Refactor pdfminer

langchain-ai · Jan 31, 2025 · 278c6d2 · 278c6d2
1 parent ceda8bc
commit 278c6d2
Show file tree

Hide file tree

Showing 9 changed files with 2,706 additions and 620 deletions.
diff --git a/docs/docs/integrations/document_loaders/pdfminer.ipynb b/docs/docs/integrations/document_loaders/pdfminer.ipynb
diff --git a/docs/docs/integrations/document_loaders/pymupdf.ipynb b/docs/docs/integrations/document_loaders/pymupdf.ipynb
diff --git a/libs/community/extended_testing_deps.txt b/libs/community/extended_testing_deps.txt
@@ -59,7 +59,7 @@ openapi-pydantic>=0.3.2,<0.4
 oracle-ads>=2.9.1,<3
 oracledb>=2.2.0,<3
 pandas>=2.0.1,<3
-pdfminer-six>=20221105,<20240706
+pdfminer-six==20231228
 pdfplumber>=0.11
 pgvector>=0.1.6,<0.2
 playwright>=1.48.0,<2
@@ -104,3 +104,4 @@ mlflow[genai]>=2.14.0
 databricks-sdk>=0.30.0
 websocket>=0.2.1,<1
 writer-sdk>=1.2.0
+unstructured[pdf]>=0.15