Commit graph

404 commits

Author SHA1 Message Date
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
Yiorgis Gozadinos
c102d4ba15
Document a2a 2025-10-13 18:01:22 +03:00
Yiorgis Gozadinos
63f0e01f60
Remove shell autocompletion. Closes #96 2025-10-13 18:00:07 +03:00
Yiorgis Gozadinos
0991df6d9e
Make it possible to override the QA agent system prompt using the client 2025-10-07 13:15:58 +03:00
Yiorgis Gozadinos
95297432eb
Doc updates 2025-10-07 12:33:14 +03:00
Yiorgis Gozadinos
c6eaf9d5cd
Add vacuum retention setting 2025-10-07 10:47:28 +03:00
Yiorgis Gozadinos
6f181e07ff
Add Success@K metrics to retrieval benchmarks 2025-10-06 14:54:17 +03:00
Yiorgis Gozadinos
a6275fcf25
Rename nodes to make it clear they are part of Q/A 2025-09-30 16:59:36 +03:00
Yiorgis Gozadinos
49eac86259
Add verbose flag to ask 2025-09-30 16:59:36 +03:00
Yiorgis Gozadinos
2dfb1882dd
Deep QA multi-agent 2025-09-30 16:59:36 +03:00
Yiorgis Gozadinos
43b9cd50ba
Move evaluations to src/ 2025-09-30 13:21:53 +03:00
Yiorgis Gozadinos
06dbdbd474
Update docs for wix benchmarks 2025-09-30 11:31:52 +03:00
Yiorgis Gozadinos
6f20d9fd6d
Update recall of qwen3 embeddings with mxbai reranking 2025-09-30 11:31:51 +03:00
Yiorgis Gozadinos
842e166041
Adapt how we measure recall when using datasets with multiple sources 2025-09-30 11:31:51 +03:00
Yiorgis Gozadinos
57e86d00fd
Refactor evaluations so that we can perform with multiple datasets..
Introduce Wix dataset.
2025-09-30 11:31:50 +03:00
Yiorgis Gozadinos
87f28ed96b
Update docs 2025-09-30 11:30:35 +03:00
Yiorgis Gozadinos
f0333e33ac
Change default embedding to qwen3-embedding. Update benchmarks using qwen3-embedding and gpt-oss 2025-09-26 13:23:38 +03:00
Yiorgis Gozadinos
064b823020
Break Evaluation node into AnalyzeInsights & DecisionNode. Use a list of updateable insights & gaps 2025-09-24 16:26:48 +03:00
Yiorgis Gozadinos
57bac178dd
Update docs 2025-09-24 13:43:49 +03:00
Yiorgis Gozadinos
8f3055d37d
Parse non-strings 2025-09-23 16:42:40 +03:00
Yiorgis Gozadinos
45d0b47a02
Meta in CLI add-src, add 2025-09-23 16:39:27 +03:00
Yiorgis Gozadinos
0e1bf3e00d
CLI command to prefetch models (Ollama & Docling) 2025-09-23 16:30:56 +03:00
Yiorgis Gozadinos
5369bd5dda
Show db table versions 2025-09-23 12:44:05 +03:00
Yiorgis Gozadinos
c0de22c9cd
Show package versions 2025-09-23 12:34:32 +03:00
Yiorgis Gozadinos
52ea1ebb70
info command in CLI 2025-09-23 12:20:25 +03:00
Yiorgis Gozadinos
8e2829bf0e
Documentation update for title 2025-09-22 12:45:32 +03:00
Yiorgis Gozadinos
c11e6da60d
Merge pull request #68 from ggozad/feat/disable-autocreation
DISABLE_DB_AUTOCREATE option to prevent auto-creation of dbs
2025-09-22 12:43:51 +03:00
Yiorgis Gozadinos
6b7f574180
Config DISABLE_DB_AUTOCREATE option to not auto-create dbs 2025-09-22 10:09:07 +03:00
Yiorgis Gozadinos
dce60fa461
Remove SSE transport, fix cli tests 2025-09-20 10:58:28 +03:00
Yiorgis Gozadinos
9daf14fd42
Research graph diagram 2025-09-19 16:28:03 +03:00
Yiorgis Gozadinos
cba8ad7696
Research agent as a pydantic graph 2025-09-19 14:39:39 +03:00
Yiorgis Gozadinos
a215a64686
Refactor to give its research subagent full responsibility 2025-09-19 12:10:00 +03:00
Yiorgis Gozadinos
ccaae7cca1
Simplify research verbose logging 2025-09-19 12:10:00 +03:00
Yiorgis Gozadinos
714c6c627e
Presearch Survey agent 2025-09-17 17:26:48 +03:00
Yiorgis Gozadinos
ad80b52759
Update documentation 2025-09-17 12:51:43 +03:00
Yiorgis Gozadinos
4a07444030
Rollback version if a failure occurs when creating/updating documents 2025-09-15 11:54:50 +03:00
Yiorgis Gozadinos
765a6e647d
Allow for custom pre-processing after markdown is generated and before it is chunked. 2025-09-15 11:02:34 +03:00
Yiorgis Gozadinos
d90dfe258c
Use logfire when running evaluations 2025-09-12 09:45:06 +03:00
Yiorgis Gozadinos
