Chris McDonough
7d80eb4f83
Fix discover() crash when file is deleted during stat()
...
A file deleted between os.walk() and path.stat() raises
FileNotFoundError, which propagated uncaught and failed the entire
discover() sweep. With enough failures this trips the circuit
breaker, silencing the poller.
Catch FileNotFoundError around the stat() call and skip the file.
The next sweep (or watchfiles) will emit the DELETE event.
2026-06-01 07:29:51 -04:00
Chris McDonough
a6b3e7f1f6
Stagger periodic poll sweeps to avoid thundering herd
...
All pollers sharing the same poll_interval_s previously woke up and
swept at exactly the same moment after startup. With 10+ sources
this causes a coordinated spike in listing traffic (S3 LIST, WebDAV
PROPFIND, HTTP HEAD) every interval.
Add a random initial delay of 0-25% of the poll interval after the
first sweep, applied to both PeriodicPoller and FSPoller's sweep
loop. Subsequent sweeps run on the normal fixed interval, now
staggered across sources.
2026-06-01 07:02:42 -04:00
Chris McDonough
07c5a97929
Reuse httpx.AsyncClient across requests in HTTP and WebDAV sources
...
HTTPSource and WebDAVSource previously created a new AsyncClient for
every head(), fetch(), and discover() call — no connection reuse, TLS
renegotiation on every request, and connection pool churn at scale.
Create the client once in __init__ and reuse it for the lifetime of
the source. Add aclose() to both sources, called by PollerManager on
shutdown to cleanly close the connection pool.
2026-06-01 07:00:15 -04:00
Chris McDonough
48826031ac
Add partial indexes for has_pending() and dashboard throughput queries
...
has_pending() scans jobs WHERE source_id=? AND status IN
('queued','claimed') on every poller sweep — without an index this
is a full table scan as the jobs table grows. Similarly,
count_succeeded_since() scans by completed_at for the dashboard's
rolling-throughput display.
Add two partial indexes:
- idx_jobs_pending_by_source: covers has_pending() lookups
- idx_jobs_succeeded_completed: covers count_succeeded_since()
Both use CREATE INDEX IF NOT EXISTS so they're idempotent on
existing databases.
2026-06-01 06:28:55 -04:00
Chris McDonough
4fa8a012b4
Use asyncio.Condition for event-driven worker wakeup
...
Workers previously polled the queue with a fixed 1s sleep between
claim attempts, adding ~500ms average latency to job pickup. Now
JobRepo.job_available (an asyncio.Condition) is notified on every
successful enqueue, waking idle workers immediately. The poll
interval remains as a timeout fallback for stop signals and breaker
state changes.
2026-06-01 06:28:16 -04:00
Yiorgis Gozadinos
5a23e4eda6
Surface failed discovery sweeps in run-batch
2026-06-01 10:27:31 +03:00
Yiorgis Gozadinos
6f2a40c676
cover run-batch, serve, and _stop_pool with tests
2026-05-29 17:43:58 +03:00
Yiorgis Gozadinos
5ba7838b71
Add haiku-ingester run-batch, remove run-once
2026-05-29 17:00:59 +03:00
Yiorgis Gozadinos
62be23d130
vb
2026-05-29 11:47:12 +03:00
Yiorgis Gozadinos
e7c7df2915
Always use the Store-owned embedder
2026-05-29 11:36:53 +03:00
Yiorgis Gozadinos
37a78a4e9b
Cache reranker on the client instead of rebuilding per search
2026-05-29 10:33:50 +03:00
Yiorgis Gozadinos
402957d3e5
Fix CI flakes for PDF attachment extraction
2026-05-28 17:51:02 +03:00
Yiorgis Gozadinos
8e8c4433bd
Extract PDF /EmbeddedFiles attachments as child documents
2026-05-28 15:51:32 +03:00
Yiorgis Gozadinos
26bc71d6d8
Cascade delete_document to children via metadata.parent_uri
2026-05-28 15:36:00 +03:00
Yiorgis Gozadinos
5400085147
Auto-prune dead jobs when a sibling DELETE succeeds
2026-05-27 17:17:01 +03:00
Yiorgis Gozadinos
4d1b89de8f
Custom hover tooltips for truncated dashboard cells
2026-05-27 15:42:17 +03:00
Yiorgis Gozadinos
1e6dc34871
Skip FS DELETE enqueue when the file is already back
2026-05-27 15:18:46 +03:00
Yiorgis Gozadinos
15d13cab04
Probe docling-serve only when converter or chunker uses it
2026-05-27 15:18:25 +03:00
Yiorgis Gozadinos
b0d0ac588d
Split snapshot APIs and resolve_fetcher by intent
2026-05-27 14:39:54 +03:00
Yiorgis Gozadinos
2c63ceda0c
Backfill ingester test gaps and drop unneeded retry clamp
2026-05-27 14:24:22 +03:00
Yiorgis Gozadinos
cfbd0b09d6
Tighten HTTP config-removal handling
2026-05-27 14:07:45 +03:00
Yiorgis Gozadinos
