More fixes

pdelfin/beakerpipeline.py

@@ -811,9 +811,7 @@ async def main():
     asyncio.run(main())
 
     # TODO
-    # - Fix loading of the model checkpoints, it's so flakey now, maybe use datasets
     # - Add logging of failed pages and have the stats function read them
-    # - Fallback to different method if < 2% of pages are failed, make that configurable
     # - Sglang commit a fix for the context length issue
     # - pypdf fix for the 'v' error
     # - Get a solid benchmark on the stream vs non stream approach

pdelfin/prompts/prompts.py

@@ -25,10 +25,24 @@ class PageResponse:
     natural_text: Optional[str]
 
     def __post_init__(self):
-        # Validate that rotation_correction is one of the allowed values
+        # Validate rotation_correction is one of the allowed values
         if self.rotation_correction not in {0, 90, 180, 270}:
             raise ValueError("rotation_correction must be one of [0, 90, 180, 270].")
 
+        # Type checks
+        if not isinstance(self.primary_language, (str, type(None))):
+            raise TypeError("primary_language must be of type Optional[str].")
+        if not isinstance(self.is_rotation_valid, bool):
+            raise TypeError("is_rotation_valid must be of type bool.")
+        if not isinstance(self.rotation_correction, int):
+            raise TypeError("rotation_correction must be of type int.")
+        if not isinstance(self.is_table, bool):
+            raise TypeError("is_table must be of type bool.")
+        if not isinstance(self.is_diagram, bool):
+            raise TypeError("is_diagram must be of type bool.")
+        if not isinstance(self.natural_text, (str, type(None))):
+            raise TypeError("natural_text must be of type Optional[str].")
+
 def openai_response_format_schema() -> dict:
     return {
         "type": "json_schema",

pdelfin/version.py

@@ -2,7 +2,7 @@
 _MINOR = "1"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "30"
+_PATCH = "32"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""

scripts/beaker/Dockerfile-inference

@@ -48,6 +48,9 @@ WORKDIR sglang/python
 RUN git checkout eff468dd5a3d24646560eb044276585f7a11ac3c
 RUN /root/.local/bin/uv pip install --system --no-cache -e .[all]
 
+# TODO You can remove this once pypdf > 5.10 comes out
+RUN /root/.local/bin/uv pip install --system --no-cache git+https://github.com/py-pdf/pypdf.git@c6e43374ab002d76811ec85333fdc2c82c268251
+
 WORKDIR /root
 COPY pdelfin pdelfin