Add /upstream endpoint (#30)

* remove catch-all route to upstream proxy (it was broken anyways)
* add /upstream/:model_id to swap and route to upstream path
* add /upstream HTML endpoint and unlisted option
* add /upstream endpoint to show a list of available models
* add `unlisted` configuration option to omit a model from /v1/models and /upstream lists
* add favicon.ico

.github/workflows/release.yml

@@ -30,4 +30,4 @@ jobs:
           version: '~> v2'
           args: release --clean
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -2,4 +2,5 @@
 .env
 build/
 dist/
-.vscode
+.vscode
+.DS_Store

Makefile

@@ -2,6 +2,16 @@
 APP_NAME = llama-swap
 BUILD_DIR = build
 
+# Get the current Git hash
+GIT_HASH := $(shell git rev-parse --short HEAD)
+ifneq ($(shell git status --porcelain),)
+    # There are untracked changes
+    GIT_HASH := $(GIT_HASH)+
+endif
+
+# Capture the current build date in RFC3339 format
+BUILD_DATE := $(shell date -u +"%Y-%m-%dT%H:%M:%SZ")
+
 # Default target: Builds binaries for both OSX and Linux
 all: mac linux simple-responder
 
@@ -18,12 +28,12 @@ test-all:
 # Build OSX binary
 mac:
 	@echo "Building Mac binary..."
-	GOOS=darwin GOARCH=arm64 go build -o $(BUILD_DIR)/$(APP_NAME)-darwin-arm64
+	GOOS=darwin GOARCH=arm64 go build -ldflags="-X main.commit=${GIT_HASH} -X main.version=local_${GIT_HASH} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-darwin-arm64
 
 # Build Linux binary
 linux:
 	@echo "Building Linux binary..."
-	GOOS=linux GOARCH=amd64 go build -o $(BUILD_DIR)/$(APP_NAME)-linux-amd64
+	GOOS=linux GOARCH=amd64 go build -ldflags="-X main.commit=${GIT_HASH} -X main.version=local_${GIT_HASH} -X main.date=${BUILD_DATE}" -o $(BUILD_DIR)/$(APP_NAME)-linux-amd64
 
 # for testing proxy.Process
 simple-responder:
@@ -35,5 +45,19 @@ simple-responder:
 $(BUILD_DIR):
 	mkdir -p $(BUILD_DIR)
 
+# Create a new release tag
+release:
+	@echo "Checking for unstaged changes..."
+	@if [ -n "$(shell git status --porcelain)" ]; then \
+		echo "Error: There are unstaged changes. Please commit or stash your changes before creating a release tag." >&2; \
+		exit 1; \
+	fi
+
+# Get the highest tag in v{number} format, increment it, and create a new tag
+	@highest_tag=$$(git tag --sort=-v:refname | grep -E '^v[0-9]+$$' | head -n 1 || echo "v0"); \
+	new_tag="v$$(( $${highest_tag#v} + 1 ))"; \
+	echo "tagging new version: $$new_tag"; \
+	git tag "$$new_tag";
+
 # Phony targets
 .PHONY: all clean osx linux

README.md

@@ -8,7 +8,7 @@ llama-swap is an OpenAI API compatible server that gives you complete control ov
 Features:
 
 - ✅ Easy to deploy: single binary with no dependencies
-- ✅ Single yaml configuration file
+- ✅ Easy to config: single yaml file
 - ✅ On-demand model switching
 - ✅ Full control over server settings per model
 - ✅ OpenAI API support (`v1/completions` and `v1/chat/completions`)
@@ -16,6 +16,8 @@ Features:
 - ✅ Run multiple models at once with `profiles`
 - ✅ Remote log monitoring at `/log`
 - ✅ Automatic unloading of models from GPUs after timeout
+- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabblyAPI, etc)
+- ✅ Direct access to proxied upstream HTTP server via `/upstream/:model_id`
 
 ## Releases
 
@@ -72,6 +74,12 @@ models:
       --model path/to/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf
     proxy: http://127.0.0.1:8999
 
+  # unlisted models do not show up in /v1/models or /upstream lists
+  # but they can still be requested as normal
+  "qwen-unlisted":
+    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
+    unlisted: true
+
 # profiles make it easy to managing multi model (and gpu) configurations.
 #
 # Tips:

config.example.yaml

@@ -33,6 +33,7 @@ models:
       - env1=hello
     cmd: build/simple-responder --port 8999
     proxy: http://127.0.0.1:8999
+    unlisted: true
 
     # use "none" to skip check. Caution this may cause some requests to fail
     # until the upstream server is ready for traffic
@@ -42,9 +43,11 @@ models:
   "broken":
     cmd: models/llama-server-osx --port 8999 -m models/doesnotexist.gguf
     proxy: http://127.0.0.1:8999
+    unlisted: true
   "broken_timeout":
     cmd: models/llama-server-osx --port 8999 -m models/qwen2.5-0.5b-instruct-q8_0.gguf
     proxy: http://127.0.0.1:9000
+    unlisted: true
 
