Commit graph

5 commits

Author SHA1 Message Date
Yiorgis Gozadinos
c9227c649f
emit synthetic picture chunks at ingest under multimodal embedders.
processing.chunk() merges text chunks with one synthetic Chunk per PictureItem-with-bytes,
sorted by iterate_items() position so chunk.order is structural.
embed_chunks dispatches on a Chunk._picture_data PrivateAttr
(text through embed_documents, picture through embed_image_query)
2026-05-03 17:04:43 +03:00
Yiorgis Gozadinos
ddcc4518ad
Cover FULL rebuild source-failure branch 2026-04-24 15:32:53 +03:00
Yiorgis Gozadinos
258ffa41fa
Improve test coverage 2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
8bdfbe526c
Fix embed-only rebuild with changed vector dimensions
When a database was created with one embedding model and rebuild
--embed-only was run with a different model, it failed with a
vector dimension validation error.

- Store reads stored vector_dim when opening existing databases
- _rebuild_embed_only recreates chunks table to handle dimension changes
- Add test for rebuild with changed vector dimensions
2026-01-14 17:42:28 +02:00
Yiorgis Gozadinos
1e9a10a235
Record cassettes for embedder, ignore huggingface while recording 2025-12-29 13:23:53 +02:00