455d90684b
Update docs 2025-09-10 11:46:02 +03:00
Yiorgis Gozadinos
13bbdc2ed6
Document autocomplete, add rm alias to delete 2025-09-05 12:04:20 +03:00
Yiorgis Gozadinos
bc28e60cf7
Support vLLM for QA agents 2025-09-04 15:20:37 +03:00
Yiorgis Gozadinos
f2847d0524
Reranking support for vLLM, documentation update 2025-09-04 13:13:10 +03:00
Yiorgis Gozadinos
221a00ab2f
Turn migration into a cli command 2025-09-03 11:12:23 +03:00
Yiorgis Gozadinos
b73949c784
update benchmarks 2025-09-02 15:10:57 +03:00
Yiorgis Gozadinos
9e5f11060d
Allow connecting to lancedb cloud, s3, gc, az etc 2025-09-02 12:49:17 +03:00
Yiorgis Gozadinos
fe850e778d
Remove Ollama reranker, this was a bad idea 2025-09-02 11:42:31 +03:00
Yiorgis Gozadinos
27b16bdf8d
Update basic benchmarks 2025-09-02 10:51:20 +03:00
Yiorgis Gozadinos
b05e5f5408
Set/get haiku version to db 2025-09-01 17:41:41 +03:00
Yiorgis Gozadinos
58a04db556
Disable reranking by default 2025-09-01 15:00:38 +03:00
Yiorgis Gozadinos
628bdc8151
Cleanup 2025-09-01 14:56:15 +03:00
Yiorgis Gozadinos
c69daecf53
update docs 2025-09-01 14:56:14 +03:00
Yiorgis Gozadinos
1f61d78165
Bring back QA_MODEL and keep compatibility with previous versions 2025-08-17 15:27:03 +02:00
Yiorgis Gozadinos
d6d79d5e94
Allow any provider/model supported by pydantic AI 2025-08-17 14:55:50 +02:00
Yiorgis Gozadinos
4e2e6e490e
Update extras and docs 2025-08-15 21:44:33 +02:00
Yiorgis Gozadinos
bf8a4f22be
Make radius a parameter we can pass to expand_context() 2025-08-12 16:53:45 +02:00
Yiorgis Gozadinos
99f7401817
Merge expanded context if possible 2025-08-12 15:02:07 +02:00
Yiorgis Gozadinos
e7c2a105ed
Use the expand_context when searching in the qa agent 2025-08-12 14:51:33 +02:00
Yiorgis Gozadinos
842e4a882d
Make citations optional, through cite parameter 2025-08-12 13:19:11 +02:00
Yiorgis Gozadinos
ffe867f7bb
Allow to disable reranking by having an empty provider 2025-08-10 21:02:17 +02:00
Yiorgis Gozadinos
5103e6c2d7
Add Ollama reranker 2025-08-10 20:50:17 +02:00
Yiorgis Gozadinos
8d98eed2e2
Make mxbai reranker optional. Only use a reranker if mxbai or cohere are installed 2025-08-10 19:49:14 +02:00
Yiorgis Gozadinos
91f6122ef7
Basic chunking using docling 2025-08-01 16:27:44 +02:00
Yiorgis Gozadinos
5a08816ed6
Replace markitdown with docling 2025-08-01 09:59:53 +02:00
Yiorgis Gozadinos
74eea9284a
create_document now optionally accepts pre-computed chunks 2025-07-26 10:42:27 +03:00
Yiorgis Gozadinos
4908ea9fcc
Update benchmarks 2025-07-20 22:45:24 +03:00
Yiorgis Gozadinos
ad9879802a
Fix incorrect syntax for uv pip install with extras 2025-07-20 22:40:12 +03:00
Yiorgis Gozadinos
942be2271c
Update docs 2025-07-20 11:33:09 +03:00
Yiorgis Gozadinos
c1d5334804
Update benchmarks with reranking 2025-07-19 19:02:47 +03:00
Yiorgis Gozadinos
a6595b1597
Update docs 2025-07-19 13:16:09 +03:00
Yiorgis Gozadinos
a2d7e527d1
Update docs on configuration changes 2025-07-14 12:00:03 +03:00
Yiorgis Gozadinos
eefd51ead6
Update mxbai recall stats 2025-07-09 12:50:39 +03:00
Yiorgis Gozadinos
42e62f92a1
Better formatting of benchmark script 2025-07-09 10:27:32 +03:00
Yiorgis Gozadinos
9d72a158a6
Document benchmarks 2025-07-08 19:01:54 +03:00
Yiorgis Gozadinos
2f261a33f5
Allow multiple tool calling rounds in QA agent 2025-07-08 12:51:58 +03:00
Yiorgis Gozadinos
b28ed57cf5
Update docs 2025-07-04 11:55:04 +03:00
Yiorgis Gozadinos
27e1c9fd49
Show settings command 2025-07-04 11:54:16 +03:00
Yiorgis Gozadinos
fb837ede69
Documentation 2025-07-02 11:17:16 +03:00
Yiorgis Gozadinos
273a3bda4f
Document QA 2025-06-28 09:37:59 +03:00
Yiorgis Gozadinos
7a1b09d5e2
Minor doc fixes 2025-06-27 20:08:51 +03:00
Yiorgis Gozadinos
cf9ec04170
Fix docs 2025-06-26 11:46:23 +03:00
Yiorgis Gozadinos
a704f300bc
Initial skeleton for docs 2025-06-25 20:16:08 +03:00