CultriX commited on
Commit
20a0e89
·
1 Parent(s): d7a506c

feat: Overhaul WebUI, add PDF/Text export, use Poetry in Docker

Browse files
Files changed (2) hide show
  1. poetry.lock +0 -0
  2. pyproject.toml +25 -26
poetry.lock CHANGED
The diff for this file is too large to render. See raw diff
 
pyproject.toml CHANGED
@@ -1,31 +1,30 @@
1
- [tool.poetry]
2
- name = "RAGScraper"
3
- version = "11.5.2023"
4
- description = "RAGScraper is a Python library designed for efficient and intelligent scraping of web documentation and content. Tailored for Retrieval-Augmented Generation systems, RAGScraper extracts and preprocesses text into structured, machine-learning-ready formats. It emphasizes precision, context preservation, and ease of integration with RAG models, making it an ideal tool for developers looking to enhance AI-driven applications with rich, web-sourced knowledge."
5
- authors = ["kdcokenny <kenny@elapse.ai>"]
6
- license = "MIT"
 
 
7
  readme = "README.md"
8
- packages = [{include = "rag_scraper"}]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
 
10
- [tool.poetry.dependencies]
11
- python = "^3.10"
12
- requests = "^2.31.0"
13
- beautifulsoup4 = "^4.12.2"
14
- html2text = "^2020.1.16"
15
- markdown-pdf = "^1.7"
16
-
17
- [tool.poetry.group.dev]
18
- optional = true
19
-
20
- [tool.poetry.group.dev.dependencies]
21
- rich = "^13.6.0"
22
- black = "^23.10.1"
23
- flake8 = "^6.1.0"
24
- ruff = "^0.1.4"
25
- isort = "^5.12.0"
26
- pyright = "^1.1.334"
27
- pytest = "^7.4.3"
28
 
29
  [build-system]
30
- requires = ["poetry-core"]
31
  build-backend = "poetry.core.masonry.api"
 
1
+ [project]
2
+ name = "rag-scraper"
3
+ version = "0.1.0"
4
+ description = "RAG-Scraper HuggingFace Space"
5
+ authors = [
6
+ {name = "CultriX",email = "cultrix@tempmail.j78.org"}
7
+ ]
8
+ license = {text = "mit"}
9
  readme = "README.md"
10
+ requires-python = ">=3.10,<4.0"
11
+ dependencies = [
12
+ "gradio (>=5.31.0,<6.0.0)",
13
+ "ruff (>=0.11.11,<0.12.0)",
14
+ "requests (>=2.32.3,<3.0.0)",
15
+ "beautifulsoup4 (>=4.13.4,<5.0.0)",
16
+ "html2text (>=2025.4.15,<2026.0.0)",
17
+ "markdown-pdf (>=1.7,<2.0)",
18
+ "rich (>=14.0.0,<15.0.0)",
19
+ "black (>=25.1.0,<26.0.0)",
20
+ "flake8 (>=7.2.0,<8.0.0)",
21
+ "isort (>=6.0.1,<7.0.0)",
22
+ "pyright (>=1.1.401,<2.0.0)",
23
+ "pytest (>=8.3.5,<9.0.0)",
24
+ "poetry-core (>=2.1.3,<3.0.0)"
25
+ ]
26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
 
28
  [build-system]
29
+ requires = ["poetry-core>=2.0.0,<3.0.0"]
30
  build-backend = "poetry.core.masonry.api"