7466539b4f
Emit DELETE for HTTP URLs removed from config
2026-05-27 13:39:18 +03:00
Yiorgis Gozadinos
d7fdd61fed
Resolve worker source by source_id, not just supports(uri)
2026-05-27 13:36:03 +03:00
Yiorgis Gozadinos
922d1d567d
Prevent DELETE/UPSERT race for the same URI
2026-05-27 13:30:46 +03:00
Yiorgis Gozadinos
1c710433c7
Collapse worker_count and max_concurrent into worker_count
2026-05-27 12:48:14 +03:00
Yiorgis Gozadinos
6f74fe67b3
Cap claimed-row count at max_concurren
2026-05-27 12:10:42 +03:00
Yiorgis Gozadinos
87af5e5139
Boot-reap stale claims at WorkerPool start
2026-05-27 11:46:37 +03:00
Yiorgis Gozadinos
1b36452629
Surface provider reachability and per-job failure context on dashboard
2026-05-27 11:38:48 +03:00
Yiorgis Gozadinos
439307d5af
Add pool-wide circuit breaker to the worker pool
2026-05-27 10:52:48 +03:00
Yiorgis Gozadinos
b491f767f3
Let httpx errors flow through DoclingServeClient
2026-05-26 17:38:49 +03:00
Yiorgis Gozadinos
fdb73fc41f
Drop defensive branches
2026-05-26 16:56:32 +03:00
Yiorgis Gozadinos
291b565b4c
Stream dashboard index.html via FileResponse
2026-05-26 16:31:41 +03:00
Yiorgis Gozadinos
29b3ccdbda
Drain orphan cancel-cleanup releases before closing the queue
2026-05-26 16:14:17 +03:00
Yiorgis Gozadinos
3c608046e2
Bound ?limit and ?offset on /jobs and /dlq
2026-05-26 16:05:47 +03:00
Yiorgis Gozadinos
761956eb70
Extend reaper-resurrection guard to reschedule and release_if_claimed
2026-05-26 16:04:24 +03:00
Yiorgis Gozadinos
6799a4a6d4
Document worker-pool settings
2026-05-26 14:13:16 +03:00
Yiorgis Gozadinos
a822b754b7
Guard mark_succeeded/mark_dead against reaper resurrection
2026-05-26 14:07:44 +03:00
Yiorgis Gozadinos
9cb3ce40ad
Shield cancel-cleanup release in worker pool
2026-05-26 13:57:35 +03:00
Yiorgis Gozadinos
78fc5d0e05
Discover within-root symlinks in FSSource
2026-05-26 13:54:33 +03:00
Yiorgis Gozadinos
e5e0df6ade
Unlink PDF slice tempfiles when slice write fails
2026-05-26 13:46:24 +03:00
Yiorgis Gozadinos
98efd73177
Serialize JobRepo and SyncStateRepo on one shared lock
2026-05-26 13:11:01 +03:00
Yiorgis Gozadinos
5f31a6b12f
Fix round-robin docling-serve
2026-05-26 13:07:21 +03:00
Yiorgis Gozadinos
cf6caf14fe
Tighten retry/reap_stale guards; fix SourceSummary.type leak
2026-05-26 12:38:55 +03:00
Yiorgis Gozadinos
f89cc998eb
add sources_provider to WorkerPool. workers now resolve extra info through these sources
2026-05-26 11:45:35 +03:00
Yiorgis Gozadinos
410279cd6c
Preserve sync_state revision when poller bumps last_seen_at
2026-05-26 11:45:35 +03:00
Yiorgis Gozadinos
083ff401d5
vacuum db after migration
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
73f8349a00
Use haiku.rag as telemtry scope
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
d900651b92
Render "queue busy" badge on sources skipped due to pending_work
...
Replaces the confusing em-dash + raw `pending_work` text when no successful sweep has run yet.
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
ef9cacf981
Harden FS source against symlink escape; surface pool/poller liveness in /health, additional auth tests
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
4aee18dcbe
Operator dashboard at GET /; tighten Logfire span shape
...
Self-contained HTML status page served from the ingester's FastAPI app.
Polls /health, /sources, /stats, /jobs?status={claimed,dead,succeeded}
every 3s from the browser and renders queue chips, sources with
last-poll/skip-reason/circuit state, active jobs with cancel, recent
failures with retry, and recently-completed feed with op badges so
DELETE rows are visually distinct from UPSERTs. Zero external deps —
single static HTML, no CDN, no fonts, no images. Works offline.
To support the dashboard:
- New /stats endpoint exposing rolling throughput (5m/30m/1h), worker
occupancy, oldest-queued age, and per-source DLQ + queue-depth
breakdowns. Each field is a single SQL aggregation against the queue.
- JobRepo gains count_succeeded_since, oldest_queued_age_seconds,
counts_by_source.
- SourceSummary gains last_skip_reason. BasePoller now records the
reason the most recent sweep attempt was skipped ("pending_work" /
"circuit_open"), cleared on the next successful poll. Closes the
gap where operators couldn't tell from /sources alone why a source
wasn't picking up new work.
