Merge pull request kubeagi#446 from Abirdcfly/typo

feat: add spell test and fix existed misspellings

.github/.codespellignore

@@ -0,0 +1 @@
+ue

.github/workflows/codespell.yaml

@@ -0,0 +1,19 @@
+name: Common misspellings
+
+on: pull_request
+
+jobs:
+  misspellings:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up misspell
+        uses: codespell-project/actions-codespell@v2
+        # plese update Makefile as well
+        with:
+          ignore_words_file: .github/.codespellignore
+          check_filenames: true
+          skip: go.*,**/*.drawio,./deploy/charts/*,./config/crd/*
+

Makefile

@@ -300,3 +300,9 @@ DATA_PROCESSING_IMAGE ?= kubebb/dp-base
 .PHONY: docker-build-dp-base
 docker-build-dp-base:
 	docker build -f ./data-process/Dockerfile.base -t $(DATA_PROCESSING_IMAGE):$(VERSION) ./data-process/
+
+.PHONY: codespell
+codespell:
+	echo "you need: pip install codespell"
+	# please update .github/workflows/codespell.yaml as well
+	codespell -w --ignore-words ".github/.codespellignore" --check-filenames --skip "go.*,**/*.drawio,./deploy/charts/*,./config/crd/*"

README.md

@@ -13,15 +13,15 @@
 
 ## What is Arcadia?
 
-**Arcadia** comes from [Greek mythology](https://www.greekmythology.com/Myths/Places/Arcadia/arcadia.html)(a tranquil and idyllic region, representing harmony, serenity, and natural beauty).We aim to help everyone find a more perfect integration between humans and AI.
+**Arcadia** comes from [Greek mythology](https://www.greekmythology.com/Myths/Places/Arcadia/arcadia.html)(a tranquil and idyllic region, representing harmony, serenity, and natural beauty). We aim to help everyone find a more perfect integration between humans and AI.
 
-To archieve this goal, we provides this one-stop LLMOps solution:
+To achieve this goal, we provide this one-stop LLMOps solution:
 
 - Dataset Management: storage/real-time data,multimodal,pre-processing,vectorization
 - Models Management: local/online LLMs(development,training,deployment),inference acceleration
 - Application Management: development,optimization,deployment with visual editor
 
-Furthermore,we can easily host **Arcadia** at any kubernetes cluster as production ready by integrating [kubebb](https://github.com/kubebb)(A kubernetes building blocks),
+Furthermore, we can easily host **Arcadia** at any kubernetes cluster as production ready by integrating [kubebb](https://github.com/kubebb)(A kubernetes building blocks).
 
 ## Architecture
 
@@ -37,7 +37,7 @@ Our design and development in Arcadia design follows operator pattern which exte
 
 2. [Kubernetes](https://kubernetes.io/)
 
-If you don't have a kubernetes cluster, you can schedule a [kind cluster](https://kind.sigs.k8s.io/). Depends on your choice on CPU or GPU when running LLM worker,you can choose to:
+If you don't have a kubernetes cluster, you can schedule a [kind cluster](https://kind.sigs.k8s.io/). Depends on your choice on CPU or GPU when running LLM worker, you can choose to:
 
 - [Create a kind cluster with/without GPU enabled](http://kubeagi.k8s.com.cn/docs/Quick%20Start/create-cluster-using-kind)
 
@@ -54,7 +54,7 @@ We provide a Command Line Tool `arctl` to interact with `arcadia`. See [here](./
 
 ## Pure Go Toolchains
 
-To enhace the AI capability in Golang, we developed some packages.Here are the examples of how to use them.
+To enhance the AI capability in Golang, we developed some packages.Here are the examples of how to use them.
 
 - [chat_with_document](https://github.com/kubeagi/arcadia/tree/main/examples/chat_with_document): a chat server which allows you to chat with your document
 - [embedding](https://github.com/kubeagi/arcadia/tree/main/examples/embedding) shows how to embedes your document to vector store with embedding service

api/base/v1alpha1/common.go

@@ -53,18 +53,18 @@ const (
 
 // Provider defines how to prvoide the service
 type Provider struct {
-	// Enpoint defines connection info
-	Enpoint *Endpoint `json:"endpoint,omitempty"`
+	// Endpoint defines connection info
+	Endpoint *Endpoint `json:"endpoint,omitempty"`
 
 	// Worker defines the worker info
 	// Means this LLM is provided by a arcadia worker
 	Worker *TypedObjectReference `json:"worker,omitempty"`
 }
 
-// GetType returnes the type of this provider
+// GetType returns the type of this provider
 func (p Provider) GetType() ProviderType {
 	// if endpoint provided, then 3rd_party
-	if p.Enpoint != nil {
+	if p.Endpoint != nil {
 		return ProviderType3rdParty
 	}
 	// if worker provided, then worker

api/base/v1alpha1/datasource_types.go

@@ -27,8 +27,8 @@ import (
 type DatasourceSpec struct {
 	CommonSpec `json:",inline"`
 
