Improve error messages formatting in doc loaders (#4586)

# Cosmetic in errors formatting

Added appropriate spacing to the `ImportError` message in a bunch of
document loaders to enhance trace readability (including Google Drive,
Youtube, Confluence and others). This change ensures that the error
messages are not displayed as a single line block, and that the `pip
install xyz` commands can be copied to clipboard from terminal easily.

## Who can review?

@eyurtsev

langchain/document_loaders/confluence.py

@@ -92,7 +92,7 @@ class ConfluenceLoader(BaseLoader):
             from atlassian import Confluence  # noqa: F401
         except ImportError:
             raise ImportError(
-                "`atlassian` package not found, please run"
+                "`atlassian` package not found, please run "
                 "`pip install atlassian-python-api`"
             )
 
@@ -124,13 +124,13 @@ class ConfluenceLoader(BaseLoader):
 
         if (api_key and not username) or (username and not api_key):
             errors.append(
-                "If one of `api_key` or `username` is provided,"
+                "If one of `api_key` or `username` is provided, "
                 "the other must be as well."
             )
 
         if (api_key or username) and oauth2:
             errors.append(
-                "Cannot provide a value for `api_key` and/or"
+                "Cannot provide a value for `api_key` and/or "
                 "`username` and provide a value for `oauth2`"
             )
 
@@ -141,8 +141,8 @@ class ConfluenceLoader(BaseLoader):
             "key_cert",
         ]:
             errors.append(
-                "You have either ommited require keys or added extra"
-                "keys to the oauth2 dictionary. key values should be"
+                "You have either ommited require keys or added extra "
+                "keys to the oauth2 dictionary. key values should be "
                 "`['access_token', 'access_token_secret', 'consumer_key', 'key_cert']`"
             )
 
@@ -192,7 +192,7 @@ class ConfluenceLoader(BaseLoader):
         """
         if not space_key and not page_ids and not label and not cql:
             raise ValueError(
-                "Must specify at least one among `space_key`, `page_ids`,"
+                "Must specify at least one among `space_key`, `page_ids`, "
                 "`label`, `cql` parameters."
             )
 
@@ -338,8 +338,8 @@ class ConfluenceLoader(BaseLoader):
             from bs4 import BeautifulSoup  # type: ignore
         except ImportError:
             raise ImportError(
-                "`beautifulsoup4` package not found, please run"
-                " `pip install beautifulsoup4`"
+                "`beautifulsoup4` package not found, please run "
+                "`pip install beautifulsoup4`"
             )
 
         if include_attachments:
@@ -374,7 +374,7 @@ class ConfluenceLoader(BaseLoader):
             from PIL import Image  # noqa: F401
         except ImportError:
             raise ImportError(
-                "`pytesseract` or `pdf2image` or `Pillow` package not found,"
+                "`pytesseract` or `pdf2image` or `Pillow` package not found, "
                 "please run `pip install pytesseract pdf2image Pillow`"
             )
 
@@ -415,7 +415,7 @@ class ConfluenceLoader(BaseLoader):
             from pdf2image import convert_from_bytes  # noqa: F401
         except ImportError:
             raise ImportError(
-                "`pytesseract` or `pdf2image` package not found,"
+                "`pytesseract` or `pdf2image` package not found, "
                 "please run `pip install pytesseract pdf2image`"
             )
 
@@ -450,7 +450,7 @@ class ConfluenceLoader(BaseLoader):
             from PIL import Image  # noqa: F401
         except ImportError:
             raise ImportError(
-                "`pytesseract` or `Pillow` package not found,"
+                "`pytesseract` or `Pillow` package not found, "
                 "please run `pip install pytesseract Pillow`"
             )
 
@@ -531,7 +531,7 @@ class ConfluenceLoader(BaseLoader):
             from svglib.svglib import svg2rlg  # noqa: F401
         except ImportError:
             raise ImportError(
-                "`pytesseract`, `Pillow`, or `svglib` package not found,"
+                "`pytesseract`, `Pillow`, or `svglib` package not found, "
                 "please run `pip install pytesseract Pillow svglib`"
             )
 

langchain/document_loaders/googledrive.py

@@ -68,10 +68,10 @@ class GoogleDriveLoader(BaseLoader, BaseModel):
             from google_auth_oauthlib.flow import InstalledAppFlow
         except ImportError:
             raise ImportError(
-                "You must run"
+                "You must run "
                 "`pip install --upgrade "
                 "google-api-python-client google-auth-httplib2 "
-                "google-auth-oauthlib`"
+                "google-auth-oauthlib` "
                 "to use the Google Drive loader."
             )
 

