New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. Weβll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: add documentation for google vertex ai backend #93
base: main
Are you sure you want to change the base?
Changes from 1 commit
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -2,14 +2,15 @@ | |
|
||
A Backend (also called Provider) is a service that provides access to the AI language model. There are many different backends available for K8sGPT. Each backend has its own strengths and weaknesses, so it is important to choose the one that is right for your needs. | ||
|
||
Currently, we have a total of 8 backends available: | ||
Currently, we have a total of 9 backends available: | ||
|
||
- [OpenAI](https://openai.com/) | ||
- [Cohere](https://cohere.com/) | ||
- [Amazon Bedrock](https://aws.amazon.com/bedrock/) | ||
- [Amazon SageMaker](https://aws.amazon.com/sagemaker/) | ||
- [Azure OpenAI](https://azure.microsoft.com/en-us/products/cognitive-services/openai-service) | ||
- [Google Gemini](https://ai.google.dev/docs/gemini_api_overview) | ||
- [Google Vertex AI](https://cloud.google.com/vertex-ai) | ||
- [LocalAI](https://github.com/go-skynet/LocalAI) | ||
- FakeAI | ||
|
||
|
@@ -110,13 +111,36 @@ Google [Gemini](https://blog.google/technology/ai/google-gemini-ai/#performance) | |
- To use Google Gemini API in K8sGPT, obtain [the API key](https://ai.google.dev/tutorials/setup). | ||
- To configure Google backend in K8sGPT with `gemini-pro` model (see all [models](https://ai.google.dev/models) here) use auth command: | ||
```bash | ||
k8sgpt auth add --backend google --model gemini-pro --password "<Your API KEY>" | ||
k8sgpt auth add --backend googlevertexai --model gemini-pro --password "<Your API KEY>" | ||
``` | ||
- Run the following command to analyze issues within your cluster with the Google provider: | ||
```bash | ||
k8sgpt analyze --explain --backend google | ||
``` | ||
|
||
## Google Gemini via Vertex AI | ||
|
||
Google [Gemini](https://blog.google/technology/ai/google-gemini-ai/#performance) allows generative AI capabilities with multimodal approach (it is capable to understand not only text, but also code, audio, image and video). | ||
|
||
- To use [Google Vertex AI](https://cloud.google.com/vertex-ai?#build-with-gemini) you need to be authorized via [Google Cloud SDK](https://cloud.google.com/sdk/install). | ||
The [Vertex AI API](https://console.cloud.google.com/apis/library/vertex-ai.googleapis.com) needs to be enabled. | ||
|
||
> Note: Vertex AI Gemini API is currently available in these [regions](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini?hl=de#http_request) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Is this expected to change? Maybe write something more along the lines of: This makes it sound more timeless independent to how things change on the Google side :) There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Agree to some degree, the only issue I have is, you can basically use the other regions to debug clusters not in this region. I added a more clarification hope this fits! |
||
|
||
- Open a terminal or command prompt and run the following command to authenticate using your Google Cloud credentials: | ||
```bash | ||
gcloud auth application-default login | ||
``` | ||
|
||
- To configure Google backend in K8sGPT with `gemini-pro` model (see all [models](https://ai.google.dev/models) here) use auth command: | ||
```bash | ||
k8sgpt auth add --backend googlevertexai --model "gemini-pro" --providerRegion "us-central1" --providerId "<your project id>" | ||
``` | ||
- Run the following command to analyze issues within your cluster with the Google provider: | ||
```bash | ||
k8sgpt analyze --explain --backend googlevertexai | ||
``` | ||
|
||
## LocalAI | ||
|
||
LocalAI is a local model, which is an OpenAI compatible API. It uses llama.cpp and ggml to run inference on consumer-grade hardware. Models supported by LocalAI for instance are Vicuna, Alpaca, LLaMA, Cerebras, GPT4ALL, GPT4ALL-J and koala. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We will need to update this once the Hugging Face Docs is merged