6c3475ca0e
chore: ingestion-pipeline refactor, sort technical debt, rustfmt
2026-05-31 19:48:41 +02:00
e9d8654324
chore: refactor retrieval pipeline to chunk-first RRF with derived entities and slimmer eval surface.
...
Collapse the multi-strategy entity engine into one benchmarked chunk retrieval path, derive entities from retrieved chunks, and update consumers, docs, and clippy fixes across the workspace.
2026-05-30 22:19:08 +02:00
920d7b5efb
chore: centralize embedding errors, retrieval strategy, and test DB helpers.
...
Replace anyhow in embedding production code with EmbeddingError, move
RetrievalStrategy into common config, and deduplicate Surreal test setup
via common::test_utils.
2026-05-29 14:44:23 +02:00
964d57ec97
test: cover system settings sync, validation, and ingestion prompts
...
Add tests for embedding provider sync, patch isolation, typed backend
serde, and DB-backed ingestion prompts.
2026-05-29 14:44:23 +02:00
544a790e34
chore: harden system settings and unify prompt usage
...
Validate settings updates, use typed embedding backends, and route
ingestion through DB-stored prompts so admin edits take effect.
2026-05-29 14:44:23 +02:00
2e2a26f5f1
chore: harden knowledge graph storage and clear common clippy warnings
...
Enforce stable 1:1 entity embeddings, relationship endpoint auth, and
user-scoped deletes; align schemas/migrations and resolve common crate
clippy findings.
2026-05-29 14:44:23 +02:00
4f02fcb853
chore: rename get_id to id, add doc comments, pre-allocate format_history
2026-05-27 18:06:16 +02:00
cd0d95abaa
fix: revoke_api_key sets NONE, remove unused bind, lowercase error msgs
...
- fix bug where revoke_api_key set literal 'test_string_nullish' instead of NONE
- remove unused table_name bind in update_timezone
- lowercase ~16 error messages across 4 crates
2026-05-27 13:56:32 +02:00
e2284b1e69
chore: removed anyhow from apperror for improved error handling
2026-05-27 13:33:02 +02:00
b8f7c826b4
perf: offload blocking calls to spawn_blocking
...
- Move headless_chrome PDF rasterization from async context to
spawn_blocking, keeping tokio worker threads responsive.
- Switch RerankerPool from tokio::sync::Mutex to std::sync::Mutex
and run TextRerank::rerank inside spawn_blocking, since the
rerank call is CPU-bound with no .await points.
2026-05-26 20:21:25 +02:00
5ce7a76c75
clippy: adhere to pedantic clippy, uniform test error handling
2026-05-26 20:21:13 +02:00
7c718712c9
refactor: replace Box<dyn Error> with anyhow::Result
...
- ingestion_pipeline::run_worker_loop returns anyhow::Result<()>
- api_router::ApiState::new returns anyhow::Result<Self>
- html_router::HtmlState::new_with_resources is infallible, returns Self
- main/server/worker binary entry points return anyhow::Result<()>
2026-05-26 20:14:11 +02:00
6c5297ec6e
chore: dep updates & kv-mem separation to test feature
...
docker builder update
2026-02-15 08:51:48 +01:00
8664abdf01
release: 1.0.0
...
fix: cargo dist
2026-01-11 20:35:01 +01:00
86270de873
tidying stuff up, dto for search
2025-12-20 22:30:31 +01:00
90bac299a3
passed wide smoke check
2025-12-10 13:54:08 +01:00
8121e04125
retrieval simplfied
2025-12-09 20:35:42 +01:00
6c458c97ce
retrieval: hybrid search, linear fusion
2025-12-04 12:48:59 +01:00
c60efb2af7
benchmarks: ready for hybrid revised
2025-12-03 11:38:07 +01:00
38cb2e5e24
fix: all tests now in sync
2025-11-29 18:59:08 +01:00
05bdaac672
evals: v3, ebeddings at the side
...
additional indexes
2025-11-26 15:15:10 +01:00
6611bf3645
retrieval-pipeline: v1
2025-11-19 12:58:27 +01:00
97d35a8982
retrieval-pipeline: v0
2025-11-18 22:46:35 +01:00
6f08429faa
benchmarks: v1
...
Benchmarking ingestion, retrieval precision and performance
2025-11-18 11:50:15 +01:00
3196e65172
fix: improved storage manager, prep for s3
2025-11-03 12:39:15 +01:00
72578296db
feat: reranking with fastembed added
2025-10-27 13:05:10 +01:00
07b3e1a0e8
refactor: implemented state machine for ingestion pipeline, improved performance
...
changelog
additional moving around
moved files around a bit
2025-10-20 13:08:00 +02:00
83d39afad4
refactor: implemented state machines for retrieval pipeline, improved tracing
2025-10-19 09:18:17 +02:00
3c97d8ead5
chore: clippy ingestion-pipeline
2025-10-16 20:36:39 +02:00
44e5d8a2fc
chore: clippy fixes
2025-10-16 20:29:15 +02:00
35ff4e1464
feat: manual entity creation
...
chore: clippy
2025-10-15 21:50:52 +02:00
dc40cf7663
feat: hybrid search
2025-10-14 20:38:43 +02:00
41fc7bb99c
feat: state machine for tasks, multiple workers
2025-10-12 22:21:20 +02:00
022f4d8575
fix: compliant with gpt-5 models
2025-10-01 10:17:31 +02:00
b0ed69330d
fix: improved concurrency
2025-09-28 22:08:08 +02:00
5cb15dab45
feat: pdf support
2025-09-28 20:53:51 +02:00
c2839f8db3
fix: somewhat improved concurrency
...
limiting edge creation to sequential due to surrealdb
2025-09-21 11:57:39 +02:00
6ea51095e8
design: neobrutalist_theme into main
2025-09-17 10:01:20 +02:00
69954cf78e
chore: clippy helps out
2025-09-06 21:00:39 +02:00
33300d3193
feat: handles submitted audio
2025-07-29 18:39:26 +02:00
ec16f2100c
fix: remove remnant job table, normalize taskstatus enum
2025-06-27 23:18:16 +02:00
43263fa77e
feat: completed image ingestion with system settings
...
styling
2025-06-27 21:48:29 +02:00
9a23c1ea1b
feat: image ingestion
2025-06-17 08:26:15 +02:00
a363c6cc05
feat: support for other providers of ai models
2025-06-06 23:16:41 +02:00
811aaec554
fix: graphmapper gracefully failing
2025-06-06 23:15:09 +02:00
5baab2f2a1
chore: centralized dependencies and cargo deny
...
chore: cargo licensing
2025-05-20 14:03:59 +02:00
bc7891a3e7
release: 0.1.1
...
fix: docker build dep
2025-05-13 22:23:49 +02:00
850878d5c3
feat: customizable data storage path
2025-05-09 23:28:36 +02:00
6ed49f7155
refactor: renamed instructions to context
2025-05-09 16:00:52 +02:00
322d1ec318
feat: docker & docker-compose example
2025-05-05 13:44:57 +02:00
Per Stark