Commit graph

230 commits

Author SHA1 Message Date
Yiorgis Gozadinos
a1162f8020
rebase from main 2025-12-08 16:07:50 +02:00
Yiorgis Gozadinos
06b4f6a224
Add format parameter for text-to-DoclingDocument conversion 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
0ea3717497
Update docs 2025-12-08 15:56:02 +02:00
Yiorgis Gozadinos
17c7147a49
Remove pre-processor, no longer needed 2025-12-08 15:56:01 +02:00
Yiorgis Gozadinos
33e6a36290
Make document import/update handling consistent for DoclingDocument 2025-12-08 15:55:29 +02:00
Yiorgis Gozadinos
60ab864fc1
Add docling_document_json to update_document_fields() and 2025-12-08 15:55:29 +02:00
Yiorgis Gozadinos
8e30f67266
Introduce import_document(), remove chunks from create_document() 2025-12-08 15:55:29 +02:00
Yiorgis Gozadinos
fe551066d8
Visual grounding docs 2025-12-08 15:55:29 +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
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
3e18a5f2ff
Update project description 2025-11-29 11:18:53 +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
88a4edb537
--embed-only, --rechunk options in rebuild command 2025-11-28 10:11:52 +02:00
Yiorgis Gozadinos
0303e6a8cd
Support LMStudio 2025-11-26 10:31:40 +02:00
Yiorgis Gozadinos
5612ecaee7
Fix documentation configuration index 2025-11-26 10:24:53 +02:00
Yiorgis Gozadinos
e83978f88b
Revert embeddings to use flat config 2025-11-25 12:51:58 +02:00
Yiorgis Gozadinos
ba4dddeeaf
Make thinking false by default 2025-11-25 12:35:38 +02:00
Yiorgis Gozadinos
a9701616c8
Rename model to name under model 2025-11-25 12:28:43 +02:00
Yiorgis Gozadinos
41ea675964
Update and restructure docs 2025-11-25 12:14:24 +02:00
Yiorgis Gozadinos
4e1752a740
Default eval db location, evaluation script 2025-11-25 11:07:20 +02:00
Yiorgis Gozadinos
13d3a366e8
Enhanced ActivitySnapshot events with richer structured data 2025-11-24 16:18:27 +02:00
Yiorgis Gozadinos
b5892699a0
Use Mean Reciprocal Rank for single document evaluation as metric. Use Mean Average Precision for variable document evaluation as metric 2025-11-24 14:49:30 +02:00
Yiorgis Gozadinos
b4c6f117a4
Merge pull request #155 from ggozad/feat/inspect
TUI db inspector
2025-11-22 17:53:49 +02:00
Yiorgis Gozadinos
727efe6b71
Update screenshot 2025-11-22 17:51:06 +02:00
Yiorgis Gozadinos
0b92eae75f
Docs 2025-11-22 17:46:21 +02:00
Yiorgis Gozadinos
fe14e73514
Benchmarks for win qwen3-embedding:4b mxbai-rerank-base-v2 2025-11-21 18:57:07 +02:00
Yiorgis Gozadinos
8c02e865c7
Change default embedding model to qwen3-embedding:4b 2025-11-21 16:30:41 +02:00
Yiorgis Gozadinos
28088aa31d
Merge pull request #148 from ggozad/feat/vector-index
Vector indexing & Search accuracy improvements
2025-11-21 16:28:45 +02:00
Yiorgis Gozadinos
6d8ab2575d
Clarify refine_factor, set default to 30 2025-11-21 15:53:24 +02:00
Yiorgis Gozadinos
9a1e7f211c
Update benchmarks 2025-11-21 15:31:36 +02:00
Yiorgis Gozadinos
dbb2837550
Add a note explaining when indexing is necessary 2025-11-21 14:11:31 +02:00
Yiorgis Gozadinos
5477446c5d
Update docs 2025-11-21 13:54:04 +02:00
Yiorgis Gozadinos
6a2f33b464
Create vector index from CLI, use configurable refine_factor 2025-11-21 13:54:01 +02:00
Yiorgis Gozadinos
63b374c7e9
