
Requires-Dist: pydantic
|
|
10
|
+
Requires-Dist: ollama
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: dataset-cleaner-cli
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: An automated pipeline to extract Q&A datasets from documentation.
|
|
5
|
+
Requires-Python: >=3.10
|
|
6
|
+
Description-Content-Type: text/markdown
|
|
7
|
+
Requires-Dist: pymupdf
|
|
8
|
+
Requires-Dist: sentence-transformers
|
|
9
|
+
Requires-Dist: pydantic
|
|
10
|
+
Requires-Dist: ollama
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
pyproject.toml
|
|
2
|
+
dataset_cleaner_cli.egg-info/PKG-INFO
|
|
3
|
+
dataset_cleaner_cli.egg-info/SOURCES.txt
|
|
4
|
+
dataset_cleaner_cli.egg-info/dependency_links.txt
|
|
5
|
+
dataset_cleaner_cli.egg-info/entry_points.txt
|
|
6
|
+
dataset_cleaner_cli.egg-info/requires.txt
|
|
7
|
+
dataset_cleaner_cli.egg-info/top_level.txt
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=61.0"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "dataset-cleaner-cli" # Change this to whatever you want your pip install name to be!
|
|
7
|
+
version = "0.1.0"
|
|
8
|
+
description = "An automated pipeline to extract Q&A datasets from documentation."
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
requires-python = ">=3.10"
|
|
11
|
+
dependencies = [
|
|
12
|
+
"pymupdf", # Required for parsing PDFs[cite: 16]
|
|
13
|
+
"sentence-transformers", # Required for semantic similarity[cite: 14]
|
|
14
|
+
"pydantic", # Required for data models[cite: 14]
|
|
15
|
+
"ollama" # Required for LLM extraction[cite: 14]
|
|
16
|
+
]
|
|
17
|
+
|
|
18
|
+
[project.scripts]
|
|
19
|
+
# This creates a terminal command named 'dataset-cleaner' that runs start() in main.py[cite: 15]
|
|
20
|
+
dataset-cleaner = "dataset_cleaner.main:start"
|