Auth: dashboard route is unauthenticated (markup only). The JS attaches
the bearer to its own JSON fetches; on 401 it prompts once and stashes
the token in localStorage.
Two Logfire fixes that landed alongside:
- Drop logfire.instrument_fastapi() and the [fastapi] extra. The control
plane is polled frequently (dashboard + docker healthcheck), so every
endpoint became a span and drowned the useful traces. logfire itself
stays — pulled in transitively via pydantic-ai-slim[logfire] — so
ingester.poller.* / ingester.job / document.* spans keep emitting.
- Wrap FSPoller._handle_watch_change in an ingester.poller.watch_event
span and pass _enqueue_extra. Without this, the watchfiles callback
ran with no active context, the _otel carrier in job.extra was empty,
and the worker's ingester.job span surfaced as an orphan trace root
instead of nesting under the FS event that caused it.
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
5affe70eae
Cover unparseable-metadata path
2026-05-26 11:44:47 +03:00
Yiorgis Gozadinos
9ca06df745
Bound pdf_split memory + release lock between slices
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
c2f681dd78
constant-time auth, migration short-circuit
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
da3cfe1a58
Release claim on jobs when cancelled
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
14beba6786
Lock pypdfium2 under concurrent workers; per-slice convert spans
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
ba623b0862
mark event-loop glue + defensive guards as no-cover
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
ed36cc2230
typed UnsupportedSourceError replaces pipeline string-marker matching
2026-05-26 11:44:46 +03:00
Yiorgis Gozadinos
57e89426ea
regex-based _strip_etag with weak-marker test
2026-05-26 11:44:45 +03:00
Yiorgis Gozadinos
6bcc2f6357
PDF split-convert-merge for memory-bound large PDFs
2026-05-26 11:44:45 +03:00
Yiorgis Gozadinos
f4468b65ee
Add --host, --port to ingester cli, update docker compose example
2026-05-26 11:44:45 +03:00
Yiorgis Gozadinos
ec94426556
HTTPSource.head() returns ETag for the revision short-circuit
2026-05-26 11:44:45 +03:00
Yiorgis Gozadinos
055fd23d5d
round-robin docling-serve across multiple base_urls
2026-05-26 11:44:45 +03:00
Yiorgis Gozadinos
5ccbadde0a
Handle shutdown more gracefully, by stopping pollers and cancelling jobs after timeout. Skip periodic poll if a source has pending jobs
2026-05-26 11:44:03 +03:00
Yiorgis Gozadinos
65c309e12b
Handle WebDAV as source
2026-05-26 11:43:30 +03:00
Yiorgis Gozadinos
13cbadeb6f
canonical metadata keys: source_revision + content_type, bump to 0.50.0
2026-05-26 11:43:30 +03:00
Yiorgis Gozadinos
fa672c298a
logfire spans for the ingester, nested poller/job/document traces
2026-05-26 11:42:42 +03:00
Yiorgis Gozadinos
6d15f1f247
fix URL-decode file:// paths before stat/exists checks
2026-05-26 11:42:42 +03:00
Yiorgis Gozadinos
7ea61a7b10
drop the old monitor, rename serve→mcp, add e2e tests
2026-05-26 11:42:41 +03:00
Yiorgis Gozadinos
1ca3c25a83
logging, sqlite cursors
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
de3b3fa1c9
HTTP control plane
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
75c3896588
additional config, pollers, serve
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
bdcc1caa49
worker pool, rety policy, pipeline
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
4b3641244c
SQLite queue + haiku-ingester CLI skeleton
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
717fc3320b
route create_document_from_source through source adapters
2026-05-26 11:41:54 +03:00
Yiorgis Gozadinos
b9637cd625
add HTTP and S3 source adapters + resolve_fetcher
2026-05-26 11:41:53 +03:00
Yiorgis Gozadinos
d0a730ef60
ingester: add source-adapter scaffolding + FS source
2026-05-26 11:41:53 +03:00
Yiorgis Gozadinos
8e9e84132e
drop list_documents/get_document from default RAG skill
2026-05-26 11:35:43 +03:00
Yiorgis Gozadinos
14d9951016
vb
2026-05-21 14:32:13 +03:00
Yiorgis Gozadinos
260b8e8b09
Merge pull request #382 from ggozad/chore/updates
...
Prepare for pydantic-ai 2.0, update haiku.skills
2026-05-21 14:30:55 +03:00
Yiorgis Gozadinos
188d35023f
rotate chat TUI conversation id per launch / clear-chat
2026-05-21 14:21:51 +03:00
Yiorgis Gozadinos
80e3ae0280
clean up deprecation warnings: docling annotations + haiku.skills 0.17.1
2026-05-21 13:45:40 +03:00
Yiorgis Gozadinos
392c74039b
bump pydantic-ai-slim to 1.100 and haiku.skills to 0.17
...
Migrate off two APIs slated for removal in pydantic-ai 2.0:
- Agent(tool_retries=, output_retries=) -> Agent(retries={"tools": ...,
"output": ...}) in the LLM-as-judge evaluator.
