Commit Graph

16 Commits

Author SHA1 Message Date
Guangya Liu
644581f495 fix: disable adding multiple openai provider (#1191)
Signed-off-by: Guangya Liu <gyliu@ibm.com>
Co-authored-by: Matthis <matthish29@gmail.com>
2024-08-20 15:52:44 +02:00
Guangya Liu
d702209941 fix: enabled auth add support watsonx backend (#1190)
Signed-off-by: Guangya Liu <gyliu@ibm.com>
Signed-off-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Matthis <matthish29@gmail.com>
2024-08-20 09:35:45 +02:00
JuHyung Son
4867d39c66 feat: support openai organization Id (#1133)
* feat: add organization flag

Signed-off-by: JuHyung-Son <sonju0427@gmail.com>

* feat: add orgId on openai backend

Signed-off-by: JuHyung-Son <sonju0427@gmail.com>

---------

Signed-off-by: JuHyung-Son <sonju0427@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2024-06-14 08:39:56 +01:00
Rui Chen
e261c09889 fix: remove shorthand flag for topp option in add command (#1115)
Signed-off-by: Rui Chen <rui@chenrui.dev>
2024-05-20 09:06:35 +01:00
Anders Swanson
047afd46d6 feat: oci genai (#1102)
Signed-off-by: Anders Swanson <anders.swanson@oracle.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2024-05-16 15:44:41 +01:00
Vaibhav Malik
eda52312ae feat: implement Top-K sampling for improved user control (#1110)
This commit adds Top-K sampling, a feature that allows users to control
the randomness of the generated text by specifying the number of most
probable next words considered by the model. This enhances user control
and potentially improves the quality of the generated outputs.

Fixes: https://github.com/k8sgpt-ai/k8sgpt/issues/1105

Signed-off-by: VaibhavMalik4187 <vaibhavmalik2018@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2024-05-16 15:41:07 +01:00
Alex Jones
8f8f5c6df7 chore: allows an environmental override of the default AWS region and… (#1025)
* chore: allows an environmental override of the default AWS region and using it for bedrock

Signed-off-by: Alex Jones <alexsimonjones@gmail.com>

* chore: missing provider region

Signed-off-by: Alex Jones <alexsimonjones@gmail.com>

---------

Signed-off-by: Alex Jones <alexsimonjones@gmail.com>
2024-03-22 10:19:11 +00:00
Mario
55ac0b2129 feat: add Google Vertex AI as provider to utilize gemini via GCP (#984)
* feat: add Google Vertex AI as provider to utilize gemini via GCP

Signed-off-by: Mario Fahlandt <mfahlandt@pixel-haufen.de>

* fix: adjust providerId description

Signed-off-by: Mario Fahlandt <mfahlandt@pixel-haufen.de>

---------

Signed-off-by: Mario Fahlandt <mfahlandt@pixel-haufen.de>
Signed-off-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Aris Boutselis <arisboutselis08@gmail.com>
2024-03-11 07:33:29 +00:00
Bartlomiej Plotka
e7d41496dd feat: added Google GenAI client; simplified IAI/clients API surface. (#829)
* refactor: Simplified IAI; made caching and processing consisent.


Signed-off-by: bwplotka <bwplotka@gmail.com>

* feat: Added Google AI API e.g. for Gemini models.

Signed-off-by: bwplotka <bwplotka@gmail.com>

---------

Signed-off-by: bwplotka <bwplotka@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Thomas Schuetz <38893055+thschue@users.noreply.github.com>
2024-01-05 06:53:36 +01:00
DKuroczko
ccef7f6170 feat: amazonsagemaker AI provider (#731)
* feat(amazonsagemaker): Add AmazonSageMaker AI provider

Co-authored-by: NAME 18630245+zaremb@users.noreply.github.com
Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

* feat(amazonsagemaker): Add AmazonSageMaker AI provider

Co-authored-by: Mateusz Zaremba <18630245+zaremb@users.noreply.github.com>
Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

* feat(auth): add top p and max tokens to auth and use them in sagemaker backend

Signed-off-by: Mateusz Zaremba <18630245+zaremb@users.noreply.github.com>

* feat: Updates SageMaker docs, validate topP, ident

Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

* feat: list of passwordlessProviders

Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

* feat: returns err

Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

* fix: remove log.Fatal(err)

Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>

---------

Signed-off-by: Damian Kuroczko <7778327+dkuroczk@users.noreply.github.com>
Signed-off-by: Mateusz Zaremba <18630245+zaremb@users.noreply.github.com>
Co-authored-by: Mateusz Zaremba <18630245+zaremb@users.noreply.github.com>
2023-11-05 20:03:40 +00:00
StevenSu
f1a7801e9e feat: add amazonbedrock (#718)
* add amazonbedrock AI provider

Signed-off-by: Su Wei <suwei007@gmail.com>

* add amazonbedrock, change model list to const var

Signed-off-by: Su Wei <suwei007@gmail.com>

* update iai config and auth cmd, add providerRegion

Signed-off-by: Wei Su <wsuam@amazon.com>

* fix filename wrong

Signed-off-by: Wei Su <wsuam@amazon.com>

* chore: added some doc info

Signed-off-by: Alex Jones <alexsimonjones@gmail.com>

---------

Signed-off-by: Su Wei <suwei007@gmail.com>
Signed-off-by: Wei Su <wsuam@amazon.com>
Signed-off-by: Alex Jones <alexsimonjones@gmail.com>
Co-authored-by: Wei Su <wsuam@amazon.com>
Co-authored-by: Aris Boutselis <aris.boutselis@senseon.io>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2023-10-28 11:49:09 +01:00
Alex Jones
2a34ff24d1 chore: fixing default model issue (#702)
Signed-off-by: Alex Jones <alexsimonjones@gmail.com>
2023-10-11 19:52:47 +01:00
Jian Zhang
7461a748f8 fix: use default values when adding auth (#568)
The `auth add` cmd should use `backend` and `model` default values when user doesn't specify them

Closes: #567

Signed-off-by: Jian Zhang <jiazha@redhat.com>
Co-authored-by: Thomas Schuetz <38893055+thschue@users.noreply.github.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2023-09-19 20:17:19 +01:00
Peter Pan
f55946d60e feat: openAI explicit value for maxToken and temperature (#659)
* feat: openAI explicit value for maxToken and temp

Because when k8sgpt talks with vLLM, the default MaxToken is 16,
which is so small.
Given the most model supports 2048 token(like Llama1 ..etc), so
put here for a safe value.

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

* feat: make temperature a flag

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

---------

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
2023-09-18 13:14:43 +01:00
Alexandre Steppé
da750df16b fix: typo in add command (#539)
Signed-off-by: Alexandre Steppé <alexandre.steppe@gmail.com>
Co-authored-by: Alex Jones <alexsimonjones@gmail.com>
2023-07-04 12:55:06 +01:00
Matthis
c659a875fc feat: rework auth commands (#438)
* feat: rename "auth new" to "auth add"

This change allows to be more consistent with the rest of the code

Signed-off-by: Matthis Holleville <matthish29@gmail.com>

* feat: rework "auth remove" to be more consistent with other remove commands like "filters remove"

Signed-off-by: Matthis Holleville <matthish29@gmail.com>

* feat: update documentation

Signed-off-by: Matthis Holleville <matthish29@gmail.com>

---------

Signed-off-by: Matthis Holleville <matthish29@gmail.com>
2023-05-18 16:50:29 +02:00