github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-24 23:54:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

DROP BOX Loader Documentation Update (#14047)

Browse Source 
- **Description:** Update the document for drop box loader + made the
messages more verbose when loading pdf file since people were getting
confused
  - **Issue:** #13952
  - **Tag maintainer:** @baskaryan, @eyurtsev, @hwchase17,

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Mohammad Mohtashim 2023-11-30 06:25:35 +05:00 committed by GitHub
parent a00db4b28f
commit f3dd4a10cf
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/integrations/document_loaders/dropbox.ipynb
View File

@ -15,7 +15,7 @@
"1. Create a Dropbox app.\n", "1. Create a Dropbox app.\n",
"2. Give the app these scope permissions: `files.metadata.read` and `files.content.read`.\n", "2. Give the app these scope permissions: `files.metadata.read` and `files.content.read`.\n",
"3. Generate access token: https://www.dropbox.com/developers/apps/create.\n", "3. Generate access token: https://www.dropbox.com/developers/apps/create.\n",
"4. `pip install dropbox` (requires `pip install unstructured` for PDF filetype).\n", "4. `pip install dropbox` (requires `pip install \"unstructured[pdf]\"` for PDF filetype).\n",
"\n", "\n",
"## Instructions\n", "## Instructions\n",
"\n", "\n",

9
libs/langchain/langchain/document_loaders/dropbox.py
View File

@ -3,7 +3,7 @@
# 2. Give the app these scope permissions: `files.metadata.read` # 2. Give the app these scope permissions: `files.metadata.read`
# and `files.content.read`. # and `files.content.read`.
# 3. Generate access token: https://www.dropbox.com/developers/apps/create. # 3. Generate access token: https://www.dropbox.com/developers/apps/create.
# 4. `pip install dropbox` (requires `pip install unstructured` for PDF filetype). # 4. `pip install dropbox` (requires `pip install unstructured[pdf]` for PDF filetype).
import os import os
@ -118,11 +118,10 @@ class DropboxLoader(BaseLoader, BaseModel):
try: try:
text = response.content.decode("utf-8") text = response.content.decode("utf-8")
except UnicodeDecodeError: except UnicodeDecodeError:
print(f"File {file_path} could not be decoded as text. Skipping.")
file_extension = os.path.splitext(file_path)[1].lower() file_extension = os.path.splitext(file_path)[1].lower()
if file_extension == ".pdf": if file_extension == ".pdf":
print(f"File {file_path} type detected as .pdf")
from langchain.document_loaders import UnstructuredPDFLoader from langchain.document_loaders import UnstructuredPDFLoader
# Download it to a temporary file. # Download it to a temporary file.
@ -139,6 +138,10 @@ class DropboxLoader(BaseLoader, BaseModel):
except Exception as pdf_ex: except Exception as pdf_ex:
print(f"Error while trying to parse PDF {file_path}: {pdf_ex}") print(f"Error while trying to parse PDF {file_path}: {pdf_ex}")
return None return None
else:
print(
f"File {file_path} could not be decoded as pdf or text. Skipping."
)
return None return None