blob42/langchain
1
0
Fork 0
forked from Archives/langchain
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Change Data Loader Namespace (#6568)

Browse Source 
Description:
Update the artifact name of the xml file and the namespaces. Co-authored
with @tjaffri
Co-authored-by: Kenzie Mihardja <kenzie@docugami.com>
This commit is contained in:
Kenzie Mihardja 2023-06-21 19:24:04 -07:00 committed by GitHub
parent 0673245d0c
commit b8d78424ab
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
langchain/document_loaders/docugami.py
View File

@ -243,7 +243,7 @@ class DocugamiLoader(BaseLoader, BaseModel):
artifact_url = artifact.get("url") artifact_url = artifact.get("url")
artifact_doc = artifact.get("document") artifact_doc = artifact.get("document")
if artifact_name == f"{project_id}.xml" and artifact_url and artifact_doc: if artifact_name == "report-values.xml" and artifact_url and artifact_doc:
doc_id = artifact_doc["id"] doc_id = artifact_doc["id"]
metadata: Dict = {} metadata: Dict = {}
@ -266,11 +266,11 @@ class DocugamiLoader(BaseLoader, BaseModel):
artifact_tree = etree.parse(io.BytesIO(response.content)) artifact_tree = etree.parse(io.BytesIO(response.content))
artifact_root = artifact_tree.getroot() artifact_root = artifact_tree.getroot()
ns = artifact_root.nsmap ns = artifact_root.nsmap
entries = artifact_root.xpath("//wp:Entry", namespaces=ns) entries = artifact_root.xpath("//pr:Entry", namespaces=ns)
for entry in entries: for entry in entries:
heading = entry.xpath("./wp:Heading", namespaces=ns)[0].text heading = entry.xpath("./pr:Heading", namespaces=ns)[0].text
value = " ".join( value = " ".join(
entry.xpath("./wp:Value", namespaces=ns)[0].itertext() entry.xpath("./pr:Value", namespaces=ns)[0].itertext()
).strip() ).strip()
metadata[heading] = value metadata[heading] = value
per_file_metadata[doc_id] = metadata per_file_metadata[doc_id] = metadata