- Evaluator.evaluation_name class attribute -> overriding
get_default_evaluation_name() on the citation MRR / MAP evaluators.
haiku.skills 0.17.0 already migrated its internal AGUIAdapter,
MCPToolset and ProcessEventStream usage; no further changes needed on
our side beyond the pin bumps.
2026-05-21 13:20:54 +03:00
Yiorgis Gozadinos
d14bf88096
fix migration failures on pre-v0.48.0 document_items schemas
2026-05-21 10:53:21 +03:00
Yiorgis Gozadinos
6690953480
fix mxbai reranker crash in chat TUI
2026-05-20 17:18:57 +03:00
Yiorgis Gozadinos
b48ac2fdd0
sandbox + cite: guard sort precondition; require rag in cite fallback
2026-05-20 13:02:25 +03:00
Yiorgis Gozadinos
f9392cee46
evaluations: judge model moves to config.evaluations.judge
2026-05-20 12:56:22 +03:00
Yiorgis Gozadinos
8c57a3ca99
Drop the multi-agent research workflow
2026-05-20 12:46:48 +03:00
Yiorgis Gozadinos
a317a951d9
CLI citations: compact panel, inline figures, doc/chunk IDs in footer
2026-05-20 12:00:24 +03:00
Yiorgis Gozadinos
3858ab905a
toc.json nodes carry chunk_ids; fix cite to accept DB-resolvable chunk_ids
2026-05-20 11:37:35 +03:00
Yiorgis Gozadinos
04eeec77d2
per-doc lazy items/toc cache; index document_items for fast per-doc lookup
2026-05-20 10:08:25 +03:00
Yiorgis Gozadinos
e3314e36fd
search: only attach picture bytes from pre-expansion chunks
2026-05-19 15:03:22 +03:00
Yiorgis Gozadinos
e8c61ad0c6
items.jsonl exposes chunk_ids per row; drops position and tree_depth
2026-05-19 14:20:11 +03:00
Yiorgis Gozadinos
6f95e2bc27
Delete the standalone QA and analysis agents
2026-05-19 11:39:20 +03:00
Yiorgis Gozadinos
947a26b391
client.analyze routes through the rag-analysis skill; drop documents= and AnalysisResult.program. Re-record all cassettes that are relevant
2026-05-19 10:46:32 +03:00
Yiorgis Gozadinos
d96d2eeb0f
client.ask routes through the rag skill; always show citations in CLI
2026-05-19 10:19:39 +03:00
Yiorgis Gozadinos
57d077e2c3
cite raises ModelRetry on unresolved chunk_ids
2026-05-18 16:49:44 +03:00
Yiorgis Gozadinos
87c551c892
Cover 0.48.0 migration
2026-05-18 16:49:44 +03:00
Yiorgis Gozadinos
3b6bef3bfb
Rename get_captions_for_chunk() to get_text_for_refs()
2026-05-18 16:49:44 +03:00
Yiorgis Gozadinos
74dea65f21
analysis.model inherits qa.model when unset; per-skill vision gate
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
52e93d08eb
Explain why no images in sandbox search(). We might want to add show_image() back in the future.
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
c562c397f9
move analysis skill toward search-first; document VFS doc_id vs uri
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
514b0c51f8
surface figure captions in search results, lower search.limit to 5
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
7d99be471f
Add tree-sitter-json on tui
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
e51841b924
Drop list_documents from analysis skill
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
68388032be
consolidate #/pictures/ prefix, tighten CHANGELOG, log migration exc_info
2026-05-18 16:49:43 +03:00
Yiorgis Gozadinos
f13461cdca
route figures through cite, drop show_image
2026-05-18 16:48:34 +03:00
Yiorgis Gozadinos
387c4f12a9
multimodal sandbox: show_image + picture_refs, drop llm
2026-05-18 16:48:34 +03:00
Yiorgis Gozadinos
2831030f9b
expose toc.json + heading_level/tree_depth in analysis VFS
2026-05-18 16:48:34 +03:00
Yiorgis Gozadinos
1360303edf
persist docling heading hierarchy on document_items
2026-05-18 16:48:34 +03:00
Yiorgis Gozadinos
f208730a5b
Merge pull request #374 from tseaver/feat-cli-search_type
...
feat: add '--search-type' option to CLI 'search'
2026-05-18 16:39:28 +03:00
Tres Seaver
8026693450
chore: ruff format
2026-05-18 09:31:38 -04:00
Tres Seaver
ad0161e6da
chore: isort
2026-05-18 09:31:12 -04:00
Tres Seaver
f9ce3bc401
refactor: move 'SearchType' to 'store.models.chunk'
2026-05-18 09:27:34 -04:00
Tres Seaver
d7e96f2658
fix: typo
2026-05-18 09:17:53 -04:00
Tres Seaver
4feac9683a
fix: default 'search_type' to None
2026-05-18 09:17:09 -04:00
Yiorgis Gozadinos
04415a9d09
bump pydantic-monty, refresh deps, cap transformers<5
2026-05-18 16:02:55 +03:00
Yiorgis Gozadinos
1df6530d03
Bump pydantic-ai, prepare for 2.*
2026-05-18 15:14:29 +03:00
Yiorgis Gozadinos
b1e8bdc839
Bump docling
2026-05-18 15:14:29 +03:00
Tres Seaver
b331dd0b76
fix: default 'search_type' to 'None' in 'client.search.search'
...
