Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-06 00:54:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Design more api routes

Browse Source
This commit is contained in:
Matúš Námešný
2025-07-18 17:34:04 +02:00
parent bc34408f83
commit 40b020ff3e
1 changed files with 48 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
server/pkg/routes.go
View File

@@ -25,16 +25,55 @@ func SetupRouter(handler *Handler) *chi.Mux {
})
// Instance management endpoints
// r.Get("/instances", handler.ListInstances()) // List all instances
// r.Post("/instances", handler.CreateInstance()) // Create and start new instance
// r.Get("/instances/{id}", handler.GetInstance()) // Get instance details
// r.Put("/instances/{id}", handler.UpdateInstance()) // Update instance configuration
// r.Delete("/instances/{id}", handler.DeleteInstance()) // Stop and remove instance
// r.Post("/instances/{id}/start", handler.StartInstance()) // Start stopped instance
// r.Post("/instances/{id}/stop", handler.StopInstance()) // Stop running instance
// r.Post("/instances/{id}/restart", handler.RestartInstance()) // Restart instance
// r.Get("/instances/{id}/logs", handler.GetInstanceLogs()) // Get instance logs
r.Route("/instances", func(r chi.Router) {
// r.Get("/", handler.ListInstances()) // List all instances
// r.Post("/", handler.CreateInstance()) // Create and start new instance
r.Route("/{id}", func(r chi.Router) {
// Instance management
// r.Get("/", handler.GetInstance()) // Get instance details
// r.Put("/", handler.UpdateInstance()) // Update instance configuration
// r.Delete("/", handler.DeleteInstance()) // Stop and remove instance
// r.Post("/start", handler.StartInstance()) // Start stopped instance
// r.Post("/stop", handler.StopInstance()) // Stop running instance
// r.Post("/restart", handler.RestartInstance()) // Restart instance
// r.Get("/logs", handler.GetInstanceLogs()) // Get instance logs
// Llama.cpp server proxy endpoints (proxied to the actual llama.cpp server)
// r.Get("/health", handler.ProxyHealthCheck()) // Health check
// r.Post("/completion", handler.ProxyCompletion()) // Text completion
// r.Post("/tokenize", handler.ProxyTokenize()) // Tokenize text
// r.Post("/detokenize", handler.ProxyDetokenize()) // Detokenize tokens
// r.Post("/apply-template", handler.ProxyApplyTemplate()) // Apply chat template
// r.Post("/embedding", handler.ProxyEmbedding()) // Generate embeddings
// r.Post("/reranking", handler.ProxyReranking()) // Rerank documents
// r.Post("/rerank", handler.ProxyRerank()) // Rerank documents (alias)
// r.Post("/infill", handler.ProxyInfill()) // Code infilling
// r.Get("/props", handler.ProxyGetProps()) // Get server properties
// r.Post("/props", handler.ProxySetProps()) // Set server properties
// r.Post("/embeddings", handler.ProxyEmbeddings()) // Non-OpenAI embeddings
// r.Get("/slots", handler.ProxyGetSlots()) // Get slots state
// r.Get("/metrics", handler.ProxyGetMetrics()) // Prometheus metrics
// r.Post("/slots/{slot_id}", handler.ProxySlotAction()) // Slot actions (save/restore/erase)
// r.Get("/lora-adapters", handler.ProxyGetLoraAdapters()) // Get LoRA adapters
// r.Post("/lora-adapters", handler.ProxySetLoraAdapters()) // Set LoRA adapters
// OpenAI-compatible endpoints (proxied to the actual llama.cpp server)
// r.Post("/v1/completions", handler.ProxyV1Completions()) // OpenAI completions
// r.Post("/v1/chat/completions", handler.ProxyV1ChatCompletions()) // OpenAI chat completions
// r.Post("/v1/embeddings", handler.ProxyV1Embeddings()) // OpenAI embeddings
// r.Post("/v1/rerank", handler.ProxyV1Rerank()) // OpenAI rerank
// r.Post("/v1/reranking", handler.ProxyV1Reranking()) // OpenAI reranking
})
})
})
// OpenAI-compatible endpoints (model name in request body determines routing)
// r.Post("/v1/completions", handler.OpenAICompletions()) // Route based on model name in request
// r.Post("/v1/chat/completions", handler.OpenAIChatCompletions()) // Route based on model name in request
// r.Post("/v1/embeddings", handler.OpenAIEmbeddings()) // Route based on model name in request (if supported)
// r.Post("/v1/rerank", handler.OpenAIRerank()) // Route based on model name in request (if supported)
// r.Post("/v1/reranking", handler.OpenAIReranking()) // Route based on model name in request (if supported)
return r
}