Yiorgis Gozadinos
c7c3f75508
vb
2026-06-27 09:59:21 +03:00
Yiorgis Gozadinos
bd520cb995
Merge pull request #477 from ggozad/fix/limit-context-blowing-expansion
...
Hard-cap context expansion at max_context_chars
2026-06-27 09:58:25 +03:00
Yiorgis Gozadinos
b94e13083f
Hard-cap context expansion at max_context_chars
...
A single oversized document_items row (e.g. a spreadsheet converted to one
table) expanded far past search.max_context_chars and could overflow the
model context window. _expand_outward only used the budget as a soft
accumulation threshold and expand_with_items never capped the joined result.
Add _clip_to_budget to clip each expanded result to max_context_chars,
returning a window centered on the matched chunk (via _evidence_anchors) so
the retrieved evidence survives the cut.
2026-06-27 09:46:36 +03:00
Yiorgis Gozadinos
cd1a73b389
vb
2026-06-26 17:13:03 +03:00
Yiorgis Gozadinos
7cdf93e23a
Merge pull request #475 from ggozad/feat/document-similarity
...
Detect near-duplicate documents in `doctor`
2026-06-26 17:05:33 +03:00
Yiorgis Gozadinos
73f62ab290
Enforce the duplicate candidate cap during row collection
2026-06-26 16:57:51 +03:00
Yiorgis Gozadinos
f1e1a16f9b
Add doctor --duplicates-out YAML export; summarize terminal report
2026-06-26 16:52:22 +03:00
Yiorgis Gozadinos
044ac62e49
Drop boilerplate handling; make duplicate report readable
2026-06-26 16:52:22 +03:00
Yiorgis Gozadinos
961913dde4
Ignore boilerplate chunks in duplicate-document detection
2026-06-26 16:52:21 +03:00
Yiorgis Gozadinos
43f2130b66
Add near-duplicate document detection to doctor
2026-06-26 16:52:21 +03:00
Yiorgis Gozadinos
ce27a7aae5
Clean up S3 test data per-test to keep SeaweedFS writable
2026-06-26 16:41:20 +03:00
Yiorgis Gozadinos
98f2a088d8
Merge pull request #474 from ggozad/chore/dependabot-alerts
...
Security dependency updates
2026-06-26 15:28:49 +03:00
Yiorgis Gozadinos
1969c4528e
Fix example app
2026-06-26 13:12:53 +03:00
Yiorgis Gozadinos
5463a07d32
chore(deps): patch Dependabot security alerts
2026-06-26 10:55:26 +03:00
Yiorgis Gozadinos
9f45addbe9
Merge pull request #470 from ggozad/fix/dangling-workers
...
Lease-renewal reaping for ingester workers
2026-06-26 09:19:43 +03:00
Yiorgis Gozadinos
87f0233bcd
Cover heartbeat health, lease-renewal failure, and breaker recovery
2026-06-25 16:32:56 +03:00
Yiorgis Gozadinos
4333ab4fe2
Document lease-based ingester reaping
2026-06-25 13:28:25 +03:00
Yiorgis Gozadinos
4707db780f
Renew job leases from the worker pool; lease-based reaping
2026-06-25 13:26:09 +03:00
Yiorgis Gozadinos
fd73f57649
Add last_heartbeat_at lease column to the ingester queue
2026-06-25 13:25:37 +03:00
Yiorgis Gozadinos
ba6b318ece
Make ingester worker ids globally unique
2026-06-25 13:25:37 +03:00
Yiorgis Gozadinos
6bbf12e794
Merge pull request #469 from ggozad/fix/minor-issues
...
Minor config and FTS-index fixes
2026-06-25 13:21:00 +03:00
Yiorgis Gozadinos
b61134b747
Log FTS index build failures at WARNING
2026-06-25 13:00:29 +03:00
Yiorgis Gozadinos
2fd025951c
Treat empty env vars as unset in config expansion
2026-06-25 12:41:04 +03:00
Yiorgis Gozadinos
73beae5a4c
Harden MCP publisher install and bump action versions
2026-06-24 19:38:50 +03:00
Yiorgis Gozadinos
197d58a602
vb
2026-06-24 18:41:05 +03:00
Yiorgis Gozadinos
d66ecb4da2
Merge pull request #468 from ggozad/fix/fastmcp-pydantic-ai-2.0
...
