mirror of
https://github.com/wavetermdev/waveterm
synced 2026-04-21 14:37:16 +00:00
feat: add NanoGPT as AI provider (#2746)
adds https://nano-gpt.com as a provider
This commit is contained in:
0xGingi
GitHub
parent
1201273bd4
commit
69435aedbb
6 changed files with 113 additions and 4 deletions
|
|
@ -27,6 +27,7 @@ const (
|
|||
DefaultAnthropicModel = "claude-sonnet-4-5"
|
||||
DefaultOpenAIModel = "gpt-5.1"
|
||||
DefaultOpenRouterModel = "mistralai/mistral-small-3.2-24b-instruct"
|
||||
DefaultNanoGPTModel = "zai-org/glm-4.7"
|
||||
DefaultGeminiModel = "gemini-3-pro-preview"
|
||||
)
|
||||
|
||||
|
|
@ -257,6 +258,55 @@ func testOpenRouter(ctx context.Context, model, message string, tools []uctypes.
|
|||
}
|
||||
}
|
||||
|
||||
func testNanoGPT(ctx context.Context, model, message string, tools []uctypes.ToolDefinition) {
|
||||
apiKey := os.Getenv("NANOGPT_KEY")
|
||||
if apiKey == "" {
|
||||
fmt.Println("Error: NANOGPT_KEY environment variable not set")
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
opts := &uctypes.AIOptsType{
|
||||
APIType: uctypes.APIType_OpenAIChat,
|
||||
APIToken: apiKey,
|
||||
Endpoint: "https://nano-gpt.com/api/v1/chat/completions",
|
||||
Model: model,
|
||||
MaxTokens: 4096,
|
||||
}
|
||||
|
||||
chatID := uuid.New().String()
|
||||
|
||||
aiMessage := &uctypes.AIMessage{
|
||||
MessageId: uuid.New().String(),
|
||||
Parts: []uctypes.AIMessagePart{
|
||||
{
|
||||
Type: uctypes.AIMessagePartTypeText,
|
||||
Text: message,
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
fmt.Printf("Testing NanoGPT with WaveAIPostMessageWrap, model: %s\n", model)
|
||||
fmt.Printf("Message: %s\n", message)
|
||||
fmt.Printf("Chat ID: %s\n", chatID)
|
||||
fmt.Println("---")
|
||||
|
||||
testWriter := &TestResponseWriter{}
|
||||
sseHandler := sse.MakeSSEHandlerCh(testWriter, ctx)
|
||||
defer sseHandler.Close()
|
||||
|
||||
chatOpts := uctypes.WaveChatOpts{
|
||||
ChatId: chatID,
|
||||
ClientId: uuid.New().String(),
|
||||
Config: *opts,
|
||||
Tools: tools,
|
||||
SystemPrompt: []string{"You are a helpful assistant. Be concise and clear in your responses."},
|
||||
}
|
||||
err := aiusechat.WaveAIPostMessageWrap(ctx, sseHandler, aiMessage, chatOpts)
|
||||
if err != nil {
|
||||
fmt.Printf("NanoGPT streaming error: %v\n", err)
|
||||
}
|
||||
}
|
||||
|
||||
func testAnthropic(ctx context.Context, model, message string, tools []uctypes.ToolDefinition) {
|
||||
apiKey := os.Getenv("ANTHROPIC_APIKEY")
|
||||
if apiKey == "" {
|
||||
|
|
@ -381,7 +431,7 @@ func testT4(ctx context.Context) {
|
|||
}
|
||||
|
||||
func printUsage() {
|
||||
fmt.Println("Usage: go run main-testai.go [--anthropic|--openaicomp|--openrouter|--gemini] [--tools] [--model <model>] [message]")
|
||||
fmt.Println("Usage: go run main-testai.go [--anthropic|--openaicomp|--openrouter|--nanogpt|--gemini] [--tools] [--model <model>] [message]")
|
||||
fmt.Println("Examples:")
|
||||
fmt.Println(" go run main-testai.go 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --model o4-mini 'What is 2+2?'")
