haiku.rag/tests/cassettes
Yiorgis Gozadinos 3603b00513
Fix base64 images leaking into expanded search results
PictureItem.export_to_markdown() defaults to ImageRefMode.EMBEDDED,
which embeds base64 image data. When _extract_item_text() called this
method during context expansion, base64 data would leak into results.

Now explicitly handles PictureItem with ImageRefMode.PLACEHOLDER to
prevent base64 while still including VLM descriptions and captions.
2026-01-08 18:42:58 +02:00
..
test_chunk Add vcr to tests 2025-12-29 14:59:15 +02:00
test_chunker Extract shared DoclingServeClient for async workflow & use it for VLM support, chunking, converting 2026-01-07 11:09:23 +02:00
test_client Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_context_enhancement Fix base64 images leaking into expanded search results 2026-01-08 18:42:58 +02:00
test_converters Extract shared DoclingServeClient for async workflow & use it for VLM support, chunking, converting 2026-01-07 11:09:23 +02:00
test_database_autocreate Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_embedder Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_filter Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_qa Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_rebuild Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_reranker Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_search Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00
test_versioning Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00