Yiorgis Gozadinos
ee41bc676f
remove defensive code
2026-05-04 15:12:27 +03:00
Yiorgis Gozadinos
e8d89aa035
dedup picture-only chunks at the search-result layer
2026-05-04 13:31:15 +03:00
Yiorgis Gozadinos
aa3e9406cf
auto-append /v1 to per-model Ollama base_url, fix flaky tests
2026-05-04 13:12:37 +03:00
Yiorgis Gozadinos
65d9c74224
expose image-as-query through MCP and the CLI.
2026-05-04 11:46:45 +03:00
Yiorgis Gozadinos
ff656504d3
make client.search() polymorphic on query type: str | bytes | PIL.Image.Image. Bytes/PIL queries embed via embed_image_query and run vector-only against the chunks table
2026-05-04 11:22:22 +03:00
Yiorgis Gozadinos
21f12cd770
add vision: bool flag on ModelConfig (default False). Gate the agent search tool's BinaryContent attachment on qa.model.vision so picture bytes are only sent to vision-capable QA models.
2026-05-04 10:47:21 +03:00
Yiorgis Gozadinos
6037f26673
drop mlx
2026-05-03 19:05:49 +03:00
Yiorgis Gozadinos
c9fdad15a9
bump docling-core to >=2.74.1 so that local docling-local and docling-serve chunkers run the same MarkdownTableSerializer
2026-05-03 18:40:44 +03:00
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
a36f920f5d
drop the batched embed_images method from multi-modal embedders
2026-05-03 16:21:47 +03:00
Yiorgis Gozadinos
37215f1a00
add multimodal embedder support for vllm and mlx
2026-05-03 10:57:56 +03:00
Yiorgis Gozadinos
4c9ef81fc6
drop the existing-row-not-found guard from the 0.45.0 picture-bytes migration.
2026-04-30 15:48:03 +03:00
Yiorgis Gozadinos
b290bbe82d
rename document_items repository's _LIGHT_COLUMNS to _METADATA_COLUMNS
2026-04-30 15:43:03 +03:00
Yiorgis Gozadinos
875c635a77
have rebuild --rechunk re-chunk from the stored docling blob instead of re-converting from the markdown export
2026-04-30 15:30:24 +03:00
Yiorgis Gozadinos
7831057339
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
Yiorgis Gozadinos
b01c649684
surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool
2026-04-30 12:43:05 +03:00
Yiorgis Gozadinos
6a77ce92a9
extract picture bytes to document_items.picture_data at ingest, strip them from the docling_document blob, and add 0.45.0 migration to backfill existing
...
databases
2026-04-30 11:26:37 +03:00
Yiorgis Gozadinos
191cdc636b
retrieve picture image bytes via referenced+zip path, fix docling-serve not returning images even when set to do so. Remove xfail from relevant test
2026-04-30 11:23:29 +03:00
Yiorgis Gozadinos
dc16f74b58
add picture_data column to document_items
2026-04-30 11:23:29 +03:00
Yiorgis Gozadinos
29bc42514e
vb
2026-04-29 13:45:36 +03:00
Yiorgis Gozadinos
5f08a2a8ae
Adapt rag SKILL.md in order to improve citation rate
2026-04-28 14:51:28 +03:00
Yiorgis Gozadinos
7685a592c2
bump haiku.skills to 0.16.0
2026-04-28 12:03:14 +03:00
Yiorgis Gozadinos
6807f082ec
vb
2026-04-25 09:35:47 +03:00
Tres Seaver
0d70f4aec6
fix: pass absolute 'db_path' to 'lancedb.connect_async'
...
Closes #354 .
2026-04-24 17:59:01 -04:00
Yiorgis Gozadinos
81ba248483
vb
2026-04-24 17:47:57 +03:00
Yiorgis Gozadinos
821b7361e9
Push document-id filter into chunk search query
2026-04-24 16:07:07 +03:00
Yiorgis Gozadinos
31fc22ce9d
List tables consistently
2026-04-24 15:57:07 +03:00
Yiorgis Gozadinos
cd4224a727
drop private title/embedding forwarders from HaikuRAG
2026-04-24 15:52:50 +03:00
Yiorgis Gozadinos
b23bad32c3
Check table_names() before dropping chunks in recreate_embeddings_table
2026-04-24 15:32:06 +03:00
Yiorgis Gozadinos
729899299b
Log post-rebuild vacuum failures and clarify vacuum-await scope
2026-04-24 15:31:36 +03:00
Yiorgis Gozadinos
258ffa41fa
Improve test coverage
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
aca3ccc29f
Close connections if __aenter__ fails mid-initialization
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
3224d1f20c
Extract document orchestration into client/documents.py
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
cb02a2c3d8
Extract rebuild machinery into client/rebuild.py
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
528acb79a3
Extract LLM agents into client/agents.py
2026-04-24 14:43:58 +03:00
Yiorgis Gozadinos
12939f1444
Extract search, expand_context, visualize_chunk into client/search.py
2026-04-24 14:43:58 +03:00
Yiorgis Gozadinos
d4ecebf896
Extract processing primitives into client/processing.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
b5e480bfa1
Extract title generation into client/titles.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
e814459e1f
Extract download_models into client/downloads.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
43f2774c14
Turn client.py into a client/ package
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
d0ed9e213f
Pin FTS search column to content_fts
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
a74c3a6f9e
Satisfy ty by adding a typed to_pydantic helper
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
b6ea07d2de
Track all in-flight background vacuum tasks, not just the last one
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
57385506c1
Fix is_new_db detection when create=True is passed on an existing DB
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
82fd10e0ee
Migrate LanceDB to native async API
...
Convert all LanceDB operations from sync calls wrapped in async
functions to the native async API (connect_async, AsyncConnection,
AsyncTable, AsyncQuery). Database I/O no longer blocks the event loop.
- Store and HaikuRAG use async context managers (async with). Store
initialization is deferred to __aenter__; direct construction
without async with is no longer supported.
- Index creation uses config objects (FTS, BTree, IvfPq) instead of
string-based index_type parameter.
- Upgrade callbacks are async.
- HaikuRAG tracks background vacuum tasks and awaits them in __aexit__
and before destructive rebuild operations to avoid races with
concurrent table mutations.
- temp_db_path fixture uses pytest's tmp_path for reliable async
cleanup.
2026-04-24 14:42:52 +03:00
Yiorgis Gozadinos
84c5391259
Merge pull request #353 from ggozad/feat/better-visual-highlight
...
Tone down the yellow colour in visual highlights
2026-04-24 14:41:27 +03:00
Yiorgis Gozadinos
cb9360ef7b
fix chat TUI citation rendering after state flattening
2026-04-24 13:48:57 +03:00
Yiorgis Gozadinos
a833e58d54
Tone down the yellow colour in visual highlights
2026-04-24 10:31:43 +03:00
Yiorgis Gozadinos
4f058bf484
vb
2026-04-22 17:00:03 +03:00
Yiorgis Gozadinos
ae2b8461be
flatten skill state citations from list[list[str]] to list[str]
2026-04-22 16:50:13 +03:00