|
||||
|
|
@ -390,6 +440,8 @@ func printUsage() {
|
|||
fmt.Println(" go run main-testai.go --openaicomp --model gpt-4o 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --openrouter 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --openrouter --model anthropic/claude-3.5-sonnet 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --nanogpt 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --nanogpt --model gpt-4o 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --gemini 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --gemini --model gemini-1.5-pro 'What is 2+2?'")
|
||||
fmt.Println(" go run main-testai.go --tools 'Help me configure GitHub Actions monitoring'")
|
||||
|
|
@ -399,24 +451,27 @@ func printUsage() {
|
|||
fmt.Printf(" Anthropic: %s\n", DefaultAnthropicModel)
|
||||
fmt.Printf(" OpenAI Completions: gpt-4o\n")
|
||||
fmt.Printf(" OpenRouter: %s\n", DefaultOpenRouterModel)
|
||||
fmt.Printf(" NanoGPT: %s\n", DefaultNanoGPTModel)
|
||||
fmt.Printf(" Google Gemini: %s\n", DefaultGeminiModel)
|
||||
fmt.Println("")
|
||||
fmt.Println("Environment variables:")
|
||||
fmt.Println(" OPENAI_APIKEY (for OpenAI models)")
|
||||
fmt.Println(" ANTHROPIC_APIKEY (for Anthropic models)")
|
||||
fmt.Println(" OPENROUTER_APIKEY (for OpenRouter models)")
|
||||
fmt.Println(" NANOGPT_KEY (for NanoGPT models)")
|
||||
fmt.Println(" GOOGLE_APIKEY (for Google Gemini models)")
|
||||
}
|
||||
|
||||
func main() {
|
||||
var anthropic, openaicomp, openrouter, gemini, tools, help, t1, t2, t3, t4 bool
|
||||
var anthropic, openaicomp, openrouter, nanogpt, gemini, tools, help, t1, t2, t3, t4 bool
|
||||
var model string
|
||||
flag.BoolVar(&anthropic, "anthropic", false, "Use Anthropic API instead of OpenAI")
|
||||
flag.BoolVar(&openaicomp, "openaicomp", false, "Use OpenAI Completions API")
|
||||
flag.BoolVar(&openrouter, "openrouter", false, "Use OpenRouter API")
|
||||
flag.BoolVar(&nanogpt, "nanogpt", false, "Use NanoGPT API")
|
||||
flag.BoolVar(&gemini, "gemini", false, "Use Google Gemini API")
|
||||
flag.BoolVar(&tools, "tools", false, "Enable GitHub Actions Monitor tools for testing")
|
||||
flag.StringVar(&model, "model", "", fmt.Sprintf("AI model to use (defaults: %s for OpenAI, %s for Anthropic, %s for OpenRouter, %s for Gemini)", DefaultOpenAIModel, DefaultAnthropicModel, DefaultOpenRouterModel, DefaultGeminiModel))
|
||||
flag.StringVar(&model, "model", "", fmt.Sprintf("AI model to use (defaults: %s for OpenAI, %s for Anthropic, %s for OpenRouter, %s for NanoGPT, %s for Gemini)", DefaultOpenAIModel, DefaultAnthropicModel, DefaultOpenRouterModel, DefaultNanoGPTModel, DefaultGeminiModel))
|
||||
flag.BoolVar(&help, "help", false, "Show usage information")
|
||||
flag.BoolVar(&t1, "t1", false, fmt.Sprintf("Run preset T1 test (%s with 'what is 2+2')", DefaultAnthropicModel))
|
||||
flag.BoolVar(&t2, "t2", false, fmt.Sprintf("Run preset T2 test (%s with 'what is 2+2')", DefaultOpenAIModel))
|
