Chore: Bump unstructured to 0.10.30 (#309)

^^^
Also releasing this version since `0.10.30` include some 500 error bug
fix

Author: yuming-long

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.0.58
+
+* Bump unstructured to 0.10.30
+
 ## 0.0.57
 * Make sure `multipage_sections` param defaults to `true` as per the readme
 * Bump unstructured to 0.10.29

Dockerfile

@@ -32,10 +32,12 @@ RUN python3.10 -m pip install pip==${PIP_VERSION} \
 USER ${NB_USER}
 
 FROM python-deps as model-deps
-
+# Note(yuming): quick workaround for ingest import error
+# should import initialize within unstructured but out of ingest dir
+COPY --chown=${NB_USER}:${NB_USER} scripts/hi_res_model_initialize.py  hi_res_model_initialize.py 
 RUN python3.10 -c "import nltk; nltk.download('punkt')" && \
   python3.10 -c "import nltk; nltk.download('averaged_perceptron_tagger')" && \
-  python3.10 -c "from unstructured.ingest.pipeline.initialize import initialize; initialize()"
+  python3.10 -c "from hi_res_model_initialize import initialize; initialize()"
 
 FROM model-deps as code
 COPY --chown=${NB_USER}:${NB_USER} CHANGELOG.md CHANGELOG.md

prepline_general/api/app.py

@@ -11,7 +11,7 @@
 app = FastAPI(
     title="Unstructured Pipeline API",
     description="""""",
-    version="0.0.57",
+    version="0.0.58",
     docs_url="/general/docs",
     openapi_url="/general/openapi.json",
 )

prepline_general/api/general.py

@@ -636,7 +636,7 @@ def return_content_type(filename):
 
 
 @router.post("/general/v0/general")
-@router.post("/general/v0.0.57/general")
+@router.post("/general/v0.0.58/general")
 def pipeline_1(
     request: Request,
     gz_uncompressed_content_type: Optional[str] = Form(default=None),

preprocessing-pipeline-family.yaml

@@ -1,2 +1,2 @@
 name: general
-version: 0.0.57
+version: 0.0.58

requirements/base.txt

@@ -39,7 +39,7 @@ cryptography==41.0.5
     # via pdfminer-six
 cycler==0.12.1
     # via matplotlib
-dataclasses-json==0.6.1
+dataclasses-json==0.6.2
     # via unstructured
 effdet==0.4.1
     # via layoutparser
@@ -58,15 +58,15 @@ filetype==1.2.0
     # via unstructured
 flatbuffers==23.5.26
     # via onnxruntime
-fonttools==4.44.0
+fonttools==4.44.3
     # via matplotlib
 fsspec==2023.10.0
     # via
     #   huggingface-hub
     #   torch
 h11==0.14.0
     # via uvicorn
-huggingface-hub==0.17.3
+huggingface-hub==0.19.3
     # via
     #   timm
     #   tokenizers
@@ -115,7 +115,7 @@ networkx==3.2.1
     #   unstructured
 nltk==3.8.1
     # via unstructured
-numpy==1.26.1
+numpy==1.26.2
     # via
     #   contourpy
     #   layoutparser
@@ -154,7 +154,7 @@ packaging==23.2
     #   pytesseract
     #   transformers
     #   unstructured-pytesseract
-pandas==2.1.2
+pandas==2.1.3
     # via
     #   layoutparser
     #   unstructured
@@ -200,9 +200,9 @@ pypandoc==1.12
     # via unstructured
 pyparsing==3.1.1
     # via matplotlib
-pypdf==3.17.0
+pypdf==3.17.1
     # via -r requirements/base.in
-pypdfium2==4.23.1
+pypdfium2==4.24.0
     # via pdfplumber
 pytesseract==0.3.10
     # via layoutparser
@@ -218,7 +218,7 @@ python-magic==0.4.27
     # via unstructured
 python-multipart==0.0.6
     # via unstructured-inference
-python-pptx==0.6.21
+python-pptx==0.6.23
     # via unstructured
 pytz==2023.3.post1
     # via pandas
@@ -271,15 +271,15 @@ tabulate==0.9.0
     # via unstructured
 timm==0.9.10
     # via effdet
-tokenizers==0.14.1
+tokenizers==0.15.0
     # via transformers
-torch==2.1.0
+torch==2.1.1
     # via
     #   effdet
     #   layoutparser
     #   timm
     #   torchvision
-torchvision==0.16.0
+torchvision==0.16.1
     # via
     #   effdet
     #   layoutparser
@@ -290,7 +290,7 @@ tqdm==4.66.1
     #   iopath
     #   nltk
     #   transformers
-transformers==4.35.0
+transformers==4.35.2
     # via unstructured-inference
 typing-extensions==4.8.0
     # via
@@ -307,13 +307,15 @@ typing-inspect==0.9.0
     # via dataclasses-json
 tzdata==2023.3
     # via pandas
-unstructured[local-inference]==0.10.29
-    # via -r requirements/base.in
+unstructured[local-inference]==0.10.30
+    # via
+    #   -r requirements/base.in
+    #   unstructured
 unstructured-inference==0.7.11
     # via unstructured
 unstructured-pytesseract==0.3.12
     # via unstructured
-urllib3==2.0.7
+urllib3==2.1.0
     # via requests
 uvicorn==0.24.0.post1
     # via -r requirements/base.in