-	// Enpoint defines connection info
-	Enpoint Endpoint `json:"endpoint"`
+	// Endpoint defines connection info
+	Endpoint Endpoint `json:"endpoint"`
 
 	// OSS defines info for object storage service
 	OSS *OSS `json:"oss,omitempty"`

api/base/v1alpha1/embedder.go

@@ -26,10 +26,10 @@ import (
 )
 
 func (e Embedder) AuthAPIKey(ctx context.Context, c client.Client, cli dynamic.Interface) (string, error) {
-	if e.Spec.Enpoint == nil {
+	if e.Spec.Endpoint == nil {
 		return "", nil
 	}
-	return e.Spec.Enpoint.AuthAPIKey(ctx, e.GetNamespace(), c, cli)
+	return e.Spec.Endpoint.AuthAPIKey(ctx, e.GetNamespace(), c, cli)
 }
 
 // GetModelList returns a model list provided by this LLM based on different provider

api/base/v1alpha1/llm.go

@@ -26,10 +26,10 @@ import (
 )
 
 func (llm LLM) AuthAPIKey(ctx context.Context, c client.Client, cli dynamic.Interface) (string, error) {
-	if llm.Spec.Enpoint == nil {
+	if llm.Spec.Endpoint == nil {
 		return "", nil
 	}
-	return llm.Spec.Enpoint.AuthAPIKey(ctx, llm.GetNamespace(), c, cli)
+	return llm.Spec.Endpoint.AuthAPIKey(ctx, llm.GetNamespace(), c, cli)
 }
 
 func (llmStatus LLMStatus) LLMReady() (string, bool) {

api/base/v1alpha1/model_types.go

@@ -28,7 +28,7 @@ type ModelSpec struct {
 	CommonSpec `json:",inline"`
 
 	// Type defines what kind of model this is
-	// Comma separated field which can be wrapped by {llm,embdding}
+	// Comma separated field which can be wrapped by {llm,embedding}
 	Types string `json:"types,omitempty"`
 
 	// TODO: extend model to utilize third party storage sources

api/base/v1alpha1/vectorstore.go

@@ -33,7 +33,7 @@ const (
 )
 
 func (vs VectorStoreSpec) Type() VectorStoreType {
-	if vs.Enpoint == nil {
+	if vs.Endpoint == nil {
 		return VectorStoreTypeUnknown
 	}
 

api/base/v1alpha1/vectorstore_types.go

@@ -25,8 +25,8 @@ import (
 type VectorStoreSpec struct {
 	CommonSpec `json:",inline"`
 
-	// Enpoint defines connection info
-	Enpoint *Endpoint `json:"endpoint,omitempty"`
+	// Endpoint defines connection info
+	Endpoint *Endpoint `json:"endpoint,omitempty"`
 
 	Chroma *Chroma `json:"chroma,omitempty"`
 }

apiserver/examples/upload-download-file/README.md

@@ -117,7 +117,7 @@ I1220 14:44:59.444794   12365 main.go:424] [Step 5], Congratulations, the file w
 I1211 15:16:42.701067 2904044 main.go:410] [Step 1] get file size
 I1211 15:16:42.703150 2904044 main.go:436] [DEBUG] file size is 51392595
 I1211 15:16:42.703168 2904044 main.go:440] [Step 2] create local file tmp.gz
-I1211 15:16:42.703225 2904044 main.go:461] [Step 3] start to donwload...
+I1211 15:16:42.703225 2904044 main.go:461] [Step 3] start to download...
 I1211 15:16:42.703303 2904044 main.go:482] [Chunk 41943040-51392595] send request to http://localhost:8099/bff/versioneddataset/files/download?bucket=abc&bucketPath=def&end=51392595&fileName=tmp.tar.gz&from=41943040
 I1211 15:16:42.703391 2904044 main.go:482] [Chunk 10485760-20971520] send request to http://localhost:8099/bff/versioneddataset/files/download?bucket=abc&bucketPath=def&end=20971520&fileName=tmp.tar.gz&from=10485760
 I1211 15:16:42.703452 2904044 main.go:482] [Chunk 20971520-31457280] send request to http://localhost:8099/bff/versioneddataset/files/download?bucket=abc&bucketPath=def&end=31457280&fileName=tmp.tar.gz&from=20971520

apiserver/examples/upload-download-file/main.go

@@ -490,7 +490,7 @@ func downloadFile(bucket, bucketPath, fileName string, transport http.RoundTripp
 	first := true
 	lock := make(chan struct{}, 1)
 	done := true
-	klog.Infof("[Step 3] start to donwload...")
+	klog.Infof("[Step 3] start to download...")
 	var wg sync.WaitGroup
 	for i := 0; i < int(parts); i++ {
 		if !first {

apiserver/pkg/application/application.go

@@ -276,7 +276,7 @@ func ListApplicationMeatadatas(ctx context.Context, c dynamic.Interface, input g
 		return res.Items[i].GetCreationTimestamp().After(res.Items[j].GetCreationTimestamp().Time)
 	})
 