langchain/document_loaders/image_captions.py

@@ -40,8 +40,8 @@ class ImageCaptionLoader(BaseLoader):
             from transformers import BlipForConditionalGeneration, BlipProcessor
         except ImportError:
             raise ValueError(
-                "transformers package not found, please install with"
-                "`pip install transformers`"
+                "`transformers` package not found, please install with "
+                "`pip install transformers`."
             )
 
         processor = BlipProcessor.from_pretrained(self.blip_processor)
@@ -67,7 +67,7 @@ class ImageCaptionLoader(BaseLoader):
             from PIL import Image
         except ImportError:
             raise ValueError(
-                "PIL package not found, please install with `pip install pillow`"
+                "`PIL` package not found, please install with `pip install pillow`"
             )
 
         try:

langchain/document_loaders/onedrive.py

@@ -197,7 +197,7 @@ class OneDriveLoader(BaseLoader, BaseModel):
                 file = drive.get_item(object_id)
                 if not file:
                     logging.warning(
-                        "There isn't a file with"
+                        "There isn't a file with "
                         f"object_id {object_id} in drive {drive}."
                     )
                     continue

langchain/document_loaders/pdf.py

@@ -194,7 +194,7 @@ class PDFMinerLoader(BasePDFLoader):
             from pdfminer.high_level import extract_text  # noqa:F401
         except ImportError:
             raise ValueError(
-                "pdfminer package not found, please install it with "
+                "`pdfminer` package not found, please install it with "
                 "`pip install pdfminer.six`"
             )
 
@@ -222,7 +222,7 @@ class PDFMinerPDFasHTMLLoader(BasePDFLoader):
             from pdfminer.high_level import extract_text_to_fp  # noqa:F401
         except ImportError:
             raise ValueError(
-                "pdfminer package not found, please install it with "
+                "`pdfminer` package not found, please install it with "
                 "`pip install pdfminer.six`"
             )
 
@@ -256,7 +256,7 @@ class PyMuPDFLoader(BasePDFLoader):
             import fitz  # noqa:F401
         except ImportError:
             raise ValueError(
-                "PyMuPDF package not found, please install it with "
+                "`PyMuPDF` package not found, please install it with "
                 "`pip install pymupdf`"
             )
 

langchain/document_loaders/s3_file.py

@@ -22,7 +22,7 @@ class S3FileLoader(BaseLoader):
             import boto3
         except ImportError:
             raise ValueError(
-                "Could not import boto3 python package. "
+                "Could not import `boto3` python package. "
                 "Please install it with `pip install boto3`."
             )
         s3 = boto3.client("s3")

langchain/document_loaders/web_base.py

@@ -76,7 +76,7 @@ class WebBaseLoader(BaseLoader):
             self.session.headers = dict(headers)
         except ImportError:
             logger.info(
-                "fake_useragent not found, using default user agent."
+                "fake_useragent not found, using default user agent. "
                 "To get a realistic header for requests, `pip install fake_useragent`."
             )
 

langchain/document_loaders/youtube.py

@@ -70,8 +70,8 @@ class GoogleApiClient:
                 "You must run"
                 "`pip install --upgrade "
                 "google-api-python-client google-auth-httplib2 "
-                "google-auth-oauthlib"
-                "youtube-transcript-api`"
+                "google-auth-oauthlib "
+                "youtube-transcript-api` "
                 "to use the Google Drive loader"
             )
 
@@ -239,8 +239,8 @@ class GoogleApiYoutubeLoader(BaseLoader):
                 "You must run"
                 "`pip install --upgrade "
                 "google-api-python-client google-auth-httplib2 "
-                "google-auth-oauthlib"
-                "youtube-transcript-api`"
+                "google-auth-oauthlib "
+                "youtube-transcript-api` "
                 "to use the Google Drive loader"
             )
 
@@ -305,7 +305,7 @@ class GoogleApiYoutubeLoader(BaseLoader):
             raise ImportError(
                 "You must run"
                 "`pip install --upgrade "
-                "youtube-transcript-api`"
+                "youtube-transcript-api` "
                 "to use the youtube loader"
             )