danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: turn off ocr on docling serve chunking to avoid issues with read-only docker containers

Browse source
This commit is contained in:
bryan davis 2026-02-02 15:20:31 -06:00
parent ef187767ed
commit d1ed616a04
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
haiku_rag_slim/haiku/rag/chunkers/docling_serve.py
View file

@ -64,6 +64,9 @@ class DoclingServeChunker(DocumentChunker):
def _build_chunking_data(self) -> dict[str, str]: def _build_chunking_data(self) -> dict[str, str]:
"""Build form data for chunking request.""" """Build form data for chunking request."""
return { return {
"convert_do_ocr": "false",
"convert_force_ocr": "false",
"convert_ocr_engine": "tesseract",
"chunking_max_tokens": str(self.config.processing.chunk_size), "chunking_max_tokens": str(self.config.processing.chunk_size),
"chunking_tokenizer": self.config.processing.chunking_tokenizer, "chunking_tokenizer": self.config.processing.chunking_tokenizer,
"chunking_merge_peers": str( "chunking_merge_peers": str(