mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-06-26 22:19:57 +00:00
update xgboost and dep scripts for local build on MacOS (#7857)
### What problem does this PR solve? There are two main changes: 1. Update xgboost to 1.6.0 to build the project on MacOS with Apple chips, this change refers to the issue: https://github.com/infiniflow/ragflow/issues/5114. 2. When `use_china_mirrors` is set in `download_deps.py`, the names of chrome files downloaded by the script will be different from the file names used in Dockerfile, so I added the file name in `get_urls` function to solve this problem. I think it's better to add testing for Docker image `infiniflow/ragflow_deps` to the test workflow, but since the workflow is currently running on a self-hosted runner, I'm not sure how to modify it. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [ ] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
This commit is contained in:
He Wang
GitHub
parent
48294e624c
commit
aaefc3f44c
6
.gitignore
vendored
6
.gitignore
vendored
@ -36,6 +36,12 @@ sdk/python/ragflow.egg-info/
|
||||
sdk/python/build/
|
||||
sdk/python/dist/
|
||||
sdk/python/ragflow_sdk.egg-info/
|
||||
|
||||
# Exclude dep files
|
||||
libssl*.deb
|
||||
tika-server*.jar*
|
||||
cl100k_base.tiktoken
|
||||
chrome*
|
||||
huggingface.co/
|
||||
nltk_data/
|
||||
|
||||
|
||||
@ -11,12 +11,13 @@
|
||||
# ///
|
||||
|
||||
from huggingface_hub import snapshot_download
|
||||
from typing import Union
|
||||
import nltk
|
||||
import os
|
||||
import urllib.request
|
||||
import argparse
|
||||
|
||||
def get_urls(use_china_mirrors=False):
|
||||
def get_urls(use_china_mirrors=False) -> Union[str, list[str]]:
|
||||
if use_china_mirrors:
|
||||
return [
|
||||
"http://mirrors.tuna.tsinghua.edu.cn/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb",
|
||||
@ -24,8 +25,8 @@ def get_urls(use_china_mirrors=False):
|
||||
"https://repo.huaweicloud.com/repository/maven/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar",
|
||||
"https://repo.huaweicloud.com/repository/maven/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar.md5",
|
||||
"https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken",
|
||||
"https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chrome-linux64.zip",
|
||||
"https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chromedriver-linux64.zip",
|
||||
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chrome-linux64.zip", "chrome-linux64-121-0-6167-85"],
|
||||
["https://storage.googleapis.com/chrome-for-testing-public/121.0.6167.85/linux64/chromedriver-linux64.zip", "chromedriver-linux64-121-0-6167-85"],
|
||||
]
|
||||
else:
|
||||
return [
|
||||
@ -60,10 +61,11 @@ if __name__ == "__main__":
|
||||
urls = get_urls(args.china_mirrors)
|
||||
|
||||
for url in urls:
|
||||
filename = url.split("/")[-1]
|
||||
print(f"Downloading {url}...")
|
||||
download_url = url[0] if isinstance(url, list) else url
|
||||
filename = url[1] if isinstance(url, list) else url.split("/")[-1]
|
||||
print(f"Downloading {filename} from {download_url}...")