Apply 'hybrid' default only for text queries.
2026-05-18 06:52:03 -04:00
Tres Seaver
5079205d3d
fix: use 'SearchType' for 'ChunkRepository.search'
2026-05-18 06:50:49 -04:00
Tres Seaver
7953de46b9
fix: declare 'SearchType' for 'search_type' arg
...
fix: allow 'search_type' only for text searches
2026-05-18 06:35:51 -04:00
Tres Seaver
b2ffc50168
WIP: add '--search-type' option to CLI 'search'
2026-05-18 06:35:50 -04:00
Yiorgis Gozadinos
97a7eb246c
vb
2026-05-14 16:03:33 +03:00
Yiorgis Gozadinos
5de4d50622
coverage
2026-05-14 15:54:43 +03:00
Yiorgis Gozadinos
57f273e000
Minor fixes, CI should build
2026-05-14 15:43:36 +03:00
Yiorgis Gozadinos
519afe6709
Add cross-encoder reranking provider
2026-05-14 15:43:35 +03:00
Yiorgis Gozadinos
dbb87e091f
Ensure schema parity for _StagingChunkRecord
2026-05-14 15:11:18 +03:00
Yiorgis Gozadinos
849eca94d0
Make rebuild --embed-only idempotent across crashes
2026-05-14 15:02:12 +03:00
Yiorgis Gozadinos
a035b0f9e4
Stream rebuild --embed-only through a staging table to bound memory
2026-05-14 15:02:12 +03:00
Yiorgis Gozadinos
862a209137
vb
2026-05-13 16:53:35 +03:00
Yiorgis Gozadinos
a98ddc14b8
Replace picture_description.enabled with processing.pictures enum
2026-05-13 16:22:44 +03:00
Yiorgis Gozadinos
bdab201c42
Merge pull request #371 from ggozad/fix/image-results
...
Verify picture bytes before attaching to multimodal tool returns
2026-05-13 16:19:09 +03:00
Yiorgis Gozadinos
a6e5664c78
Verify picture bytes before attaching to multimodal tool returns
2026-05-13 16:01:39 +03:00
Yiorgis Gozadinos
072edad62f
Merge pull request #368 from ggozad/feat/relax-compat-check
...
Relax embedding compatibility check to vector_dim only
2026-05-13 15:43:37 +03:00
Yiorgis Gozadinos
701e9d3632
Relax embedding compat check to vector_dim only
2026-05-13 14:44:18 +03:00
Yiorgis Gozadinos
8b135c4d4d
Expose embedding batch size as config
2026-05-13 14:09:47 +03:00
Yiorgis Gozadinos
c6cd847299
Add ModelConfig.extra_body for raw provider pass-through
2026-05-13 13:45:09 +03:00
Yiorgis Gozadinos
0f4c4af495
Cache the chunking tokenizer to avoid HF Hub 429
2026-05-13 13:32:24 +03:00
Yiorgis Gozadinos
d512f9fbd1
Disable Typer locals in CLI tracebacks
2026-05-13 13:24:05 +03:00
Yiorgis Gozadinos
bf1cd68f64
Preserve cause chain on docling wrapper exceptions
2026-05-13 12:18:53 +03:00
Yiorgis Gozadinos
674b80e8c9
Support streaming for markdown
2026-05-12 16:01:42 +03:00
Yiorgis Gozadinos
afd4665517
Thread source_uri through URL ingest
2026-05-12 15:13:02 +03:00
Yiorgis Gozadinos
a25d9699ee
Wire per-format options across docling-local
2026-05-12 15:02:59 +03:00
Yiorgis Gozadinos
ef82e6eb08
swap aioboto3 for obstore in the S3 client path
2026-05-11 11:29:42 +03:00
Yiorgis Gozadinos
37099988a6
poll S3 prefixes with S3Watcher and wire into serve
2026-05-11 11:28:40 +03:00
Yiorgis Gozadinos
d009da06d6
support s3:// document sources
2026-05-11 11:28:31 +03:00
Yiorgis Gozadinos
387032511e
Simplify
2026-05-08 12:11:25 +03:00
Yiorgis Gozadinos
788fac422e
Clean up migration
2026-05-08 11:52:57 +03:00
Yiorgis Gozadinos
e55e3d13c8
fix _patch_picture_descriptions silently dropping docling_pages
2026-05-06 12:57:41 +03:00
Yiorgis Gozadinos
75f75ec505
render attached pictures in inspector context modal under qa.model.vision
2026-05-06 12:00:12 +03:00
Yiorgis Gozadinos
7fac35d2af
rename embed_image_query to embed_image; run description check on text path
2026-05-05 16:15:47 +03:00
Yiorgis Gozadinos
1ccb5b5fad
auto-append /v1 to vllm base_url, matching ollama behavior
2026-05-05 16:08:14 +03:00
Yiorgis Gozadinos
4478b7ce2b
test v0.45.0 migration
2026-05-05 16:06:14 +03:00
Yiorgis Gozadinos
c96894a0f0
fix cross-document picture dedup in agent and skill search tools
2026-05-05 15:56:10 +03:00
Yiorgis Gozadinos
