github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-16 17:53:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Confluence: Add page status filter for spaces (#3732)

Browse Source 
At the moment all content in Confluence is retrieved by default,
including archived content.

Often, this is undesired as the content is not relevant anymore.

**Notes**
Fetching pages by label does not support excluding archived content.
This may lead to unexpected results.
This commit is contained in:
Jelmer Borst 2023-04-29 04:56:53 +02:00 committed by GitHub
parent 7a129ac043
commit 8cf2ff0be0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
langchain/document_loaders/confluence.py
View File

@ -156,6 +156,7 @@ class ConfluenceLoader(BaseLoader):
page_ids: Optional[List[str]] = None,
label: Optional[str] = None,
cql: Optional[str] = None,
include_archived_content: bool = False,
include_attachments: bool = False,
include_comments: bool = False,
limit: Optional[int] = 50,
@ -170,6 +171,9 @@ class ConfluenceLoader(BaseLoader):
:type label: Optional[str], optional
:param cql: CQL Expression, defaults to None
:type cql: Optional[str], optional
:param include_archived_content: Whether to include archived content,
defaults to False
:type include_archived_content: bool, optional
:param include_attachments: defaults to False
:type include_attachments: bool, optional
:param include_comments: defaults to False
@ -197,6 +201,7 @@ class ConfluenceLoader(BaseLoader):
space=space_key,
limit=limit,
max_pages=max_pages,
status="any" if include_archived_content else "current",
expand="body.storage.value",
)
for page in pages:
@ -221,6 +226,7 @@ class ConfluenceLoader(BaseLoader):
cql=cql,
limit=limit,
max_pages=max_pages,
include_archived_spaces=include_archived_content,
expand="body.storage.value",
)
for page in pages: