fix (document_extractor): eml files contain images

9 months ago · 89a3000afe
parent 6d3e198c3c
commit 89a3000afe
2 changed files with 2857 additions and 2171 deletions
--- a/api/pyproject.toml
+++ b/api/pyproject.toml
@ -78,7 +78,7 @@ dependencies = [
    "starlette==0.41.0",
    "tiktoken~=0.9.0",
    "transformers~=4.51.0",
-    "unstructured[docx,epub,md,ppt,pptx]~=0.16.1",
+    "unstructured[docx,epub,image,md,ppt,pptx]~=0.16.1",
    "weave~=0.51.0",
    "yarl~=1.18.3",
    "webvtt-py~=0.5.1",
--- a/api/uv.lock
+++ b/api/uv.lock