merlyn/server/utils
AbelDuan df166eb64e
feat: Add multilingual support for ocr module (#3325)
* Add multilingual support for ocr mudule

* Add OCR langauge as server var that is passed into Collector
Support all valid tesseract language codes
Filter and parse only valid codes with fallbacks'

* persist TARGET_OCR_LANG

* update docker example env

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2025-02-27 12:31:17 -08:00
..
agentFlows fix: Patch agent flow to honor agent handler established provider (#3251) 2025-02-17 14:44:23 -08:00
agents Add new model provider PPIO (#3211) 2025-02-27 10:53:00 -08:00
AiProviders Add new model provider PPIO (#3211) 2025-02-27 10:53:00 -08:00
BackgroundWorkers Add winston logging for production (#1811) 2024-07-03 16:39:33 -07:00
boot Add RAG agent plugin to API agent (#2171) 2024-08-23 09:32:19 -07:00
chats wip agent ui animation (#2999) 2025-01-22 11:10:02 -08:00
collectorApi feat: Add multilingual support for ocr module (#3325) 2025-02-27 12:31:17 -08:00
comKey [BETA] Live document sync (#1719) 2024-06-21 13:38:50 -07:00
database Full developer api (#221) 2023-08-23 19:15:07 -07:00
DocumentManager Enable ability to do full-text query on documents (#758) 2024-02-21 13:15:45 -08:00
EmbeddingEngines Enable num_ctx to match defined chunk length in ollama embedder (#3129) 2025-02-05 15:46:39 -08:00
EmbeddingRerankers/native bump cdn 2025-02-05 10:30:43 -08:00
EncryptionManager [BETA] Live document sync (#1719) 2024-06-21 13:38:50 -07:00
files Fix garbled non English chars on document upload (#3301) 2025-02-20 23:09:34 -08:00
helpers feat: Add multilingual support for ocr module (#3325) 2025-02-27 12:31:17 -08:00
http Agent flow builder (#3077) 2025-02-12 16:50:43 -08:00
logger patch logger for full logs 2024-07-19 18:35:41 -07:00
middleware Patch custom models endpoint (#2903) 2024-12-30 14:58:26 -08:00
PasswordRecovery Strengthen field validations on user Updates (#1201) 2024-04-26 16:46:04 -07:00
prisma Remove unused deps (#1938) 2024-07-25 10:21:03 -07:00
telemetry Replace custom sqlite dbms with prisma (#239) 2023-09-28 14:00:03 -07:00
TextSplitter Add header static class for metadata assembly (#2567) 2024-11-04 11:47:46 -08:00
TextToSpeech Tts open ai compatible endpoints (#2487) 2024-10-15 21:39:31 -07:00
vectorDbProviders fix: sanitizeNamespace (#3246) 2025-02-17 13:54:32 -08:00
vectorStore Purge cached docs and remove docs from all workspaces on vectorDB/embedder changes (#2819) 2024-12-16 12:16:20 -08:00