haiku.rag/haiku_rag_slim/haiku/rag/converters
Yiorgis Gozadinos d2f5ecfc58
Prevent magic-byte sniffing from misrouting text conversion in docling-local
Docling guesses a DocumentStream's format from its first bytes before
considering the extension, so markdown/HTML content starting with a binary
magic signature ("BM" = BMP, "ID3" = MP3) was routed to an image or audio
backend and fell back to plain-text conversion. Prefix the encoded text
with a newline so the sniff finds nothing and the extension decides.
2026-07-15 19:20:54 +03:00
..
__init__.py Additional options for document conversion with docling 2025-11-18 15:44:04 +02:00
base.py Share the VLM URL builder and centralize the embedder empty guard 2026-06-29 15:15:26 +03:00
docling_local.py Prevent magic-byte sniffing from misrouting text conversion in docling-local 2026-07-15 19:20:54 +03:00
docling_serve.py Fail docling-serve requests over to another instance with per-instance breaking 2026-07-08 11:03:44 +03:00
pdf_split.py move cpu bound actions off of main loop 2026-06-18 16:35:48 -05:00
text_utils.py Wire per-format options across docling-local 2026-05-12 15:02:59 +03:00