darroyo
4c9ed3c24b
Complete rewrite from Python/FastAPI to Go/Gin: - Go backend: auth (API keys + bcrypt), llama.cpp subprocess manager, hot-swap multi-model, rate limiting, quota system, webhooks - Vue 3 SPA admin panel (src/) with Tailwind CSS - Deployment: Docker multi-stage, docker-compose, nginx, systemd - GORM/SQLite models: ApiKey, Model, UsageLog, Quota, Webhook - REST API: /api/v1/admin/* (keys, models, chat, usage, health) - Embedded frontend via go:embed (build output at web/dist/) Removed legacy Python artifacts (app/, tests/, pyproject.toml, etc.)
78 lines
2.4 KiB
Go
78 lines
2.4 KiB
Go
package api
|
|
|
|
import (
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/llamalink/llamalink/internal/api/handlers"
|
|
"github.com/llamalink/llamalink/internal/api/middleware"
|
|
"github.com/llamalink/llamalink/internal/auth"
|
|
"github.com/llamalink/llamalink/internal/config"
|
|
"github.com/llamalink/llamalink/internal/llama"
|
|
"github.com/llamalink/llamalink/internal/quota"
|
|
"gorm.io/gorm"
|
|
)
|
|
|
|
func New(cfg *config.Config, db *gorm.DB, llamaManager *llama.Manager) *gin.Engine {
|
|
if cfg.LlamalinkEnv == "production" {
|
|
gin.SetMode(gin.ReleaseMode)
|
|
}
|
|
|
|
r := gin.New()
|
|
r.Use(gin.Recovery())
|
|
r.Use(gin.Logger())
|
|
|
|
// Initialize services
|
|
authService := auth.NewService(db)
|
|
quotaSvc := quota.NewService(db)
|
|
webhookSvc := quota.NewWebhookService(db)
|
|
proxy := llama.NewProxy(llamaManager)
|
|
|
|
// Initialize handlers
|
|
healthHandler := handlers.NewHealthHandler(db, llamaManager)
|
|
chatHandler := handlers.NewChatHandler(proxy, authService, quotaSvc, webhookSvc)
|
|
keysHandler := handlers.NewKeysHandler(authService)
|
|
modelsHandler := handlers.NewModelsHandler(llamaManager)
|
|
usageHandler := handlers.NewUsageHandler(db, quotaSvc)
|
|
|
|
// Health endpoints (public)
|
|
r.GET("/health", healthHandler.Health)
|
|
r.GET("/ready", healthHandler.Ready)
|
|
|
|
// API v1 group
|
|
v1 := r.Group("/v1")
|
|
|
|
// Chat completions (requires API key auth + chat scope)
|
|
chat := v1.Group("/chat")
|
|
chat.Use(middleware.APIKeyAuth(authService))
|
|
chat.POST("/completions", chatHandler.ChatCompletions)
|
|
|
|
// Keys management (admin only)
|
|
keys := v1.Group("/keys")
|
|
keys.Use(middleware.APIKeyAuth(authService))
|
|
keys.Use(middleware.AdminOnly())
|
|
keys.GET("", keysHandler.ListKeys)
|
|
keys.POST("", keysHandler.CreateKey)
|
|
keys.DELETE("/:id", keysHandler.RevokeKey)
|
|
|
|
// Models management
|
|
models := v1.Group("/models")
|
|
models.Use(middleware.APIKeyAuth(authService))
|
|
models.GET("", modelsHandler.ListModels)
|
|
models.POST("", modelsHandler.CreateModel)
|
|
models.GET("/active", modelsHandler.GetActiveModel)
|
|
models.GET("/:name", modelsHandler.GetActiveModel) // alias for compatibility
|
|
|
|
// Model load (admin only)
|
|
modelLoad := v1.Group("/models")
|
|
modelLoad.Use(middleware.APIKeyAuth(authService))
|
|
modelLoad.Use(middleware.AdminOnly())
|
|
modelLoad.POST("/:name/load", modelsHandler.LoadModel)
|
|
|
|
// Usage (requires API key auth)
|
|
usage := v1.Group("/usage")
|
|
usage.Use(middleware.APIKeyAuth(authService))
|
|
usage.GET("", usageHandler.GetCurrentKeyUsage)
|
|
usage.GET("/:key_id", usageHandler.GetUsage)
|
|
|
|
return r
|
|
}
|