 # creating a coding profile with models for code generation and general questions
 profiles:

go.mod

@@ -32,9 +32,9 @@ require (
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/crypto v0.23.0 // indirect
+	golang.org/x/crypto v0.31.0 // indirect
 	golang.org/x/net v0.25.0 // indirect
-	golang.org/x/sys v0.20.0 // indirect
-	golang.org/x/text v0.15.0 // indirect
+	golang.org/x/sys v0.28.0 // indirect
+	golang.org/x/text v0.21.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 )

go.sum

@@ -66,14 +66,20 @@ golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
 golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
 golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
 golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
+golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
+golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
 golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
 golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
 golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
+golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
 golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
+golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
 google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
 google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=

llama-swap.go

@@ -9,13 +9,23 @@ import (
 	"github.com/mostlygeek/llama-swap/proxy"
 )
 
+var version string = "0"
+var commit string = "abcd1234"
+var date = "unknown"
+
 func main() {
 	// Define a command-line flag for the port
 	configPath := flag.String("config", "config.yaml", "config file name")
 	listenStr := flag.String("listen", ":8080", "listen ip/port")
+	showVersion := flag.Bool("version", false, "show version of build")
 
 	flag.Parse() // Parse the command-line flags
 
+	if *showVersion {
+		fmt.Printf("version: %s (%s), built at %s\n", version, commit, date)
+		os.Exit(0)
+	}
+
 	config, err := proxy.LoadConfig(*configPath)
 	if err != nil {
 		fmt.Printf("Error loading config: %v\n", err)

proxy/config.go

@@ -16,6 +16,7 @@ type ModelConfig struct {
 	Env           []string `yaml:"env"`
 	CheckEndpoint string   `yaml:"checkEndpoint"`
 	UnloadAfter   int      `yaml:"ttl"`
+	Unlisted      bool     `yaml:"unlisted"`
 }
 
 func (m *ModelConfig) SanitizedCommand() ([]string, error) {

proxy/logMonitor.go

@@ -46,7 +46,7 @@ func (w *LogMonitor) Write(p []byte) (n int, err error) {
 	w.buffer = w.buffer.Next()
 	w.bufferMu.Unlock()
 
-	w.broadcast(p)
+	w.broadcast(bufferCopy)
 	return n, nil
 }
 

proxy/process.go

@@ -125,11 +125,15 @@ func (p *Process) start() error {
 			maxDuration := time.Duration(p.config.UnloadAfter) * time.Second
 
 			for range time.Tick(time.Second) {
+				if p.state != StateReady {
+					return
+				}
+
 				// wait for all inflight requests to complete and ticker
 				p.inFlightRequests.Wait()
 
 				if time.Since(p.lastRequestHandled) > maxDuration {
-					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %d reached.\n", p.ID, p.config.UnloadAfter)
+					fmt.Fprintf(p.logMonitor, "!!! Unloading model %s, TTL of %ds reached.\n", p.ID, p.config.UnloadAfter)
 					p.Stop()
 				}
 			}
@@ -162,25 +166,25 @@ func (p *Process) Stop() {
 	// will be a source of pain in the future.
 
 	p.cmd.Process.Signal(syscall.SIGTERM)
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	sigtermTimeout, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 
-	done := make(chan error, 1)
+	sigtermNormal := make(chan error, 1)
 	go func() {
-		done <- p.cmd.Wait()
+		sigtermNormal <- p.cmd.Wait()
 	}()
 
 	select {
-	case <-ctx.Done():
-		fmt.Printf("!!! process for %s timed out waiting to stop\n", p.ID)
+	case <-sigtermTimeout.Done():
+		fmt.Fprintf(p.logMonitor, "!!! process for %s timed out waiting to stop\n", p.ID)
 		p.cmd.Process.Kill()
 		p.cmd.Wait()
-	case err := <-done:
+	case err := <-sigtermNormal:
 		if err != nil {
 			if err.Error() != "wait: no child processes" {
 				// possible that simple-responder for testing is just not
 				// existing right, so suppress those errors.
-				fmt.Printf("!!! process for %s stopped with error > %v\n", p.ID, err)
+				fmt.Fprintf(p.logMonitor, "!!! process for %s stopped with error > %v\n", p.ID, err)
 			}
 		}
 	}

proxy/proxymanager.go

@@ -2,10 +2,12 @@ package proxy
 
 import (
 	"bytes"
+	"embed"
 	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"sync"
@@ -18,6 +20,15 @@ const (
 	PROFILE_SPLIT_CHAR = ":"
 )
 