||||
|
|
@ -457,6 +512,8 @@ func main() {
|
|||
model = "gpt-4o"
|
||||
} else if openrouter {
|
||||
model = DefaultOpenRouterModel
|
||||
} else if nanogpt {
|
||||
model = DefaultNanoGPTModel
|
||||
} else if gemini {
|
||||
model = DefaultGeminiModel
|
||||
} else {
|
||||
|
|
@ -481,6 +538,8 @@ func main() {
|
|||
testOpenAIComp(ctx, model, message, toolDefs)
|
||||
} else if openrouter {
|
||||
testOpenRouter(ctx, model, message, toolDefs)
|
||||
} else if nanogpt {
|
||||
testNanoGPT(ctx, model, message, toolDefs)
|
||||
} else if gemini {
|
||||
testGemini(ctx, model, message, toolDefs)
|
||||
} else {
|
||||
|
|
|
|||
|
|
@ -34,6 +34,7 @@ Wave AI now supports provider-based configuration which automatically applies se
|
|||
|
||||
- **`openai`** - OpenAI API (automatically configures endpoint and secret name) [[see example](#openai)]
|
||||
- **`openrouter`** - OpenRouter API (automatically configures endpoint and secret name) [[see example](#openrouter)]
|
||||
- **`nanogpt`** - NanoGPT API (automatically configures endpoint and secret name) [[see example](#nanogpt)]
|
||||
- **`google`** - Google AI (Gemini) [[see example](#google-ai-gemini)]
|
||||
- **`azure`** - Azure OpenAI Service (modern API) [[see example](#azure-openai-modern-api)]
|
||||
- **`azure-legacy`** - Azure OpenAI Service (legacy deployment API) [[see example](#azure-openai-legacy-deployment-api)]
|
||||
|
|
@ -260,6 +261,40 @@ For OpenRouter, you must manually specify `ai:capabilities` based on your model'
|
|||
```
|
||||
:::
|
||||
|
||||
### NanoGPT
|
||||
|
||||
[NanoGPT](https://nano-gpt.com) provides access to multiple AI models at competitive prices. Using the `nanogpt` provider simplifies configuration:
|
||||
|
||||
```json
|
||||
{
|
||||
"nanogpt-glm47": {
|
||||
"display:name": "NanoGPT - GLM 4.7",
|
||||
"ai:provider": "nanogpt",
|
||||
"ai:model": "zai-org/glm-4.7"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The provider automatically sets:
|
||||
- `ai:endpoint` to `https://nano-gpt.com/api/v1/chat/completions`
|
||||
- `ai:apitype` to `openai-chat`
|
||||
- `ai:apitokensecretname` to `NANOGPT_KEY` (store your NanoGPT API key with this name)
|
||||
|
||||
:::note
|
||||
NanoGPT is a proxy service that provides access to multiple AI models. You must manually specify `ai:capabilities` based on the model's features. NanoGPT supports OpenAI-compatible tool calling for models that have that capability. Check the model's `capabilities.vision` field from the [NanoGPT models API](https://nano-gpt.com/api/v1/models?detailed=true) to determine image support. Example for a text-only model with tool support:
|
||||
```json
|
||||
{
|
||||
"nanogpt-glm47": {
|
||||
"display:name": "NanoGPT - GLM 4.7",
|
||||
"ai:provider": "nanogpt",
|
||||
"ai:model": "zai-org/glm-4.7",
|
||||
"ai:capabilities": ["tools"]
|
||||
}
|
||||
}
|
||||
```
|
||||
For vision-capable models like `openai/gpt-5`, add `"images"` to capabilities.