61a88edfd8
drop bogus deprecation warning for processing.pictures
2026-05-05 14:46:41 +03:00
Yiorgis Gozadinos
49274ab51b
attach picture bytes through skill search and document the schema
2026-05-05 14:33:57 +03:00
Yiorgis Gozadinos
ffc7b95375
yield per document during rebuild for live progress reporting
2026-05-05 14:04:37 +03:00
Yiorgis Gozadinos
a45d82f206
Update benchmark
2026-05-05 13:58:48 +03:00
Yiorgis Gozadinos
dca3188a48
hydrate documents lazily during rebuild
2026-05-05 12:47:45 +03:00
Yiorgis Gozadinos
ff82d36c2f
add rebuild --descriptions: run VLM over stored picture bytes only
2026-05-05 12:02:46 +03:00
Yiorgis Gozadinos
5fad0aa5c6
warn when picture descriptions silently fail to come back
2026-05-05 11:44:18 +03:00
Yiorgis Gozadinos
2038d43435
collapse pictures enum to picture_description.enabled boolean
2026-05-05 11:16:08 +03:00
Yiorgis Gozadinos
e88321767d
always store picture bytes; collapse converter to a single zip path
2026-05-05 10:40:40 +03:00
Yiorgis Gozadinos
ee41bc676f
remove defensive code
2026-05-04 15:12:27 +03:00
Yiorgis Gozadinos
e8d89aa035
dedup picture-only chunks at the search-result layer
2026-05-04 13:31:15 +03:00
Yiorgis Gozadinos
aa3e9406cf
auto-append /v1 to per-model Ollama base_url, fix flaky tests
2026-05-04 13:12:37 +03:00
Yiorgis Gozadinos
65d9c74224
expose image-as-query through MCP and the CLI.
2026-05-04 11:46:45 +03:00
Yiorgis Gozadinos
ff656504d3
make client.search() polymorphic on query type: str | bytes | PIL.Image.Image. Bytes/PIL queries embed via embed_image_query and run vector-only against the chunks table
2026-05-04 11:22:22 +03:00
Yiorgis Gozadinos
21f12cd770
add vision: bool flag on ModelConfig (default False). Gate the agent search tool's BinaryContent attachment on qa.model.vision so picture bytes are only sent to vision-capable QA models.
2026-05-04 10:47:21 +03:00
Yiorgis Gozadinos
6037f26673
drop mlx
2026-05-03 19:05:49 +03:00
Yiorgis Gozadinos
c9fdad15a9
bump docling-core to >=2.74.1 so that local docling-local and docling-serve chunkers run the same MarkdownTableSerializer
2026-05-03 18:40:44 +03:00
Yiorgis Gozadinos
c9227c649f
emit synthetic picture chunks at ingest under multimodal embedders.
...
processing.chunk() merges text chunks with one synthetic Chunk per PictureItem-with-bytes,
sorted by iterate_items() position so chunk.order is structural.
embed_chunks dispatches on a Chunk._picture_data PrivateAttr
(text through embed_documents, picture through embed_image_query)
2026-05-03 17:04:43 +03:00
Yiorgis Gozadinos
a36f920f5d
drop the batched embed_images method from multi-modal embedders
2026-05-03 16:21:47 +03:00
Yiorgis Gozadinos
37215f1a00
add multimodal embedder support for vllm and mlx
2026-05-03 10:57:56 +03:00
Yiorgis Gozadinos
75c8e83515
Allow uri override on create_document_from_source
2026-04-30 16:36:35 +03:00
Yiorgis Gozadinos
4c9ef81fc6
drop the existing-row-not-found guard from the 0.45.0 picture-bytes migration.
2026-04-30 15:48:03 +03:00
Yiorgis Gozadinos
b290bbe82d
rename document_items repository's _LIGHT_COLUMNS to _METADATA_COLUMNS
2026-04-30 15:43:03 +03:00
Yiorgis Gozadinos
875c635a77
have rebuild --rechunk re-chunk from the stored docling blob instead of re-converting from the markdown export
2026-04-30 15:30:24 +03:00
Yiorgis Gozadinos
7831057339
add processing.pictures enum (none|description|image), replacing the implicit pair of generate_picture_images+picture_description.enabled flags
2026-04-30 14:26:14 +03:00
Yiorgis Gozadinos
b01c649684
surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool
2026-04-30 12:43:05 +03:00
Yiorgis Gozadinos
6a77ce92a9
extract picture bytes to document_items.picture_data at ingest, strip them from the docling_document blob, and add 0.45.0 migration to backfill existing
...