|
||||
if not os.path.exists(filename):
|
||||
urllib.request.urlretrieve(url, filename)
|
||||
urllib.request.urlretrieve(download_url, filename)
|
||||
|
||||
local_dir = os.path.abspath('nltk_data')
|
||||
for data in ['wordnet', 'punkt', 'punkt_tab']:
|
||||
|
||||
@ -106,7 +106,7 @@ dependencies = [
|
||||
"werkzeug==3.0.6",
|
||||
"wikipedia==1.4.0",
|
||||
"word2number==1.1",
|
||||
"xgboost==1.5.0",
|
||||
"xgboost==1.6.0",
|
||||
"xpinyin==0.7.6",
|
||||
"yfinance==0.1.96",
|
||||
"zhipuai==2.0.1",
|
||||
|
||||
15
uv.lock
generated
15
uv.lock
generated
@ -5071,7 +5071,7 @@ requires-dist = [
|
||||
{ name = "werkzeug", specifier = "==3.0.6" },
|
||||
{ name = "wikipedia", specifier = "==1.4.0" },
|
||||
{ name = "word2number", specifier = "==1.1" },
|
||||
{ name = "xgboost", specifier = "==1.5.0" },
|
||||
{ name = "xgboost", specifier = "==1.6.0" },
|
||||
{ name = "xpinyin", specifier = "==0.7.6" },
|
||||
{ name = "xxhash", specifier = ">=3.5.0,<4.0.0" },
|
||||
{ name = "yfinance", specifier = "==0.1.96" },
|
||||
@ -6583,18 +6583,19 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "xgboost"
|
||||
version = "1.5.0"
|
||||
version = "1.6.0"
|
||||
source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
|
||||
dependencies = [
|
||||
{ name = "numpy" },
|
||||
{ name = "scipy" },
|
||||
]
|
||||
sdist = { url = "https://mirrors.aliyun.com/pypi/packages/15/70/7308768fdd4a35477efb01098ffd426e455b600837ed0dd70c3293cd3e03/xgboost-1.5.0.tar.gz", hash = "sha256:6b7c34a18474c1b73b5c6dcf1231f5fe102d6f26490a65465e3879048bf1f3d4" }
|
||||
sdist = { url = "https://mirrors.aliyun.com/pypi/packages/77/89/92b399140a7688443fc182b54240822c903e906121d63446eb2f84350e99/xgboost-1.6.0.tar.gz", hash = "sha256:9c944c2495cb426b8a365021565755c39ee0b53156cf5e53a4346bdad2e3b734" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/9e/0d/376d5491ba5f06c6224304d572e1131521115d423a6c6dc347e85129c55c/xgboost-1.5.0-py3-none-macosx_10_14_x86_64.macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:ae122406c2c1d2a407c18a49c2a05f9bbbaa3249fd39e91c11cb223d538dba4e" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/dd/e2/43d1d96344d8733bbebde084bbf95ef8f2a3aab9f8d3779c3ee381754514/xgboost-1.5.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:ebe36ee21516a37f645bcd1f3ca1247485fe77d96f1c3d605f970c469b6a9015" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/a7/c9/4968ca0434c313aed71fc4cc2339aa8844482d5eefdcc8989c985a19ea2e/xgboost-1.5.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:edaad84317a53671069b4477152915c25b4121d997bfa531711f0a18ba1402fe" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/a2/8a/dbfcab37ea93951fa85e5746de0fc7378b2a4c99a32ddad36a7fb504ed57/xgboost-1.5.0-py3-none-win_amd64.whl", hash = "sha256:9502a9ed5c52669c83207380eeaaa3862cbf38b271040c6d5226914e07cf196c" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/f1/71/abca2240b5d19aa3e90c8228cf307962fc9f598acc3c623fb49db83b4092/xgboost-1.6.0-py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.macosx_12_0_x86_64.whl", hash = "sha256:5f7fd61024c41d0c424a8272dfd27797a0393a616b717c05c0f981a49a47b4fd" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/49/d0/85c9c40e7ca1a4bc05278c1e57a89c43ab846be4cb5227871ca7605921a6/xgboost-1.6.0-py3-none-macosx_12_0_arm64.whl", hash = "sha256:ad27c6a72f6abef6d20e67f957fb25553bb09a6d1c4eaf08cb8ee7efca288255" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/c3/be/18970943eb7e9d9ded5e37e87c1dc02c8a961416f725f2734629f26d69d5/xgboost-1.6.0-py3-none-manylinux2014_aarch64.whl", hash = "sha256:b1d532b8d548dd3acb4bd5f56632339e48167d9e2ec0eda2d8d6b4cd772e03b4" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/bf/64/c467a20848adc3d1c3f45d60df9c7cd0c40a548fd534a9f842a35114039d/xgboost-1.6.0-py3-none-manylinux2014_x86_64.whl", hash = "sha256:640b9649104f22f0dc43c7202d22cde5531cc303801a9c75cad3f2b6e413dcf7" },
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/64/51/3e33a4df0ca66474e7f4e357328a5c7b35fb52cbc48b312c64d276d37da8/xgboost-1.6.0-py3-none-win_amd64.whl", hash = "sha256:e2f9baca0b7cbc208ad4fbafa4cd70b50b292717ee8ba817a3ba7a0fe49de958" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user