mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-01 21:00:48 +08:00
5e31b06a7d
## [1.14.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v1.13.3...v1.14.0) (2024-08-20) ### Features * add async call ([f60aa3a](f60aa3acde)) * add integration for new module of gpt4o ([982150e](982150e81f)) * Add new feature to support gpt-4o variant models with different pricing ([8551448](855144876d)) * add refactoring of default temperature ([6c3b37a](6c3b37ab00)) * add structured output format ([7d2fc67](7d2fc672c8)) * **GenerateAnswerNode:** built-in structured output through LangChain ([d29338b](d29338b7c2)) * Implemented a filter logic in search_link_node.py ([08e9d9d](08e9d9d6a0)) * refactoring of the code ([5eb3cff](5eb3cff64f)) * update abstract graph ([c77231c](c77231c983)) * update model tokens dict ([0aca287](0aca28732b)) ### Bug Fixes * broken node ([1272273](1272273499)) * browser-base integration ([1d7f30b](1d7f30b65b)) * **models_tokens:** incorrect provider names ([cb6b353](cb6b35397e)) * **ParseNode:** leave room for LLM reply in context window ([683bf57](683bf57d89)) * merge_anwser prompt import ([f17cef9](f17cef94bb)) * model count ([faef318](faef3186f7)) * **AbstractGraph:** pass kwargs to Ernie and Nvidia models ([e6bedb6](e6bedb6701)) * **SearchNode:** prompt ([052f7d5](052f7d5e66)) ### chore * **examples:** add vertex examples, rename genai examples ([1aa9c6e](1aa9c6e73b)) * **examples:** fix import bug in image2text demo ([71438a1](71438a1e86)) * **examples:** update provider names to match tokens dictionary ([ee078cb](ee078cb102)) * **requirements:** update requirements.txt ([7fe181f](7fe181f69b)) ### CI * **release:** 1.13.0-beta.8 [skip ci] ([b470d97](b470d974cf)) * **release:** 1.13.0-beta.9 [skip ci] ([d4c1a1c](d4c1a1c58a)) * **release:** 1.14.0-beta.1 [skip ci] ([40043f3](40043f376e)) * **release:** 1.14.0-beta.10 [skip ci] ([6a08cc8](6a08cc8a43)) * **release:** 1.14.0-beta.11 [skip ci] ([d617750](d61775090a)) * **release:** 1.14.0-beta.12 [skip ci] ([fec3582](fec358253b)) * **release:** 1.14.0-beta.13 [skip ci] ([f4dbe5b](f4dbe5b841)) * **release:** 1.14.0-beta.2 [skip ci] ([7fd921b](7fd921b990)) * **release:** 1.14.0-beta.3 [skip ci] ([3bf9c3c](3bf9c3c9e6)) * **release:** 1.14.0-beta.4 [skip ci] ([7af1e45](7af1e45565)) * **release:** 1.14.0-beta.5 [skip ci] ([db3494d](db3494d377)) * **release:** 1.14.0-beta.6 [skip ci] ([6730797](6730797008)) * **release:** 1.14.0-beta.7 [skip ci] ([a6fcc1e](a6fcc1ea58)) * **release:** 1.14.0-beta.8 [skip ci] ([d639a9e](d639a9e9cc)) * **release:** 1.14.0-beta.9 [skip ci] ([2053693](2053693eba))
100 lines
2.5 KiB
TOML
100 lines
2.5 KiB
TOML
[project]
|
|
name = "scrapegraphai"
|
|
|
|
|
|
version = "1.14.0"
|
|
|
|
|
|
description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
|
|
|
|
authors = [
|
|
{ name = "Marco Vinciguerra", email = "mvincig11@gmail.com" },
|
|
{ name = "Marco Perini", email = "perinim.98@gmail.com" },
|
|
{ name = "Lorenzo Padoan", email = "lorenzo.padoan977@gmail.com" }
|
|
]
|
|
|
|
dependencies = [
|
|
"langchain>=0.2.14",
|
|
"langchain-fireworks>=0.1.3",
|
|
"langchain_community>=0.2.9",
|
|
"langchain-google-genai>=1.0.7",
|
|
"langchain-google-vertexai>=1.0.7",
|
|
"langchain-openai>=0.1.22",
|
|
"langchain-groq>=0.1.3",
|
|
"langchain-aws>=0.1.3",
|
|
"langchain-anthropic>=0.1.11",
|
|
"langchain-mistralai>=0.1.12",
|
|
"langchain-huggingface>=0.0.3",
|
|
"langchain-nvidia-ai-endpoints>=0.1.6",
|
|
"html2text>=2024.2.26",
|
|
"faiss-cpu>=1.8.0",
|
|
"beautifulsoup4>=4.12.3",
|
|
"pandas>=2.2.2",
|
|
"python-dotenv>=1.0.1",
|
|
"tiktoken>=0.7",
|
|
"tqdm>=4.66.4",
|
|
"graphviz>=0.20.3",
|
|
"minify-html>=0.15.0",
|
|
"free-proxy>=1.1.1",
|
|
"playwright>=1.43.0",
|
|
"google>=3.0.0",
|
|
"undetected-playwright>=0.3.0",
|
|
"semchunk>=1.0.1",
|
|
"browserbase>=0.3.0",
|
|
]
|
|
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
homepage = "https://scrapegraphai.com/"
|
|
repository = "https://github.com/VinciGit00/Scrapegraph-ai"
|
|
documentation = "https://scrapegraph-ai.readthedocs.io/en/latest/"
|
|
keywords = [
|
|
"scrapegraph",
|
|
"scrapegraphai",
|
|
"langchain",
|
|
"ai",
|
|
"artificial intelligence",
|
|
"gpt",
|
|
"machine learning",
|
|
"rag",
|
|
"nlp",
|
|
"natural language processing",
|
|
"openai",
|
|
"scraping",
|
|
"web scraping",
|
|
"web scraping library",
|
|
"web scraping tool",
|
|
"webscraping",
|
|
"graph",
|
|
]
|
|
classifiers = [
|
|
"Intended Audience :: Developers",
|
|
"Topic :: Software Development :: Libraries :: Python Modules",
|
|
"Programming Language :: Python :: 3",
|
|
"Operating System :: OS Independent",
|
|
]
|
|
requires-python = ">=3.9,<4.0"
|
|
|
|
[project.optional-dependencies]
|
|
burr = ["burr[start]==0.22.1"]
|
|
docs = ["sphinx==6.0", "furo==2024.5.6"]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.rye]
|
|
managed = true
|
|
dev-dependencies = [
|
|
"pytest==8.0.0",
|
|
"pytest-mock==3.14.0",
|
|
"-e file:.[burr]",
|
|
"-e file:.[docs]",
|
|
"pylint>=3.2.5",
|
|
]
|
|
|
|
[tool.rye.scripts]
|
|
pylint-local = "pylint scrapegraphai/**/*.py"
|
|
pylint-ci = "pylint --disable=C0114,C0115,C0116 --exit-zero scrapegraphai/**/*.py"
|
|
update-requirements = "python 'manual deployment/autorequirements.py'"
|