databases
2026-04-30 11:26:37 +03:00
Yiorgis Gozadinos
191cdc636b
retrieve picture image bytes via referenced+zip path, fix docling-serve not returning images even when set to do so. Remove xfail from relevant test
2026-04-30 11:23:29 +03:00
Yiorgis Gozadinos
dc16f74b58
add picture_data column to document_items
2026-04-30 11:23:29 +03:00
Yiorgis Gozadinos
29bc42514e
vb
2026-04-29 13:45:36 +03:00
Yiorgis Gozadinos
5f08a2a8ae
Adapt rag SKILL.md in order to improve citation rate
2026-04-28 14:51:28 +03:00
Yiorgis Gozadinos
7685a592c2
bump haiku.skills to 0.16.0
2026-04-28 12:03:14 +03:00
Yiorgis Gozadinos
6807f082ec
vb
2026-04-25 09:35:47 +03:00
Tres Seaver
0d70f4aec6
fix: pass absolute 'db_path' to 'lancedb.connect_async'
...
Closes #354 .
2026-04-24 17:59:01 -04:00
Yiorgis Gozadinos
81ba248483
vb
2026-04-24 17:47:57 +03:00
Yiorgis Gozadinos
821b7361e9
Push document-id filter into chunk search query
2026-04-24 16:07:07 +03:00
Yiorgis Gozadinos
31fc22ce9d
List tables consistently
2026-04-24 15:57:07 +03:00
Yiorgis Gozadinos
cd4224a727
drop private title/embedding forwarders from HaikuRAG
2026-04-24 15:52:50 +03:00
Yiorgis Gozadinos
b23bad32c3
Check table_names() before dropping chunks in recreate_embeddings_table
2026-04-24 15:32:06 +03:00
Yiorgis Gozadinos
729899299b
Log post-rebuild vacuum failures and clarify vacuum-await scope
2026-04-24 15:31:36 +03:00
Yiorgis Gozadinos
258ffa41fa
Improve test coverage
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
aca3ccc29f
Close connections if __aenter__ fails mid-initialization
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
3224d1f20c
Extract document orchestration into client/documents.py
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
cb02a2c3d8
Extract rebuild machinery into client/rebuild.py
2026-04-24 14:43:59 +03:00
Yiorgis Gozadinos
528acb79a3
Extract LLM agents into client/agents.py
2026-04-24 14:43:58 +03:00
Yiorgis Gozadinos
12939f1444
Extract search, expand_context, visualize_chunk into client/search.py
2026-04-24 14:43:58 +03:00
Yiorgis Gozadinos
d4ecebf896
Extract processing primitives into client/processing.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
b5e480bfa1
Extract title generation into client/titles.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
e814459e1f
Extract download_models into client/downloads.py
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
43f2774c14
Turn client.py into a client/ package
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
d0ed9e213f
Pin FTS search column to content_fts
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
a74c3a6f9e
Satisfy ty by adding a typed to_pydantic helper
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
b6ea07d2de
Track all in-flight background vacuum tasks, not just the last one
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
57385506c1
Fix is_new_db detection when create=True is passed on an existing DB
2026-04-24 14:42:53 +03:00
Yiorgis Gozadinos
82fd10e0ee
Migrate LanceDB to native async API
...
Convert all LanceDB operations from sync calls wrapped in async
functions to the native async API (connect_async, AsyncConnection,
AsyncTable, AsyncQuery). Database I/O no longer blocks the event loop.
- Store and HaikuRAG use async context managers (async with). Store
initialization is deferred to __aenter__; direct construction
without async with is no longer supported.
- Index creation uses config objects (FTS, BTree, IvfPq) instead of
string-based index_type parameter.
- Upgrade callbacks are async.
- HaikuRAG tracks background vacuum tasks and awaits them in __aexit__
and before destructive rebuild operations to avoid races with
concurrent table mutations.
- temp_db_path fixture uses pytest's tmp_path for reliable async
cleanup.
2026-04-24 14:42:52 +03:00
Yiorgis Gozadinos
84c5391259
Merge pull request #353 from ggozad/feat/better-visual-highlight
...
Tone down the yellow colour in visual highlights
2026-04-24 14:41:27 +03:00
Yiorgis Gozadinos
cb9360ef7b
fix chat TUI citation rendering after state flattening
2026-04-24 13:48:57 +03:00
Yiorgis Gozadinos
a833e58d54
Tone down the yellow colour in visual highlights
2026-04-24 10:31:43 +03:00
Yiorgis Gozadinos
4f058bf484
vb
2026-04-22 17:00:03 +03:00
Yiorgis Gozadinos
ae2b8461be
flatten skill state citations from list[list[str]] to list[str]
2026-04-22 16:50:13 +03:00
Yiorgis Gozadinos
bb9e7b28ca
vb
2026-04-22 16:18:44 +03:00
Yiorgis Gozadinos
206c4ffcf2
address review: top-level AnalysisRunDeps import, asserts, e2e tests
...
- Move AnalysisRunDeps to the module-level import in _tools.py.
