7 Commits

Author SHA1 Message Date
joachim-danswer
463340b8a1
Reduce ranking scores for short chunks without actual information (#4098)
* remove title for slack

* initial working code

* simplification

* improvements

* name change to information_content_model

* avoid boost_score > 1.0

* nit

* EL comments and improvements

Improvements:
  - proper import of information content model from cache or HF
  - warm up for information content model

Other:
  - EL PR review comments

* nit

* requirements version update

* fixed docker file

* new home for model_server configs

* default off

* small updates

* YS comments - pt 1

* renaming to chunk_boost & chunk table def

* saving and deleting chunk stats in new table

* saving and updating chunk stats

* improved dict score update

* create columns for individual boost factors

* RK comments

* Update migration

* manual import reordering
2025-03-13 17:35:45 +00:00
rkuo-danswer
870b59a1cc
Bugfix/vertex crash (#4181)
* Update text embedding model to version 005 and enhance embedding retrieval process

* re

* Fix formatting issues

* Add support for Bedrock reranking provider and AWS credentials handling

* fix: improve AWS key format validation and error messages

* Fix vertex embedding model crash

* feat: add environment template for local development setup

* Add display name for Claude 3.7 Sonnet model

* Add display names for Gemini 2.0 models and update Claude 3.7 Sonnet entry

* Fix ruff errors by ensuring lines are within 130 characters

* revert to currently default onyx browser settings

* add / fix boto requirements

---------

Co-authored-by: ferdinand loesch <f.loesch@sportradar.com>
Co-authored-by: Ferdinand Loesch <ferdinandloesch@me.com>
Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>
2025-03-05 01:59:46 +00:00
Richard Kuo (Danswer)
bc2c56dfb6 improve gpu detection functions and logging in model server 2025-02-07 16:59:02 -08:00
Yuhong Sun
ce666f3320
Propagate Embedding Enum (#2108) 2024-08-11 12:17:54 -07:00
Weves
6fe3eeaa48 Fix model serer startup 2024-07-14 23:33:58 -07:00
pablodanswer
e7f81d1688
add third party embedding models (#1818) 2024-07-14 10:19:53 -07:00
Yuhong Sun
2db906b7a2
Always Use Model Server (#1306) 2024-04-07 21:25:06 -07:00