-	filterd := make([]generated.PageNode, 0)
+	filtered := make([]generated.PageNode, 0)
 	for _, u := range res.Items {
 		if keyword != "" {
 			displayName, _, _ := unstructured.NestedString(u.Object, "spec", "displayName")
@@ -288,25 +288,25 @@ func ListApplicationMeatadatas(ctx context.Context, c dynamic.Interface, input g
 		if err != nil {
 			return nil, err
 		}
-		filterd = append(filterd, m)
+		filtered = append(filtered, m)
 	}
-	totalCount := len(filterd)
+	totalCount := len(filtered)
 
 	end := page * pageSize
 	if end > totalCount {
 		end = totalCount
 	}
 	start := (page - 1) * pageSize
 	if start < totalCount {
-		filterd = filterd[start:end]
+		filtered = filtered[start:end]
 	} else {
-		filterd = []generated.PageNode{}
+		filtered = []generated.PageNode{}
 	}
 
 	return &generated.PaginatedResult{
 		TotalCount:  totalCount,
 		HasNextPage: end < totalCount,
-		Nodes:       filterd,
+		Nodes:       filtered,
 		Page:        &page,
 		PageSize:    &pageSize,
 	}, nil

apiserver/pkg/common/common.go

@@ -72,7 +72,7 @@ func SystemDatasourceOSS(ctx context.Context, mgrClient client.Client, dynamicCl
 	if err != nil {
 		return nil, err
 	}
-	endpoint := systemDatasource.Spec.Enpoint.DeepCopy()
+	endpoint := systemDatasource.Spec.Endpoint.DeepCopy()
 	if endpoint.AuthSecret != nil && endpoint.AuthSecret.Namespace == nil {
 		endpoint.AuthSecret.WithNameSpace(systemDatasource.Namespace)
 	}

apiserver/pkg/common/endpoint.go

@@ -118,7 +118,7 @@ func MakeAuthSecret(ctx context.Context, c dynamic.Interface, secret generated.T
 
 	_, err = ResouceGet(ctx, c, secret, metav1.GetOptions{})
 	if err != nil {
-		// Create is not fount
+		// Create is not found
 		if apierrors.IsNotFound(err) {
 			_, err = c.Resource(schema.GroupVersionResource{Group: corev1.SchemeGroupVersion.Group, Version: corev1.SchemeGroupVersion.Version, Resource: "secrets"}).
 				Namespace(*secret.Namespace).Create(ctx, &unstructured.Unstructured{Object: unstructuredDatasource}, metav1.CreateOptions{})

apiserver/pkg/datasource/datasource.go

@@ -58,14 +58,14 @@ func datasource2model(obj *unstructured.Unstructured) *generated.Datasource {
 
 	// parse endpoint
 	endpoint := generated.Endpoint{
-		URL:      &datasource.Spec.Enpoint.URL,
-		Insecure: &datasource.Spec.Enpoint.Insecure,
+		URL:      &datasource.Spec.Endpoint.URL,
+		Insecure: &datasource.Spec.Endpoint.Insecure,
 	}
-	if datasource.Spec.Enpoint.AuthSecret != nil {
+	if datasource.Spec.Endpoint.AuthSecret != nil {
 		endpoint.AuthSecret = &generated.TypedObjectReference{
 			Kind:      "Secret",
-			Name:      datasource.Spec.Enpoint.AuthSecret.Name,
-			Namespace: datasource.Spec.Enpoint.AuthSecret.Namespace,
+			Name:      datasource.Spec.Endpoint.AuthSecret.Name,
+			Namespace: datasource.Spec.Endpoint.AuthSecret.Namespace,
 		}
 	}
 
@@ -132,7 +132,7 @@ func CreateDatasource(ctx context.Context, c dynamic.Interface, input generated.
 	if err != nil {
 		return nil, err
 	}
-	datasource.Spec.Enpoint = endpoint
+	datasource.Spec.Endpoint = endpoint
 
 	if input.Ossinput != nil {
 		datasource.Spec.OSS = &v1alpha1.OSS{
@@ -206,7 +206,7 @@ func UpdateDatasource(ctx context.Context, c dynamic.Interface, input *generated
 		if err != nil {
 			return nil, err
 		}
-		datasource.Spec.Enpoint = endpoint
+		datasource.Spec.Endpoint = endpoint
 	}
 