- Swap the RuntimeError guards in _require_rag and execute_code for
plain asserts with the same diagnostic messages. Apply the same
treatment to the ty-reachability guard in Sandbox._ensure_initialized.
- Add end-to-end lifespan tests for both skills that drive _run_skill
with TestModel, covering the sub-agent entry path that the existing
tool-level tests bypass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-22 15:04:24 +03:00
Yiorgis Gozadinos
9067b89d2f
fix convert() misreading text content that starts with a URL
2026-04-22 14:47:23 +03:00
Yiorgis Gozadinos
f0016ebcd2
scope citations, searches, and executions to the current invocation
2026-04-22 13:53:39 +03:00
Yiorgis Gozadinos
4a9dd9b49a
persist sandbox variables across execute_code calls within one invocation
2026-04-22 13:30:38 +03:00
Yiorgis Gozadinos
4e9c02afc2
open one HaikuRAG client per skill invocation via lifespan
2026-04-22 13:13:42 +03:00
Yiorgis Gozadinos
8a23108fbd
vb
2026-04-20 16:36:32 +03:00
Yiorgis Gozadinos
eb4e1721ce
remove dead code, add tool descriptions in frontend, update changelog
2026-04-20 15:38:17 +03:00
Yiorgis Gozadinos
ff8ad0879c
fix context expansion: respect section boundaries, remove max_context_items
2026-04-20 15:18:16 +03:00
Yiorgis Gozadinos
af7731f4e1
bulk-fetch items.jsonl via lazy cache to avoid per-document query timeout
2026-04-20 14:25:16 +03:00
Yiorgis Gozadinos
cd0c21c996
remove cited_chunks from analysis agent, hoist _deny_write out of loop
2026-04-20 14:05:10 +03:00
Yiorgis Gozadinos
579e609ae1
revert REPL persistence: fresh sandbox per execute_code call
2026-04-20 12:48:05 +03:00
Yiorgis Gozadinos
9d921b13fe
reset sandbox per skill invocation to prevent state leaks
2026-04-20 12:18:14 +03:00
Yiorgis Gozadinos
167c837514
repository methods, module-level executor, read-only VFS
2026-04-20 11:57:39 +03:00
Yiorgis Gozadinos
27c5defdbb
Improve analysis SKILL.md
2026-04-20 11:38:09 +03:00
Yiorgis Gozadinos
4d75943df5
use MontyRepl for persistent variables across execute_code calls
2026-04-20 10:47:50 +03:00
Yiorgis Gozadinos
68a9f191d2
Remove documents from state, fix tests
2026-04-20 09:48:18 +03:00
Yiorgis Gozadinos
d52f453c44
flatten skill architecture: replace ask/analyze/research with direct tools
2026-04-17 18:35:17 +03:00
Yiorgis Gozadinos
20e40d75f9
add collapsible program display to chat TUI
...
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-17 18:35:17 +03:00
Yiorgis Gozadinos
7d98d0ec57
add citation support to analysis agent
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
cf89ff55cd
When setting --model, set all subagents as well
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
aa4ce07dc9
remove filter parameter from analyze skill tool and clean up unused filter helpers
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
2a0e89bbe7
add --skill flag to chat TUI for rag and analysis skills
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
a45820dbf7
add document virtual filesystem to analysis sandbox
...
Replace get_document() and get_docling_document() with a VFS at
/documents/{id}/ with metadata.json (eager), content.txt (lazy),
and items.jsonl (lazy). Keep search(), list_documents() (now returns
all), and llm() as external functions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
bacc21b38b
expose doc_item_refs and labels in sandbox search results
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
4118533db1
fold context expansion into sandbox search and remove get_context
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
44fd0c9906
add get_context() to analysis sandbox and improve prompt
2026-04-17 18:32:45 +03:00
Yiorgis Gozadinos
d2b3ba1b59
rename RLM agent to analysis throughout the codebase
2026-04-17 18:32:01 +03:00
Yiorgis Gozadinos
499a843a43
remove unused create_analysis_toolset and AnalysisResult
2026-04-17 18:32:01 +03:00
Yiorgis Gozadinos
1049586469
vb
2026-04-17 16:24:25 +03:00
Yiorgis Gozadinos
a1181ff52d
extract get_database_stats and share it across info, inspector, and backend
2026-04-17 15:33:30 +03:00
Yiorgis Gozadinos
a0a9a3410b
info: report partial stats and pending migrations on pre-migration DBs
2026-04-17 14:00:03 +03:00
Yiorgis Gozadinos
75c84805b4
Improve judge prompt, QA prompt, and raise max_searches to 5
2026-04-16 12:12:23 +03:00
Yiorgis Gozadinos
d3c8ed62a8
preserve original chunk when expansion produces less content
2026-04-16 12:11:54 +03:00
Yiorgis Gozadinos
e2bac1e887
deduplicate escape_sql_string into utils
2026-04-16 12:11:53 +03:00
Yiorgis Gozadinos
3c1a33779f
use windowed fetch for context expansion instead of loading all items
2026-04-16 12:11:53 +03:00