Depend on fastmcp directly for the MCP server
2026-06-24 18:40:21 +03:00
Yiorgis Gozadinos
b343f3687d
Depend on fastmcp directly for the MCP server
2026-06-24 18:35:00 +03:00
Yiorgis Gozadinos
ab1775dbc6
vb
2026-06-24 16:45:19 +03:00
Yiorgis Gozadinos
af66af45a0
Merge pull request #467 from ggozad/perf/item-text-serializer-reuse
...
Reuse one MarkdownDocSerializer per document in item extraction
2026-06-24 15:13:06 +03:00
Yiorgis Gozadinos
9f4dda9254
Reuse one MarkdownDocSerializer per document in item extraction
2026-06-24 12:02:13 +03:00
Yiorgis Gozadinos
54ac3450b5
Merge pull request #465 from bd-mkt/perf_redundant_serialization
...
perf: avoid redundant serialization in docling ingestion path
2026-06-24 10:51:08 +03:00
Yiorgis Gozadinos
2b2b475279
Collapse docling compression to a single function
2026-06-24 10:43:27 +03:00
bryan davis
e95ac2e25d
remove redundant serialization
2026-06-24 10:42:58 +03:00
Yiorgis Gozadinos
e73a4272f8
Merge pull request #464 from bd-mkt/zstd_concurrency
...
adjust zstd handling to avoid possible core dumps with concurrency
2026-06-24 10:17:34 +03:00
Yiorgis Gozadinos
62d2326933
Use single-threaded zstd compressor
2026-06-24 10:08:25 +03:00
bryan davis
2ca12c0096
adjust zstd handling to avoid possible core dumps with concurrency
2026-06-23 15:26:33 -05:00
Yiorgis Gozadinos
65f1339aa0
vb
2026-06-23 16:59:00 +03:00
Yiorgis Gozadinos
0b822ee402
Merge pull request #463 from ggozad/chore/docling-update
...
Adapt docling-serve integration to docling-serve 1.25.0
2026-06-23 16:55:10 +03:00
Yiorgis Gozadinos
e1fbaf8aad
Re-record remaining docling-serve cassettes against 1.25.0
2026-06-23 16:44:58 +03:00
Yiorgis Gozadinos
3cc3c98986
Store docling-serve chunk bodies via raw_text
2026-06-23 16:35:21 +03:00
Yiorgis Gozadinos
68715c9657
Request page images explicitly from docling-serve
2026-06-23 16:15:02 +03:00
Yiorgis Gozadinos
f22341f003
Fix doctor's vector-index check to match documented guidance
2026-06-23 15:39:44 +03:00
Yiorgis Gozadinos
195dce7511
Merge pull request #462 from ggozad/fix/multi-modal-embedder-config
...
Decouple multimodal embedding from the provider name; add VoyageAI & Cohere multimodal embedders
2026-06-23 15:33:57 +03:00
Yiorgis Gozadinos
b098be790b
Document multimodal embedder flag and Voyage/Cohere providers
2026-06-23 15:23:10 +03:00
Yiorgis Gozadinos
3586ac30a7
Add Cohere multimodal embedder
2026-06-23 15:23:10 +03:00
Yiorgis Gozadinos
a1ec310bf4
Add VoyageAI multimodal embedder
2026-06-23 15:23:10 +03:00
Yiorgis Gozadinos
0ea251219c
Add explicit multimodal embedding flag, decoupled from provider name
2026-06-23 15:23:10 +03:00
Yiorgis Gozadinos
2c906b16cd
Merge pull request #461 from ggozad/feat/doctor
...
Add `haiku-rag doctor` health check
2026-06-23 14:43:22 +03:00
Yiorgis Gozadinos
4fae733a50
Fix doctor provider checks: custom endpoints and processing models
2026-06-23 11:48:21 +03:00
Yiorgis Gozadinos
eb855f827a
Refine doctor's content and coverage checks
2026-06-23 11:31:20 +03:00
