Actor: Refactor actor.sh and add docling_processor.py

Refactor the `actor.sh` script to modularize functions for finding the Apify CLI, setting up a temporary environment, and cleaning it up. Introduce a new function, `get_actor_input()`, to handle input detection more robustly. Replace inline Python conversion logic with an external script, `docling_processor.py`, for processing documents via the docling-serve API. Signed-off-by: Václav Vančura <[email protected]>
DS4SD · Mar 9, 2025 · 16bbed2 · 16bbed2
1 parent 103e0f1
commit 16bbed2
Show file tree

Hide file tree

Showing 3 changed files with 521 additions and 489 deletions.
diff --git a/.actor/Dockerfile b/.actor/Dockerfile
@@ -62,6 +62,7 @@ ENV EASYOCR_MODULE_PATH=/tmp/easyocr-models
 COPY --chown=1000:1000 .actor/actor.sh .actor/actor.sh
 COPY --chown=1000:1000 .actor/actor.json .actor/actor.json
 COPY --chown=1000:1000 .actor/input_schema.json .actor/input_schema.json
+COPY --chown=1000:1000 .actor/docling_processor.py .actor/docling_processor.py
 RUN chmod +x .actor/actor.sh
 
 # Copy the build files from builder