 	// Update ossinput

apiserver/pkg/embedder/embedder.go

@@ -61,7 +61,7 @@ func Embedder2model(ctx context.Context, c dynamic.Interface, obj *unstructured.
 	case v1alpha1.ProviderTypeWorker:
 		baseURL, _ = common.GetAPIServer(ctx, c, true)
 	case v1alpha1.ProviderType3rdParty:
-		baseURL = embedder.Spec.Enpoint.URL
+		baseURL = embedder.Spec.Endpoint.URL
 	}
 
 	md := generated.Embedder{
@@ -112,7 +112,7 @@ func CreateEmbedder(ctx context.Context, c dynamic.Interface, input generated.Cr
 				Description: description,
 			},
 			Provider: v1alpha1.Provider{
-				Enpoint: &v1alpha1.Endpoint{
+				Endpoint: &v1alpha1.Endpoint{
 					URL: input.Endpointinput.URL,
 				},
 			},
@@ -131,7 +131,7 @@ func CreateEmbedder(ctx context.Context, c dynamic.Interface, input generated.Cr
 		if err != nil {
 			return nil, err
 		}
-		embedder.Spec.Enpoint.AuthSecret = &v1alpha1.TypedObjectReference{
+		embedder.Spec.Endpoint.AuthSecret = &v1alpha1.TypedObjectReference{
 			Kind:      "Secret",
 			Name:      secret,
 			Namespace: &input.Namespace,

apiserver/pkg/knowledgebase/knowledgebase.go

@@ -116,7 +116,7 @@ func knowledgebase2model(obj *unstructured.Unstructured) *generated.KnowledgeBas
 	return &md
 }
 
-func CreateKnowledgeBase(ctx context.Context, c dynamic.Interface, name, namespace, displayname, discription, embedder string, vectorstore v1alpha1.TypedObjectReference, filegroups []v1alpha1.FileGroup) (*generated.KnowledgeBase, error) {
+func CreateKnowledgeBase(ctx context.Context, c dynamic.Interface, name, namespace, displayname, description, embedder string, vectorstore v1alpha1.TypedObjectReference, filegroups []v1alpha1.FileGroup) (*generated.KnowledgeBase, error) {
 	knowledgebase := v1alpha1.KnowledgeBase{
 		ObjectMeta: metav1.ObjectMeta{
 			Name:      name,
@@ -129,7 +129,7 @@ func CreateKnowledgeBase(ctx context.Context, c dynamic.Interface, name, namespa
 		Spec: v1alpha1.KnowledgeBaseSpec{
 			CommonSpec: v1alpha1.CommonSpec{
 				DisplayName: displayname,
-				Description: discription,
+				Description: description,
 			},
 			Embedder: &v1alpha1.TypedObjectReference{
 				Kind:      "Embedder",

apiserver/pkg/llm/llm.go

@@ -59,7 +59,7 @@ func LLM2model(ctx context.Context, c dynamic.Interface, obj *unstructured.Unstr
 	case v1alpha1.ProviderTypeWorker:
 		baseURL, _ = common.GetAPIServer(ctx, c, true)
 	case v1alpha1.ProviderType3rdParty:
-		baseURL = llm.Spec.Enpoint.URL
+		baseURL = llm.Spec.Endpoint.URL
 	}
 
 	md := generated.Llm{
@@ -188,7 +188,7 @@ func CreateLLM(ctx context.Context, c dynamic.Interface, input generated.CreateL
 				Description: description,
 			},
 			Provider: v1alpha1.Provider{
-				Enpoint: &v1alpha1.Endpoint{
+				Endpoint: &v1alpha1.Endpoint{
 					URL: input.Endpointinput.URL,
 				},
 			},
@@ -206,7 +206,7 @@ func CreateLLM(ctx context.Context, c dynamic.Interface, input generated.CreateL
 		if err != nil {
 			return nil, err
 		}
-		llm.Spec.Enpoint.AuthSecret = &v1alpha1.TypedObjectReference{
+		llm.Spec.Endpoint.AuthSecret = &v1alpha1.TypedObjectReference{
 			Kind:      "Secret",
 			Name:      secret,
 			Namespace: &input.Namespace,

apiserver/pkg/model/model.go

@@ -286,7 +286,7 @@ func ModelFiles(ctx context.Context, c dynamic.Interface, modelName, namespace s
 		return nil, err
 	}
 
-	endpoint := systemDatasource.Spec.Enpoint.DeepCopy()
+	endpoint := systemDatasource.Spec.Endpoint.DeepCopy()
 	if endpoint.AuthSecret != nil && endpoint.AuthSecret.Namespace == nil {
 		endpoint.AuthSecret.WithNameSpace(systemDatasource.Namespace)
 	}