+//go:embed html/favicon.ico
+var faviconData []byte
+
+//go:embed html/logs.html
+var logsHTML []byte
+
+// make sure embed is kept there by the IDE auto-package importer
+var _ = embed.FS{}
+
 type ProxyManager struct {
 	sync.Mutex
 
@@ -48,7 +59,12 @@ func New(config *Config) *ProxyManager {
 	pm.ginEngine.GET("/logs/stream", pm.streamLogsHandler)
 	pm.ginEngine.GET("/logs/streamSSE", pm.streamLogsHandlerSSE)
 
-	pm.ginEngine.NoRoute(pm.proxyNoRouteHandler)
+	pm.ginEngine.GET("/upstream", pm.upstreamIndex)
+	pm.ginEngine.Any("/upstream/:model_id/*upstreamPath", pm.proxyToUpstream)
+
+	pm.ginEngine.GET("/favicon.ico", func(c *gin.Context) {
+		c.Data(http.StatusOK, "image/x-icon", faviconData)
+	})
 
 	// Disable console color for testing
 	gin.DisableConsoleColor()
@@ -86,7 +102,11 @@ func (pm *ProxyManager) stopProcesses() {
 
 func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	data := []interface{}{}
-	for id := range pm.config.Models {
+	for id, modelConfig := range pm.config.Models {
+		if modelConfig.Unlisted {
+			continue
+		}
+
 		data = append(data, map[string]interface{}{
 			"id":       id,
 			"object":   "model",
@@ -113,7 +133,7 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	pm.Lock()
 	defer pm.Unlock()
 
-	// Check if requestedModel contains a /
+	// Check if requestedModel contains a PROFILE_SPLIT_CHAR
 	profileName, modelName := "", requestedModel
 	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
 		profileName = requestedModel[:idx]
@@ -170,6 +190,48 @@ func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
 	return pm.currentProcesses[requestedProcessKey], nil
 }
 
+func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+	requestedModel := c.Param("model_id")
+
+	if requestedModel == "" {
+		c.AbortWithError(http.StatusBadRequest, fmt.Errorf("model id required in path"))
+		return
+	}
+
+	if process, err := pm.swapModel(requestedModel); err != nil {
+		c.AbortWithError(http.StatusNotFound, fmt.Errorf("unable to swap to model, %s", err.Error()))
+	} else {
+		// rewrite the path
+		c.Request.URL.Path = c.Param("upstreamPath")
+		process.ProxyRequest(c.Writer, c.Request)
+	}
+}
+
+func (pm *ProxyManager) upstreamIndex(c *gin.Context) {
+	var html strings.Builder
+
+	html.WriteString("<!doctype HTML>\n<html><body><h1>Available Models</h1><ul>")
+
+	// Extract keys and sort them
+	var modelIDs []string
+	for modelID, modelConfig := range pm.config.Models {
+		if modelConfig.Unlisted {
+			continue
+		}
+
+		modelIDs = append(modelIDs, modelID)
+	}
+	sort.Strings(modelIDs)
+
+	// Iterate over sorted keys
+	for _, modelID := range modelIDs {
+		html.WriteString(fmt.Sprintf("<li><a href=\"/upstream/%s\">%s</a></li>", modelID, modelID))
+	}
+	html.WriteString("</ul></body></html>")
+	c.Header("Content-Type", "text/html")
+	c.String(http.StatusOK, html.String())
+}
+
 func (pm *ProxyManager) proxyChatRequestHandler(c *gin.Context) {
 	bodyBytes, err := io.ReadAll(c.Request.Body)
 	if err != nil {
@@ -201,16 +263,6 @@ func (pm *ProxyManager) proxyChatRequestHandler(c *gin.Context) {
 	}
 }
 
-func (pm *ProxyManager) proxyNoRouteHandler(c *gin.Context) {
-	// since maps are unordered, just use the first available process if one exists
-	for _, process := range pm.currentProcesses {
-		process.ProxyRequest(c.Writer, c.Request)
-		return
-	}
-
-	c.AbortWithError(http.StatusBadRequest, fmt.Errorf("no strategy to handle request"))
-}
-
 func ProcessKeyName(groupName, modelName string) string {
 	return groupName + PROFILE_SPLIT_CHAR + modelName
 }

proxy/proxymanager_loghandlers.go

@@ -1,7 +1,6 @@
 package proxy
 
 import (
-	"embed"
 	"fmt"
 	"net/http"
 	"strings"
@@ -9,12 +8,6 @@ import (
 	"github.com/gin-gonic/gin"
 )
 
-//go:embed html/logs.html
-var logsHTML []byte
-
-// make sure embed is kept there by the IDE auto-package importer
-var _ = embed.FS{}
-
 func (pm *ProxyManager) sendLogsHandlers(c *gin.Context) {
 
 	accept := c.GetHeader("Accept")