Name evaluation runs. Use only LLMJudge evaluator. 2025-11-21 13:26:39 +02:00
Yiorgis Gozadinos
5089ea4203
New update_document_fields() method for partial document updates 2025-11-19 11:37:36 +02:00
Yiorgis Gozadinos
0bb3f4301c
Additional options for document conversion with docling 2025-11-18 15:44:04 +02:00
Yiorgis Gozadinos
f728fea489
Stop building full docker image 2025-11-18 14:48:34 +02:00
Yiorgis Gozadinos
cc09ce87c2
Increase reranking candidate retrieval multiplier from 3x to 10x for improved result quality 2025-11-18 14:35:57 +02:00
Yiorgis Gozadinos
d197fb5a35
Update docker example & relevant docs 2025-11-17 14:21:08 +02:00
Yiorgis Gozadinos
973522ffe2
Documentation 2025-11-17 13:07:46 +02:00
Yiorgis Gozadinos
dcba9d9a0e
Benchmarks for qwen3-embedding:0.6b 2025-11-14 15:36:36 +02:00
Yiorgis Gozadinos
4599dd1481
Drop disable_auto_create flag, simply create only on write operations 2025-11-13 13:53:11 +02:00
Yiorgis Gozadinos
8e802d4a91
Default vacuum_retention_seconds increased from 60 seconds to 86400 seconds (1 day) for better version retention in typical workflows 2025-11-13 13:31:53 +02:00
Yiorgis Gozadinos
032625b0bb
Refactor everything graph-related under the graph module 2025-11-13 13:22:03 +02:00
Yiorgis Gozadinos
8f0597e89e
Update deep ask graph 2025-11-13 13:22:03 +02:00
Yiorgis Gozadinos
ed27acc1a2
Update docs 2025-11-13 13:22:02 +02:00
Yiorgis Gozadinos
9ee64a33e0
Remove A2A from haiku.rag, turn it into an example 2025-11-07 13:31:51 +02:00
Yiorgis Gozadinos
0b696d9629
Remove deprecated use of env variables for configuration 2025-11-07 10:54:32 +02:00
Yiorgis Gozadinos
b51283c647
Use haiku.rag.yaml as the default config filename everywhere 2025-11-07 10:42:57 +02:00
Yiorgis Gozadinos
3c557d5bfe
Make --config a global CLI parameter, add it as a param to HaikuRAGApp 2025-11-07 10:31:55 +02:00
Yiorgis Gozadinos
782fbafb3d
Make graph settings part of config for both deep ask and research graphs 2025-11-06 14:31:22 +02:00
Yiorgis Gozadinos
fa93226a28
Update docs 2025-11-06 11:02:33 +02:00
Yiorgis Gozadinos
17d6a1dfee
Bring back max_concurrency by means of asyncio.Semaphore 2025-11-06 11:02:32 +02:00
Yiorgis Gozadinos
6858760bca
Remove max_concurrency, not supported (yet) when we .map() in the beta Graph API 2025-11-06 11:02:32 +02:00
Yiorgis Gozadinos
ef5e829bdc
Update docs 2025-11-05 12:56:03 +02:00
Yiorgis Gozadinos
106945ddc0
Update tutorial 2025-11-05 12:48:14 +02:00
Yiorgis Gozadinos
700e7c94e0
Update docs 2025-11-04 18:49:57 +02:00
Yiorgis Gozadinos
2f9c907031
Restructure into uv workspace to support minimal and full installations 2025-11-04 17:59:12 +02:00
Yiorgis Gozadinos
1f22f74e1a
Add filtering to document listing in CLI/client 2025-11-04 16:02:58 +02:00
Yiorgis Gozadinos
baedf65415
Fix typo, thanks @bd_mkt 2025-10-30 16:31:55 +02:00
Yiorgis Gozadinos
a7fd41d24f
Document passing config files when running evaluations 2025-10-30 15:17:02 +02:00
Yiorgis Gozadinos
5c7c79397c
Merge pull request #125 from ggozad/feat/filtering
Filtered searches
2025-10-30 14:28:42 +02:00
Yiorgis Gozadinos
6e0587c40e
Merge pull request #124 from ggozad/fix/add-src-monitor-filter
Apply configured include/exclude filters when using CLI's add-src to add a directory
2025-10-30 14:27:00 +02:00
Yiorgis Gozadinos
2f00686605
