github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-21 10:26:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: fix the "page" mode in the AzureAIDocumentIntelligenceParser (bug) (#15958)

Browse Source 
**Description**: the "page" mode in the
AzureAIDocumentIntelligenceParser is not accessible due to a wrong
membership test. The mode argument can only be a string (also see the
assertion in the `__init__`: `assert self.mode in ["single", "page",
"object", "markdown"]`, so the check `elif self.mode == ["page"]:`
always fails.
As a result, effectively the "object" mode is used when selecting the
"page" mode, which may lead to errors.

The docstring of the `AzureAIDocumentIntelligenceLoader` also ommitted
the `mode` parameter alltogether, so I added it.

**Issue**: I could not find a related issue (this class is only 3 weeks
old anyways)

**Dependencies**: this PR does not introduce or affect dependencies.

The current demo notebook and examples are not affected because they all
use the default markdown mode.
This commit is contained in:
Edwin Wenink 2024-01-12 20:01:28 +01:00 committed by GitHub
parent eb76f9c9fe
commit 9fb09c1c30
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
libs/community/langchain_community/document_loaders/doc_intelligence.py
View File

@ -48,6 +48,8 @@ class AzureAIDocumentIntelligenceLoader(BaseLoader):
the default value from SDK. the default value from SDK.
api_model: str api_model: str
The model name or ID to be used for form recognition in Azure. The model name or ID to be used for form recognition in Azure.
mode: Optional[str]
The type of content representation of the generated Documents.
Examples: Examples:
--------- ---------
@ -56,7 +58,8 @@ class AzureAIDocumentIntelligenceLoader(BaseLoader):
... api_endpoint="https://endpoint.azure.com", ... api_endpoint="https://endpoint.azure.com",
... api_key="APIKEY", ... api_key="APIKEY",
... api_version="2023-10-31-preview", ... api_version="2023-10-31-preview",
... model="prebuilt-document" ... model="prebuilt-document",
... mode="markdown"
... ) ... )
""" """

4
libs/community/langchain_community/document_loaders/parsers/doc_intelligence.py
View File

@ -98,7 +98,7 @@ class AzureAIDocumentIntelligenceParser(BaseBlobParser):
if self.mode in ["single", "markdown"]: if self.mode in ["single", "markdown"]:
yield from self._generate_docs_single(result) yield from self._generate_docs_single(result)
elif self.mode == ["page"]: elif self.mode in ["page"]:
yield from self._generate_docs_page(result) yield from self._generate_docs_page(result)
else: else:
yield from self._generate_docs_object(result) yield from self._generate_docs_object(result)
@ -116,7 +116,7 @@ class AzureAIDocumentIntelligenceParser(BaseBlobParser):
if self.mode in ["single", "markdown"]: if self.mode in ["single", "markdown"]:
yield from self._generate_docs_single(result) yield from self._generate_docs_single(result)
elif self.mode == ["page"]: elif self.mode in ["page"]:
yield from self._generate_docs_page(result) yield from self._generate_docs_page(result)
else: else:
yield from self._generate_docs_object(result) yield from self._generate_docs_object(result)