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
..
__init__.py	emit synthetic picture chunks at ingest under multimodal embedders.	2026-05-03 17:04:43 +03:00
agents.py	Extract LLM agents into client/agents.py	2026-04-24 14:43:58 +03:00
documents.py	emit synthetic picture chunks at ingest under multimodal embedders.	2026-05-03 17:04:43 +03:00
downloads.py	add processing.pictures enum (none|description|image), replacing the implicit pair of generate_picture_images+picture_description.enabled flags	2026-04-30 14:26:14 +03:00
processing.py	emit synthetic picture chunks at ingest under multimodal embedders.	2026-05-03 17:04:43 +03:00
rebuild.py	emit synthetic picture chunks at ingest under multimodal embedders.	2026-05-03 17:04:43 +03:00
search.py	surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool	2026-04-30 12:43:05 +03:00
titles.py	Extract title generation into client/titles.py	2026-04-24 14:42:53 +03:00