Remove unwanted libraries and lighten package (#1391)

This commit is contained in:
Dev Khant
2024-07-09 04:30:16 +05:30
committed by GitHub
parent ebbf90f4aa
commit 1a5d0d236a
28 changed files with 235 additions and 1541 deletions

View File

@@ -24,7 +24,7 @@ class BeehiivLoader(BaseLoader):
from bs4.builder import ParserRejectedMarkup
except ImportError:
raise ImportError(
'Beehiiv requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
"Beehiiv requires extra dependencies. Install with `pip install beautifulsoup4==4.12.3`"
) from None
if not url.endswith("sitemap.xml"):

View File

@@ -8,7 +8,7 @@ try:
from bs4 import BeautifulSoup
except ImportError:
raise ImportError(
'DocsSite requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
"DocsSite requires extra dependencies. Install with `pip install beautifulsoup4==4.12.3`"
) from None

View File

@@ -3,9 +3,7 @@ import hashlib
try:
from langchain_community.document_loaders import Docx2txtLoader
except ImportError:
raise ImportError(
'Docx file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
) from None
raise ImportError("Docx file requires extra dependencies. Install with `pip install docx2txt==0.8`") from None
from embedchain.helpers.json_serializable import register_deserializable
from embedchain.loaders.base_loader import BaseLoader

View File

@@ -17,9 +17,7 @@ class DropboxLoader(BaseLoader):
try:
from dropbox import Dropbox, exceptions
except ImportError:
raise ImportError(
'Dropbox requires extra dependencies. Install with `pip install --upgrade "embedchain[dropbox]"`'
)
raise ImportError("Dropbox requires extra dependencies. Install with `pip install dropbox==11.36.2`")
try:
dbx = Dropbox(access_token)

View File

@@ -30,7 +30,8 @@ class GithubLoader(BaseLoader):
from github import Github
except ImportError as e:
raise ValueError(
"GithubLoader requires extra dependencies. Install with `pip install --upgrade 'embedchain[github]'`"
"GithubLoader requires extra dependencies. \
Install with `pip install gitpython==3.1.38 PyGithub==1.59.1`"
) from e
self.config = config

View File

@@ -1,11 +1,6 @@
import hashlib
try:
from langchain_community.document_loaders import PyPDFLoader
except ImportError:
raise ImportError(
'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
) from None
from langchain_community.document_loaders import PyPDFLoader
from embedchain.helpers.json_serializable import register_deserializable
from embedchain.loaders.base_loader import BaseLoader
from embedchain.utils.misc import clean_string

View File

@@ -28,12 +28,11 @@ class RSSFeedLoader(BaseLoader):
@staticmethod
def get_rss_content(url: str):
try:
from langchain_community.document_loaders import \
RSSFeedLoader as LangchainRSSFeedLoader
from langchain_community.document_loaders import RSSFeedLoader as LangchainRSSFeedLoader
except ImportError:
raise ImportError(
"""RSSFeedLoader file requires extra dependencies.
Install with `pip install --upgrade "embedchain[rss_feed]"`"""
Install with `pip install feedparser==6.0.10 newspaper3k==0.2.8 listparser==0.19`"""
) from None
output = []

View File

@@ -12,7 +12,7 @@ try:
from bs4.builder import ParserRejectedMarkup
except ImportError:
raise ImportError(
'Sitemap requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
"Sitemap requires extra dependencies. Install with `pip install beautifulsoup4==4.12.3`"
) from None
from embedchain.helpers.json_serializable import register_deserializable

View File

@@ -24,7 +24,7 @@ class SubstackLoader(BaseLoader):
from bs4.builder import ParserRejectedMarkup
except ImportError:
raise ImportError(
'Substack requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
"Substack requires extra dependencies. Install with `pip install beautifulsoup4==4.12.3`"
) from None
if not url.endswith("sitemap.xml"):

View File

@@ -7,7 +7,7 @@ try:
from bs4 import BeautifulSoup
except ImportError:
raise ImportError(
'Webpage requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
"Webpage requires extra dependencies. Install with `pip install beautifulsoup4==4.12.3`"
) from None
from embedchain.helpers.json_serializable import register_deserializable

View File

@@ -18,7 +18,7 @@ class YoutubeChannelLoader(BaseLoader):
import yt_dlp
except ImportError as e:
raise ValueError(
"YoutubeLoader requires extra dependencies. Install with `pip install --upgrade 'embedchain[youtube_channel]'`" # noqa: E501
"YoutubeChannelLoader requires extra dependencies. Install with `pip install yt_dlp==2023.11.14 youtube-transcript-api==0.6.1`" # noqa: E501
) from e
data = []

View File

@@ -5,14 +5,12 @@ import logging
try:
from youtube_transcript_api import YouTubeTranscriptApi
except ImportError:
raise ImportError('YouTube video requires extra dependencies. Install with `pip install youtube-transcript-api "`')
raise ImportError("YouTube video requires extra dependencies. Install with `pip install youtube-transcript-api`")
try:
from langchain_community.document_loaders import YoutubeLoader
from langchain_community.document_loaders.youtube import _parse_video_id
except ImportError:
raise ImportError(
'YouTube video requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
) from None
raise ImportError("YouTube video requires extra dependencies. Install with `pip install pytube==15.0.0`") from None
from embedchain.helpers.json_serializable import register_deserializable
from embedchain.loaders.base_loader import BaseLoader
from embedchain.utils.misc import clean_string