Commit Graph

26 Commits

Author SHA1 Message Date
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
pablonyx
fa408ff447 add 3.7 (#4116) 2025-02-25 12:41:40 -08:00
pablonyx
0ec065f1fb Set GPT 4o as default and add O3 mini (#3899)
* quick update to models

* add reqs

* update version
2025-02-05 03:06:05 +00:00
pablonyx
ca9ba925bd Support o1 (#3510)
* support o1

* nit
2024-12-19 00:05:00 +00:00
Weves
06f4146597 Bump litellm to support Nova models from AWS 2024-12-09 21:19:11 -08:00
Chris Weaver
2783fa08a3 Update openai version in model server (#3306) 2024-12-02 21:39:10 +00:00
hagen-danswer
94edcac36e upgraded claude model strings (#2876)
* upgraded model strings

* trolled

* we do a little trolling

* reeeeeee

* alembic upgrade

* added ignore

* bump litellm

* k

* nit

---------

Co-authored-by: pablodanswer <pablo@danswer.ai>
2024-10-26 00:11:52 +00:00
pablodanswer
1b6b134722 Clearer azure models (#2898)
* clear up llm

* remove logs
2024-10-24 17:29:36 +00:00
pablodanswer
61424de531 add sentry (#2786)
* add sentry

* nit

* nit

* add requirement to ee

* try to ensure sentry is installed in integration tests
2024-10-17 23:20:37 +00:00
pablodanswer
15afe4dc78 bump litellm (#2827) 2024-10-17 18:05:35 +00:00
pablodanswer
e022e77b6d Simpler azure embedding (#2751)
* functional but janky

* nit

* adapt for azure

* nit

* minor updates

* nits

* nit

* nit

* ensure access to litellm

* k
2024-10-15 23:23:11 +00:00
pablodanswer
45f67368a2 Add support for o1 (#2538)
* add o1 support + bump litellm/openai

* ports

* update exception message for testing
2024-09-22 23:16:28 +00:00
dependabot[bot]
1e4b27185d Bump torch from 2.0.1 to 2.2.0 in /backend/requirements (#1933)
Bumps [torch](https://github.com/pytorch/pytorch) from 2.0.1 to 2.2.0.
- [Release notes](https://github.com/pytorch/pytorch/releases)
- [Changelog](https://github.com/pytorch/pytorch/blob/main/RELEASE.md)
- [Commits](https://github.com/pytorch/pytorch/compare/v2.0.1...v2.2.0)

---
updated-dependencies:
- dependency-name: torch
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-09-08 10:17:17 -07:00
josvdw
50c17438d5 Litellm bump (#2195)
* ran bump-pydantic

* replace root_validator with model_validator

* mostly working. some alternate assistant error. changed root_validator and typing_extensions

* working generation chat. changed type

* replacing .dict with .model_dump

* argument needed to bring model_dump up to parity with dict()

* fix a fewremaining issues -- working with llama and gpt

* updating requirements file

* more requirement updates

* more requirement updates

* fix to make search work

* return type fix:

* half way tpyes change

* fixes for mypy and pydantic:

* endpoint fix

* fix pydantic protected namespaces

* it works!

* removed unecessary None initializations

* better logging

* changed default values to empty lists

* mypy fixes

* fixed array defaulting

---------

Co-authored-by: hagen-danswer <hagen@danswer.ai>
2024-08-28 00:00:27 +00:00
Yuhong Sun
7dcc42aa95 Intent Model Update (#2069) 2024-08-08 20:45:53 -07:00
hagen-danswer
1be1959d80 Changed default local model to nomic (#1943) 2024-07-31 18:54:02 -07:00
Yuhong Sun
0e8ba111c8 Model Touchups (#1887) 2024-07-21 12:31:00 -07:00
hagen-danswer
eb3e7610fc Added retries and multithreading for cloud embedding (#1879)
* added retries and multithreading for cloud embedding

* refactored a bit

* cleaned up code

* got the errors to bubble up to the ui correctly

* added exceptin printing

* added requirements

* touchups

---------

Co-authored-by: Yuhong Sun <yuhongsun96@gmail.com>
2024-07-20 22:10:18 -07:00
pablodanswer
e7f81d1688 add third party embedding models (#1818) 2024-07-14 10:19:53 -07:00
dependabot[bot]
52fd18d3bd Bump pydantic from 1.10.7 to 1.10.13 in /backend/requirements (#1377) 2024-05-11 10:32:31 -07:00
Yuhong Sun
b59912884b Fix Model Server (#1320) 2024-04-10 23:13:22 -07:00
Yuhong Sun
2db906b7a2 Always Use Model Server (#1306) 2024-04-07 21:25:06 -07:00
Weves
db21d82ea2 Bump tf version 2024-02-19 20:17:20 -08:00
dependabot[bot]
33c1cc491f Bump fastapi from 0.103.0 to 0.109.1 in /backend/requirements (#1043)
Bumps [fastapi](https://github.com/tiangolo/fastapi) from 0.103.0 to 0.109.1.
- [Release notes](https://github.com/tiangolo/fastapi/releases)
- [Commits](https://github.com/tiangolo/fastapi/compare/0.103.0...0.109.1)

---
updated-dependencies:
- dependency-name: fastapi
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-02-19 14:27:39 -08:00
Yuhong Sun
ff014e4f5a Bump Transformer Version (#857) 2023-12-22 01:47:18 -08:00
Yuhong Sun
7433dddac3 Model Server (#695)
Provides the ability to pull out the NLP models into a separate model server which can then be hosted on a GPU instance if desired.
2023-11-06 16:36:09 -08:00