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
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
af7731f4e1
bulk-fetch items.jsonl via lazy cache to avoid per-document query timeout
2026-04-20 14:25:16 +03:00
Yiorgis Gozadinos
167c837514
repository methods, module-level executor, read-only VFS
2026-04-20 11:57:39 +03:00
Yiorgis Gozadinos
a1181ff52d
extract get_database_stats and share it across info, inspector, and backend
2026-04-17 15:33:30 +03:00
Yiorgis Gozadinos
d3c8ed62a8
preserve original chunk when expansion produces less content
2026-04-16 12:11:54 +03:00
Yiorgis Gozadinos
e2bac1e887
deduplicate escape_sql_string into utils
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
b6113bf8ab
replace fixed-radius expansion with section-bounded algorithm
...
Context expansion is now automatic and structure-aware. For structured
documents, expands within the section containing the match. For sections
that exceed the budget or are too small, expands item-by-item outward
skipping noise labels. Unstructured documents use budget-based outward
expansion. Results sorted by relevance score.
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
364b1bc509
add document_items table for fast context expansion
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
a118ee7aaa
Cleanup
2026-04-08 14:19:33 +03:00
Yiorgis Gozadinos
8e876ef28d
For remote stores, detect new db by checking if tables exist
2026-04-08 14:19:10 +03:00
Yiorgis Gozadinos
110accb8e7
Add ConnectionMode enum (LOCAL/CLOUD/OBJECT_STORAGE) and connect_lancedb() utility to support S3, GCS, Azure, and HDFS backends via storage_options.
2026-04-08 14:19:09 +03:00
Yiorgis Gozadinos
3fe953eccb
Minor fixes
2026-04-08 14:04:32 +03:00
Yiorgis Gozadinos
9c5bef163e
Use zstandard get_frame_parameters for max_output_size
2026-04-08 14:04:32 +03:00
Yiorgis Gozadinos
89e2a303e6
migration to split pages and re-compress with zstd
2026-04-08 14:04:32 +03:00
Yiorgis Gozadinos
53445b8722
Add docling_pages column to DocumentRecord/Document for separate page image storage.
2026-04-08 14:04:32 +03:00
Yiorgis Gozadinos
b614ef19e1
switch compression from gzip to zstd, use stdlib for python >= 3.14
2026-04-08 14:04:32 +03:00
Yiorgis Gozadinos
8a24606784
Strip page images from DoclingDocument before validation, unless we use visualize_chunk()
2026-04-07 12:54:23 +03:00
Yiorgis Gozadinos
68c3fa0f79
Add order to SearchResult, add ChunkRepository.get_chunks_in_range(), to use them in _expand_with_chunks to fetch only nearby chunks
2026-04-07 12:04:05 +03:00
Yiorgis Gozadinos
6fdb15e3b2
Add DocumentRepository.get_docling_data() for lazy loading docling in expand_context
2026-04-07 11:19:04 +03:00
Yiorgis Gozadinos
52712dbdb2
Use .select() projection to fetch only id/uri/title/metadata in search
2026-04-07 11:04:40 +03:00
Yiorgis Gozadinos
ce320ca772
Update docling, docling-core and move to version 1.10.0 of DoclingDocument.
2026-03-23 17:34:06 +02:00
Tres Seaver
53481a7d7a
chore: suppress deprecation wwarning from 'lancedb'
2026-03-12 17:11:58 -04:00
Yiorgis Gozadinos
b8c377da1e
Prevent read-only mode from creating tables in empty directories
2026-03-12 11:42:04 +02:00
Yiorgis Gozadinos
d1fdbdeb21
Refactor MCP to use proper models, test
2026-02-20 17:39:02 +02:00
Yiorgis Gozadinos
8c2a101a8a
Fix out-of-memory in list_documents by adding column projection
2026-02-06 14:11:36 +01:00
Yiorgis Gozadinos
4241a4b09e
Security fixes for RLM. Fix type() builtin, AST validation for dict key access, sql injection
2026-02-06 12:07:19 +01:00
Yiorgis Gozadinos
626f5cdd0e
Make list_documents return structured output and give feedback about total count and pages
2026-01-27 17:00:39 +02:00
Yiorgis Gozadinos
b4c158ffcf
Fix potential 0.25.0 migration crash
2026-01-22 17:29:26 +02:00
Yiorgis Gozadinos
7f51c63ad7
Search results now show rank position instead of raw scores. Consolidate cassettes
2026-01-21 14:54:15 +02:00
Yiorgis Gozadinos
5e55c0df54
replace pyright with ty type checker
2026-01-19 15:50:14 +02:00
Yiorgis Gozadinos
5464d24483
require explicit migrate command for database migrations
2026-01-19 13:22:09 +02:00
Yiorgis Gozadinos
fae274a04d
Remove defensive checks in info()
2026-01-15 10:30:45 +02:00
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
061095e855
Remove obsolete migrations
2026-01-12 12:07:49 +02:00
Yiorgis Gozadinos
29c682d8eb
Add migration
2026-01-11 11:40:57 +02:00
Yiorgis Gozadinos
afc5b02285
Update schema to store docling_document as compressed bytes
...
- Change DocumentRecord.docling_document_json (str) to docling_document (bytes)
- Use large_binary Arrow type (64-bit offsets) to avoid 2GB column limit
- Decompress in Document.get_docling_document() using gzip
- Update DocumentRepository field mappings
2026-01-10 15:17:27 +02:00
Yiorgis Gozadinos
face6f95bc
compression utils
2026-01-10 15:11:58 +02:00
Yiorgis Gozadinos
c9cb005d07
Use FTS on contextualized text
2025-12-29 14:50:07 +02:00
Yiorgis Gozadinos
132b8a36bc
Differentiate between embedding a query and a document
2025-12-24 12:43:11 +02:00
Yiorgis Gozadinos
1e5eebfbf0
Checkout version logic and datetime utils
2025-12-19 12:03:16 +02:00
Yiorgis Gozadinos
1a8f72f99a
Add is_read_only property to Store. Guard all write operations in repositories
2025-12-18 15:55:24 +02:00
Yiorgis Gozadinos
5c4799164c
Escape when getting by URI
2025-12-12 10:56:37 +02:00
Yiorgis Gozadinos
448d00f9b2
Add pagination to chunk repo's get_by_document_id
2025-12-11 15:38:19 +02:00
Yiorgis Gozadinos
1b14a4643d
Remove unused bounding box calculations
2025-12-08 15:56:21 +02:00
Yiorgis Gozadinos
9a5f8e4368
Add type-aware context expansion for search results
2025-12-08 15:56:21 +02:00
Yiorgis Gozadinos
4f0f214f26
Remove unecessary tests, add no coverage pragmas where appropriate
2025-12-08 15:56:02 +02:00
Yiorgis Gozadinos
2572125804
Move embedding logic from ChunkRepository to client._ensure_chunks_embedded()
2025-12-08 15:56:02 +02:00
