Commit Graph

12 Commits

Author SHA1 Message Date
Marcello Fitton
42a41201a8
feat: Document Embedding Status Events | Refactor Document Embedding to Job Queue and Forked Process (#5254)
* implement native embedder job queue

* persist embedding progress across renders

* add development worker timeouts

* change to static method

* native reranker

* remove useless return

* lint

* simplify

* make embedding worker timeout value configurable by admin

* add event emission for missing data

* lint

* remove onProgress callback argument

* make rerank to rerankDirect

* persists progress state across app reloads

* remove chunk level progress reporting

* remove unuse dvariable

* make NATIVE_RERANKING_WORKER_TIMEOUT user configurable

* remove dead code

* scope embedding progress per-user and clear stale state on SSE reconnect

* lint

* revert vector databases and embedding engines to call their original methods

* simplify rerank

* simplify progress fetching by removing updateProgressFromApi

* remove duplicate jsdoc

* replace sessionStorage persistence with server-side history replay for embedding progress

* fix old comment

* fix: ignore premature SSE all_complete when embedding hasn't started yet

The SSE connection opens before the embedding API call fires, so the
server sees no buffered history and immediately sends all_complete.
Firefox dispatches this eagerly enough that it closes the EventSource
before real progress events arrive, causing the progress UI to clear
and fall back to the loading spinner. Chrome's EventSource timing
masks the race.

Track slugs where startEmbedding was called but no real progress event
has arrived yet via awaitingProgressRef. Ignore the first all_complete
for those slugs and keep the connection open for the real events.

* reduce duplication with progress emissions

* remove dead code

* refactor: streamline embedding progress handling

Removed unnecessary tracking of slugs for premature all_complete events in the EmbeddingProgressProvider. Updated the server-side logic to avoid sending all_complete when no embedding is in progress, allowing the connection to remain open for real events. Adjusted the embedding initiation flow to ensure the server processes the job before the SSE connection opens, improving the reliability of progress updates.

* fix stale comment

* remove unused function

* fix event emissions for document creation failure

* refactor: move Reranking Worker Idle Timeout input to LanceDBOptions component

Extracted the Reranking Worker Idle Timeout input from GeneralEmbeddingPreference and integrated it into the LanceDBOptions component. This change enhances modularity and maintains a cleaner structure for the settings interface.

* lint

* remove unused hadHistory vars

* refactor workspace directory by hoisting component and converting into functions

* moved EmbeddingProgressProvider to wrap Document Manager Modal

* refactor embed progress SSE connection to use fetchEventSource instead of native EventSource API.

* refactor message handlng into a function and reduce duplication

* refactor: utilize writeResponseChunk for event emissions in document embedding progress SSE

* refactor: explicit in-proc embedding and rerank methods that are called by workers instead of process.send checks

* Abstract EmbeddingProgressBus and Worker Queue into modules

* remove error and toast messages on embed process result

* use safeJsonParse

* add chunk-level progress events with per-document progress bar in UI

* remove unused parameter

* rename all worker timeout references to use ttl | remove ttl updating from UI

* refactor: pass embedding context through job payload instead of global state

* lint

* add graceful shutdown for workers

* apply figma styles

* refactor embedding worker to use bree

* use existing WorkerQueue class as the management layer for jobs

* lint

* revert all reranking worker changes back to master state

Removes the reranking worker queue, rerankViaWorker/rerankInProcess
renames, and NATIVE_RERANKING_WORKER_TTL config so this branch
only contains the embedding worker job queue feature.

* remove breeManaged flag — WorkerQueue always spawns via Bree

* fix prompt embedding bug

* have embedTextInput call embedChunksInProcess

* add message field to `process.send()`

* remove nullish check and error throw

* remove bespoke graceful shutdown logix

* add spawnWorker method and asbtract redudant flows into helper methods

* remove unneeded comment

* remove recomputation of TTL value

* frontend cleanup and refactor

* wip on backend refactor

* backend overhaul

* small lint

* second pass

* add logging, update endpoint

* simple refactor

* add reporting to all embedder providers

* fix styles

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2026-04-06 17:00:15 -07:00
Marcello Fitton
6855bbf695
Refactor Class Name Logging (#4426)
* Add className property to various LLM and embedder classes to fix logging bug after minification

* Fix bug with this.log method by applying the missing private field symbol
2025-09-25 15:34:19 -10:00
Shinya Suzuki
cd900f9e4c
Replace @azure/openai with openai, and update openai to version 4.95.1 (#3691)
* Replace @azure/openai to OpenAI lib

* Remove @azure/openai dependency and update openai to version 4.95.1

* linting

* update logging
fix translation dictionary error

* remove bad ENV key that DNE
linting
Patch Azure OpenAI
Migrate Azure Agent provider to use OpenAI Schema for tool calling performance

* unset

* migrate azure to use default OAI stream handler

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2025-04-29 11:21:39 -07:00
Timothy Carambat
bf435b2861
Adjust how text is split depending on input type (#1238)
resolves #1230
2024-04-30 10:11:56 -07:00
Timothy Carambat
ce98ff4653
Enable customization of chunk length and overlap (#1059)
* Enable customization of chunk length and overlap

* fix onboarding link
show max limit in UI and prevent overlap >= chunk size
2024-04-06 16:38:07 -07:00
Timothy Carambat
658e7fa390
chore: Better VectorDb and Embedder error messages (#620)
* chore: propogate embedder and vectordb errors during document mutations

* add default value for errors on addDocuments
2024-01-18 11:40:48 -08:00
Timothy Carambat
d0a3f1e3e1
Fix present diminsions on vectorDBs to be inferred for providers who require it (#605) 2024-01-16 13:41:01 -08:00
Shuyoou
6faa0efaa8
Issue #543 support milvus vector db (#579)
* issue #543 support milvus vector db

* migrate Milvus to use MilvusClient instead of ORM
normalize env setup for docs/implementation
feat: embedder model dimension added

* update comments

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-12 13:23:57 -08:00
timothycarambat
049bfa14cb fix: fully separate chunkconcurrency from chunk length 2023-12-20 11:20:40 -08:00
timothycarambat
a7f6003277 fix: set lower maxChunk limit on native embedder to stay within resource constraints
chore: update comment for what embedding chunk means
2023-12-19 16:20:34 -08:00
Timothy Carambat
8cc1455b72
feat: add support for variable chunk length (#415)
fix: cleanup code for embedding length clarify
resolves #388
2023-12-07 16:27:36 -08:00
Timothy Carambat
5d56ab623b
Anthropic claude 2 support (#305)
* WIP Anythropic support for chat, chat and query w/context

* Add onboarding support for Anthropic

* cleanup

* fix Anthropic answer parsing
move embedding selector to general util
2023-10-30 15:44:03 -07:00