|
||||
:::
|
||||
|
||||
### Google AI (Gemini)
|
||||
|
||||
[Google AI](https://ai.google.dev) provides the Gemini family of models. Using the `google` provider simplifies configuration:
|
||||
|
|
|
|||
|
|
@ -27,6 +27,7 @@ const (
|
|||
AIProvider_Wave = "wave"
|
||||
AIProvider_Google = "google"
|
||||
AIProvider_OpenRouter = "openrouter"
|
||||
AIProvider_NanoGPT = "nanogpt"
|
||||
AIProvider_OpenAI = "openai"
|
||||
AIProvider_Azure = "azure"
|
||||
AIProvider_AzureLegacy = "azure-legacy"
|
||||
|
|
|
|||
|
|
@ -21,6 +21,7 @@ const (
|
|||
OpenAIResponsesEndpoint = "https://api.openai.com/v1/responses"
|
||||
OpenAIChatEndpoint = "https://api.openai.com/v1/chat/completions"
|
||||
OpenRouterChatEndpoint = "https://openrouter.ai/api/v1/chat/completions"
|
||||
NanoGPTChatEndpoint = "https://nano-gpt.com/api/v1/chat/completions"
|
||||
AzureLegacyEndpointTemplate = "https://%s.openai.azure.com/openai/deployments/%s/chat/completions?api-version=%s"
|
||||
AzureResponsesEndpointTemplate = "https://%s.openai.azure.com/openai/v1/responses"
|
||||
AzureChatEndpointTemplate = "https://%s.openai.azure.com/openai/v1/chat/completions"
|
||||
|
|
@ -30,6 +31,7 @@ const (
|
|||
|
||||
OpenAIAPITokenSecretName = "OPENAI_KEY"
|
||||
OpenRouterAPITokenSecretName = "OPENROUTER_KEY"
|
||||
NanoGPTAPITokenSecretName = "NANOGPT_KEY"
|
||||
AzureOpenAIAPITokenSecretName = "AZURE_OPENAI_KEY"
|
||||
GoogleAIAPITokenSecretName = "GOOGLE_AI_KEY"
|
||||
)
|
||||
|
|
@ -99,6 +101,17 @@ func applyProviderDefaults(config *wconfig.AIModeConfigType) {
|
|||
config.APITokenSecretName = OpenRouterAPITokenSecretName
|
||||
}
|
||||
}
|
||||
if config.Provider == uctypes.AIProvider_NanoGPT {
|
||||
if config.APIType == "" {
|
||||
config.APIType = uctypes.APIType_OpenAIChat
|
||||
}
|
||||
if config.Endpoint == "" {
|
||||
config.Endpoint = NanoGPTChatEndpoint
|
||||
}
|
||||
if config.APITokenSecretName == "" {
|
||||
config.APITokenSecretName = NanoGPTAPITokenSecretName
|
||||
}
|
||||
}
|
||||
if config.Provider == uctypes.AIProvider_AzureLegacy {
|
||||
if config.AzureAPIVersion == "" {
|
||||
config.AzureAPIVersion = AzureLegacyDefaultAPIVersion
|
||||
|
|
|
|||
|
|
@ -274,7 +274,7 @@ type AIModeConfigType struct {
|
|||
DisplayOrder float64 `json:"display:order,omitempty"`
|
||||
DisplayIcon string `json:"display:icon,omitempty"`
|
||||
DisplayDescription string `json:"display:description,omitempty"`
|
||||
Provider string `json:"ai:provider,omitempty" jsonschema:"enum=wave,enum=google,enum=openrouter,enum=openai,enum=azure,enum=azure-legacy,enum=custom"`
|
||||
Provider string `json:"ai:provider,omitempty" jsonschema:"enum=wave,enum=google,enum=openrouter,enum=nanogpt,enum=openai,enum=azure,enum=azure-legacy,enum=custom"`
|
||||
APIType string `json:"ai:apitype,omitempty" jsonschema:"enum=google-gemini,enum=openai-responses,enum=openai-chat"`
|
||||
Model string `json:"ai:model,omitempty"`
|
||||
ThinkingLevel string `json:"ai:thinkinglevel,omitempty" jsonschema:"enum=low,enum=medium,enum=high"`
|
||||
|
|
|
|||
|
|
@ -21,6 +21,7 @@
|
|||
"wave",
|
||||
"google",
|
||||
"openrouter",
|
||||
"nanogpt",
|
||||
"openai",
|
||||
"azure",
|
||||
"azure-legacy",
|
||||
|
|
|
|||
Loading…
Reference in a new issue