Update dependencies for fast installation (#811)

embedchain/loaders/docs_site_loader.py

@@ -3,7 +3,14 @@ import logging
 from urllib.parse import urljoin, urlparse
 
 import requests
-from bs4 import BeautifulSoup
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    raise ImportError(
+        'DocsSite requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
+
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

embedchain/loaders/docx_file.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import Docx2txtLoader
-
+try:
+    from langchain.document_loaders import Docx2txtLoader
+except ImportError:
+    raise ImportError(
+        'Docx file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 

embedchain/loaders/pdf_file.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import PyPDFLoader
-
+try:
+    from langchain.document_loaders import PyPDFLoader
+except ImportError:
+    raise ImportError(
+        'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string

embedchain/loaders/sitemap.py

@@ -2,8 +2,14 @@ import hashlib
 import logging
 
 import requests
-from bs4 import BeautifulSoup
-from bs4.builder import ParserRejectedMarkup
+
+try:
+    from bs4 import BeautifulSoup
+    from bs4.builder import ParserRejectedMarkup
+except ImportError:
+    raise ImportError(
+        'Sitemap requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

embedchain/loaders/web_page.py

@@ -2,7 +2,13 @@ import hashlib
 import logging
 
 import requests
-from bs4 import BeautifulSoup
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    raise ImportError(
+        'Webpage requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

embedchain/loaders/xml.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import UnstructuredXMLLoader
-
+try:
+    from langchain.document_loaders import UnstructuredXMLLoader
+except ImportError:
+    raise ImportError(
+        'XML file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string

embedchain/loaders/youtube_video.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import YoutubeLoader
-
+try:
+    from langchain.document_loaders import YoutubeLoader
+except ImportError:
+    raise ImportError(
+        'YouTube video requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string