Support for zero entropy reranker 2025-10-30 13:36:44 +02:00
Yiorgis Gozadinos
f0f844d21d
Update documentation 2025-10-30 13:07:13 +02:00
Yiorgis Gozadinos
79d3559f15
Apply configured include/exclude filters when using CLIs add-src to add a directory recursively 2025-10-29 14:55:00 +02:00
Yiorgis Gozadinos
5a7d90ce9f
Change default location for config from XDG statndatd to use the platform-specific folder we use for the db as well 2025-10-29 11:50:30 +02:00
Yiorgis Gozadinos
4e19753d0f
Improve config docs 2025-10-29 11:50:22 +02:00
Yiorgis Gozadinos
ad1ee52a27
Move monitor config in its own section 2025-10-29 11:23:56 +02:00
Yiorgis Gozadinos
e6e3273cae
Document include/exclude patterns in FileMonitor 2025-10-29 10:50:25 +02:00
Yiorgis Gozadinos
8ddc966bf9
Respect OLLAMA_BASE_URL in providers.ollama.base_url config 2025-10-28 09:26:57 +02:00
Yiorgis Gozadinos
9f3eb1b79c
Remove docs references to env vars 2025-10-27 10:42:24 +02:00
Yiorgis Gozadinos
9c8ffcc212
Drop ConfigProxy in favour of passing AppConfig as an keyword param to HaikuRag clients. 2025-10-27 10:33:33 +02:00
Yiorgis Gozadinos
110cc447e7
Update documentation to remove references to env variables and replace with yaml config 2025-10-23 15:56:34 +03:00
Yiorgis Gozadinos
52fbac06e4
Use a proxy for the global Config so we can set it programmatically 2025-10-23 15:51:09 +03:00
Yiorgis Gozadinos
268c26eb4e
Drop support for using comma separated values in monitor_directories, only use that logic when converting from env vars 2025-10-23 14:09:20 +03:00
Yiorgis Gozadinos
469d993542
Remove provider API keys from config, rely on environment variables for those 2025-10-23 13:52:57 +03:00
Yiorgis Gozadinos
0fbe8cc516
Update documentation 2025-10-23 11:58:47 +03:00
Yiorgis Gozadinos
8e0fbc80fc
Remove sqlite migration from next version 2025-10-23 10:47:24 +03:00
Yiorgis Gozadinos
586f342a77
Fix typos 2025-10-20 19:22:25 +03:00
Mikko Ohtamaa
7e2ecf0636
Typo 2025-10-20 19:11:41 +03:00
Mikko Ohtamaa
623b234346
Polish tutorial 2025-10-20 19:11:40 +03:00
Mikko Ohtamaa
e5e435e028
Adding end to end tutorial 2025-10-20 19:11:40 +03:00
Yiorgis Gozadinos
c7e84aa2da
Merge pull request #111 from ggozad/feat/ag-ui-example
Full AG-UI integration example featuring an interactive frontend doing research
2025-10-20 17:41:31 +03:00
Yiorgis Gozadinos
3f7e410fc4
Add link to vimeo 2025-10-20 17:33:38 +03:00
Yiorgis Gozadinos
1ab15decf6
Update docs 2025-10-20 16:46:55 +03:00
Mikko Ohtamaa
47d0b7851e
Update Python version requirement to 3.12 2025-10-17 16:24:23 +02:00
Yiorgis Gozadinos
b9c22e634c
Update docs to refer to docker 2025-10-16 17:25:02 +03:00
Yiorgis Gozadinos
81c41ff66c
Fix doc typo 2025-10-14 13:36:47 +03:00
Yiorgis Gozadinos
34b3e9969f
Interactive client 2025-10-14 11:55:47 +03:00
Yiorgis Gozadinos
c562aa0551
Fix typos 2025-10-14 09:57:52 +03:00
Yiorgis Gozadinos
c0691bc237
Remove list documents, make separate artifacts for q/a, search & get document 2025-10-13 18:01:24 +03:00
Yiorgis Gozadinos
1f2552bd6a
Make serve cli command run monitor, mcp or a2a independently 2025-10-13 18:01:24 +03:00
Yiorgis Gozadinos
fce68a6673
Document securing a2a 2025-10-13 18:01:23 +03:00
Yiorgis Gozadinos
48cdb8a1db
Implement an LRUMemoryStorage for context 2025-10-13 18:01:22 +03:00