Skip to content

Commit

Permalink
fix: Address misnamed paths
Browse files Browse the repository at this point in the history
  • Loading branch information
ishaansehgal99 committed Jan 8, 2025
1 parent 6a98a01 commit 65619da
Show file tree
Hide file tree
Showing 6 changed files with 60 additions and 7 deletions.
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Kubernetes AI Toolchain Operator (Kaito)

![GitHub Release](https://img.shields.io/github/v/release/Azure/kaito)
![GitHub Release](https://img.shields.io/github/v/release/kaito-project/kaito)
[![Go Report Card](https://goreportcard.com/badge/github.com/kaito-project/kaito)](https://goreportcard.com/report/github.com/kaito-project/kaito)
![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/Azure/kaito)
![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/kaito-project/kaito)
[![codecov](https://codecov.io/gh/Azure/kaito/graph/badge.svg?token=XAQLLPB2AR)](https://codecov.io/gh/Azure/kaito)

| ![notification](docs/img/bell.svg) What is NEW! |
Expand Down
2 changes: 1 addition & 1 deletion config/manager/kustomization.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,5 +4,5 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
images:
- name: controller
newName: ghcr.io/azure//kaito
newName: ghcr.io/kaito-project/kaito/workspace
newTag: latest
2 changes: 1 addition & 1 deletion docs/How-to-use-kaito-in-aks-arc.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ AKS Arc, or Azure Kubernetes Service (AKS) on Azure Arc, is a service that exten
Follow the workflow below to enable this feature.

## Supported Models
Currently KAITO supports models such as Falcon, Phi2, Phi3, Llama2, Llama2Chat, Mistral. Please refer to KAITO’s [readme](https://github.com/Azure/kaito/blob/main/presets/README.md) file for the latest models.
Currently KAITO supports models such as Falcon, Phi2, Phi3, Llama2, Llama2Chat, Mistral. Please refer to KAITO’s [readme](https://github.com/kaito-project/kaito/blob/main/presets/README.md) file for the latest models.

## Prerequisite
1. Before you begin, please make sure you have the following details from your infrastructure administrator:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ inference:
spec:
containers:
- name: custom-llm-container
image: ghcr.io/azure/kaito/llm-reference-preset:latest
image: ghcr.io/kaito-project/kaito/llm-reference-preset:latest
command: ["accelerate"]
args:
- "launch"
Expand Down
53 changes: 53 additions & 0 deletions docs/rag-todos.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
apiVersion: kaito.sh/v1alpha1
kind: RAG_Workspace
metadata:
name: random

resources:
- instanceType: "Standard_NC12s_v3"
labelSelector:
matchLabels:
apps: RAG
rag:
index: # Dataset input
# Optional
storage: # Need to handle following: azure, aws, (gcp?), postgresql, data via api
# Example #1
AzureCosmosDB: URI
secret: <secret_store> # Auth (CSI Secret Store)
# Example #2
AWSDocDB: URI
secret: <secret_store> # Auth (CSI Secret Store)
# Example #3
# If blank use data via API and FAISS
# Example #4
# Perssitent Volume - local files (SimpleDirectoryReader)
query: # FAISS (Take out of CRD and put in POST Request)
search_method: "l2" # Voronoi Search, product search

models:
llm:
endpoint: "URL" # Service Endpoint
# -- OR --
secret: # OpenAI Secret (Prorjected Volume)


embedding_model:
endpoint: "URL" # Service Endpoint - need to add presets for embedding
# -- OR --
secret: # OpenAI Secret (Prorjected Volume)
# -- OR --
hf_model:
- name: "BAAI/bge-small-en-v1.5" # model_id
token: # Optional
remote: false # can also run remotely





Whole RAG workflow runs on one node
POST Request for handling Indexing Uses CRD information for Storage Info (Optional)



4 changes: 2 additions & 2 deletions terraform/kaito.tf
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ resource "azurerm_federated_identity_credential" "kaito" {
# Install the gpu-provisioner chart
resource "helm_release" "gpu_provisioner" {
name = "gpu-provisioner"
chart = "https://raw.githubusercontent.com/Azure/kaito/refs/heads/gh-pages/charts/kaito/gpu-provisioner-${var.kaito_gpu_provisioner_version}.tgz"
chart = "https://raw.githubusercontent.com/kaito-project/kaito/refs/heads/gh-pages/charts/kaito/gpu-provisioner-${var.kaito_gpu_provisioner_version}.tgz"
namespace = "gpu-provisioner"
create_namespace = true

Expand All @@ -48,7 +48,7 @@ resource "helm_release" "gpu_provisioner" {
# Install the kaito-workspace chart
resource "helm_release" "kaito_workspace" {
name = "kaito-workspace"
chart = "https://raw.githubusercontent.com/Azure/kaito/refs/heads/gh-pages/charts/kaito/workspace-${var.kaito_workspace_version}.tgz"
chart = "https://raw.githubusercontent.com/kaito-project/kaito/refs/heads/gh-pages/charts/kaito/workspace-${var.kaito_workspace_version}.tgz"
namespace = "kaito-workspace"
create_namespace = true
}
Expand Down

0 comments on commit 65619da

Please sign in to comment.