Commit graph

726 commits

Author SHA1 Message Date
Yiorgis Gozadinos
d267b2c433
LRU cache for DoclingDocument 2025-12-08 15:54:31 +02:00
Yiorgis Gozadinos
a5d8af07e9
Resolve DoclingDocument 2025-12-08 15:54:31 +02:00
Yiorgis Gozadinos
84aa46a10b
Update rebuild to handle DoclingDocument json 2025-12-08 15:54:31 +02:00
Yiorgis Gozadinos
ad4e79ab5d
Store DoclingDocument json 2025-12-08 15:54:31 +02:00
Yiorgis Gozadinos
343272d6fb
Chunkers return chunks with metadata, i.e. (refs, labels, headings, page_numbers) 2025-12-08 15:54:31 +02:00
Yiorgis Gozadinos
44e8d7b340
Update Document & Chunk schemas to include DoclingDocument references. 2025-12-08 15:54:30 +02:00
Yiorgis Gozadinos
e7f2981b13
Merge pull request #179 from ggozad/feat/client-download-models
Make download_models() a HaikuRAG client method, show updates in app.
2025-12-08 15:51:54 +02:00
Yiorgis Gozadinos
0dc4458070
Fix qa accuracy table for wix 2025-12-06 12:01:13 +02:00
Yiorgis Gozadinos
80447c9024
Make download_models() a HaikuRAG client method. Update app to show progress of what happens. 2025-12-04 16:30:26 +02:00
Yiorgis Gozadinos
e890add8cc
pyproject keywords 2025-12-03 08:59:22 +02:00
Yiorgis Gozadinos
4e30637d61
vb 2025-12-03 08:57:14 +02:00
Yiorgis Gozadinos
f631e74bf1
Merge pull request #176 from ggozad/fix/embedding-model-config
Always perform db upgrades, introduce `init` to create a db, update embeddings configuration.
2025-12-03 08:54:59 +02:00
Yiorgis Gozadinos
78f1d0cef5
No warnings, just info on db upgrade 2025-12-03 08:51:25 +02:00
Yiorgis Gozadinos
33b254ae3d
Always upgrade database on access. Explicitly create db by running init or HaikuRAG(path, create=True) 2025-12-02 16:49:55 +02:00
Yiorgis Gozadinos
47d8f7ba3f
Update docs 2025-12-02 12:01:10 +02:00
Yiorgis Gozadinos
3525fae625
Use EmbeddingModelConfig similar to ModelConfig for embeddings 2025-12-02 11:55:31 +02:00
Yiorgis Gozadinos
f07590bd5b
vb 2025-12-01 17:58:47 +02:00
Yiorgis Gozadinos
80ff2fa509
Merge pull request #174 from ggozad/fix/optimize-batch-update-chunks
Optimized `rebuild --embed-only` to use batch updates
2025-12-01 17:57:51 +02:00
Yiorgis Gozadinos
e548a51ff7
Optimized rebuild --embed-only to use batch updates via LanceDB merge_insert instead of individual chunk updates 2025-12-01 17:53:27 +02:00
Yiorgis Gozadinos
3e18a5f2ff
Update project description 2025-11-29 11:18:53 +02:00
Yiorgis Gozadinos
37c9d088af
Merge pull request #173 from ggozad/chore/improve-documentation
Improve documentation
2025-11-28 13:11:30 +02:00
Yiorgis Gozadinos
e10b207b47
Improve documentation 2025-11-28 13:10:03 +02:00
Yiorgis Gozadinos
5dfa07cb2c
Update benchmarks 2025-11-28 12:10:08 +02:00
Yiorgis Gozadinos
10aa2a7cf2
vb 2025-11-28 10:15:59 +02:00
Yiorgis Gozadinos
fc44cb2286
Merge pull request #171 from ggozad/feat/rebuild-options
New options for `rebuild` command to control what gets rebuilt
2025-11-28 10:13:37 +02:00
Yiorgis Gozadinos
88a4edb537
--embed-only, --rechunk options in rebuild command 2025-11-28 10:11:52 +02:00
Yiorgis Gozadinos
9302de0aff
Merge pull request #170 from ggozad/fix/docling-tables-local
Add opencv-python-headless to docling optional dependency, required for table detection.
2025-11-27 16:23:41 +02:00
Yiorgis Gozadinos
8a0cc04181
Add opencv-python-headless to docling optional dependency, required for TableStructureModel which uses TableFormer for table detection. 2025-11-27 16:22:37 +02:00
Yiorgis Gozadinos
eee29578ba
vb 2025-11-27 15:24:39 +02:00
Yiorgis Gozadinos
5d00bbf6dd
Merge pull request #169 from ggozad/fix/docling-fixes
Fix docling OCR options.
2025-11-27 15:24:02 +02:00
Yiorgis Gozadinos
b4602b0cab
use OcrAutoOptions for automatic OCR engine selection. 2025-11-27 15:23:17 +02:00
Yiorgis Gozadinos
51104ddb5a
Use httpx for docling-serve 2025-11-27 15:06:13 +02:00
Yiorgis Gozadinos
3959ce39f7
vb 2025-11-27 13:06:04 +02:00
Yiorgis Gozadinos
f6956341ec
Merge pull request #168 from ggozad/fix/async-fixes
Wrap synchronous calls to async.
2025-11-27 13:01:56 +02:00
Yiorgis Gozadinos
bdbd3ce556
cl 2025-11-27 10:43:23 +02:00
Yiorgis Gozadinos
ed53ec461a
Convert prefetch_models() to async 2025-11-26 18:08:48 +02:00
Yiorgis Gozadinos
e40c352026
Switch from requests to httpx.AsyncClient for docling-serve 2025-11-26 18:00:29 +02:00
Yiorgis Gozadinos
14bdb7cb27
async versions for convert_file() convert_text() 2025-11-26 17:46:25 +02:00
Yiorgis Gozadinos
6e24d5772b
Make sure haiku.rag always requires same version of haiku.rag-slim 2025-11-26 17:14:58 +02:00
Yiorgis Gozadinos
ca2445d869
vb 2025-11-26 10:33:46 +02:00
Yiorgis Gozadinos
e188051fb3
Merge pull request #164 from ggozad/feat/lm_studio
Support LMStudio
2025-11-26 10:32:11 +02:00
Yiorgis Gozadinos
0303e6a8cd
Support LMStudio 2025-11-26 10:31:40 +02:00
Yiorgis Gozadinos
7876830eca
Merge pull request #166 from ggozad/fix/init-config
Fix `init-config` command generating invalid configuration files
2025-11-26 10:30:44 +02:00
Yiorgis Gozadinos
d30ac60a75
cl 2025-11-26 10:29:00 +02:00
Yiorgis Gozadinos
5612ecaee7
Fix documentation configuration index 2025-11-26 10:24:53 +02:00
Yiorgis Gozadinos
283c44867d
Generate the config from the AppConfig model directly, add tests 2025-11-26 10:17:22 +02:00
Yiorgis Gozadinos
1008e6e10f
Fix broken links 2025-11-25 14:27:44 +02:00
Yiorgis Gozadinos
2c554a9350
Do not use private methods in tests 2025-11-25 14:19:28 +02:00
Yiorgis Gozadinos
c22a5bb0ce
vb 2025-11-25 13:44:48 +02:00
Yiorgis Gozadinos
b9f608a039
Merge pull request #163 from ggozad/feat/model-customizations
Support for per-model configuration settings such as thinking, temperature, max_tokens
2025-11-25 13:14:30 +02:00