highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-03-26 17:51:54 +01:00
Code Issues Packages Projects Releases Wiki Activity

BookStack connector: Changed to use id-based document ids

Browse Source
This commit is contained in:
Dan Brown 2023-07-06 17:04:31 +01:00
parent 104a248b11
commit 019e474a4e
No known key found for this signature in database
GPG Key ID: 46D9F943C24A2EF9
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
backend/danswer/connectors/bookstack/connector.py
View File

@ -72,7 +72,7 @@ class BookstackConnector(LoadConnector, PollConnector):
url = self.bookstack_client.build_app_url("/books/" + book.get("slug"))
text = book.get("name", "") + "\n" + book.get("description", "")
return Document(
id=url,
id="book:" + str(book.get("id")),
sections=[Section(link=url, text=text)],
source=DocumentSource.BOOKSTACK,
semantic_identifier="Book: " + book.get("name"),
@ -86,7 +86,7 @@ class BookstackConnector(LoadConnector, PollConnector):
url = self.bookstack_client.build_app_url("/books/" + chapter.get("book_slug") + "/chapter/" + chapter.get("slug"))
text = chapter.get("name", "") + "\n" + chapter.get("description", "")
return Document(
id=url,
id="chapter:" + str(chapter.get("id")),
sections=[Section(link=url, text=text)],
source=DocumentSource.BOOKSTACK,
semantic_identifier="Chapter: " + chapter.get("name"),
@ -100,7 +100,7 @@ class BookstackConnector(LoadConnector, PollConnector):
url = self.bookstack_client.build_app_url("/shelves/" + shelf.get("slug"))
text = shelf.get("name", "") + "\n" + shelf.get("description", "")
return Document(
id=url,
id="shelf:" + str(shelf.get("id")),
sections=[Section(link=url, text=text)],
source=DocumentSource.BOOKSTACK,
semantic_identifier="Shelf: " + shelf.get("name"),
@ -119,7 +119,7 @@ class BookstackConnector(LoadConnector, PollConnector):
text = soup.get_text(HTML_SEPARATOR)
time.sleep(0.1)
return Document(
id=url,
id="page:" + page_id,
sections=[Section(link=url, text=text)],
source=DocumentSource.BOOKSTACK,
semantic_identifier="Page: " + page_data.get("name"),