对于独立部署版本的Confluence的CQL支持有Bug

from langchain.document_loaders import ConfluenceLoader
import lxml

loader = ConfluenceLoader(
    url="https://confluence.zhenguanyu.com/",
    token= {CONFLUENCE_TOKEN},
    cloud=False
)
page_id = 192873905
raw_cql = f"type = page AND ancestor = {page_id}"
documents = loader.load(cql=raw_cql, include_attachments=False, limit=50)

比如上述代码即会报如下错误

start
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[40], line 11
      9 page_id = 192873905
     10 raw_cql = f"type = page AND ancestor = {page_id}"
---> 11 documents = loader.load(cql=raw_cql, include_attachments=False, limit=50)

File ~/code/git/github/langchain/langchain/document_loaders/confluence.py:251, in ConfluenceLoader.load(self, space_key, page_ids, label, cql, include_restricted_content, include_archived_content, include_attachments, include_comments, limit, max_pages)
    242 pages = self.paginate_request(
    243     self.confluence.cql,
    244     cql=cql,
   (...)
    248     expand="body.storage.value",
    249 )
    250 print(pages[1])
--> 251 ids_by_cql = [page["content"]["id"] for page in pages]
    252 if page_ids:
    253     page_ids = list(set(page_ids + ids_by_cql))

File ~/code/git/github/langchain/langchain/document_loaders/confluence.py:251, in <listcomp>(.0)
    242 pages = self.paginate_request(
    243     self.confluence.cql,
    244     cql=cql,
   (...)
    248     expand="body.storage.value",
    249 )
    250 print(pages[1])
--> 251 ids_by_cql = [page["content"]["id"] for page in pages]
    252 if page_ids:
    253     page_ids = list(set(page_ids + ids_by_cql))

TypeError: string indices must be integers, not 'str'

coderfengyun / chat-confluence

对于独立部署版本的Confluence的CQL支持有Bug #4