chore(docs): extra-Usage and Machine-Tag docs (#4627)

Rename LocalAI-Extra-Usage -> Extra-Usage, add MACHINE_TAG as cli flag option, add docs about extra-usage and machine-tag

Signed-off-by: mintyleaf <mintyleafdev@gmail.com>

core/cli/run.go

@@ -70,7 +70,7 @@ type RunCMD struct {
 	WatchdogBusyTimeout                string   `env:"LOCALAI_WATCHDOG_BUSY_TIMEOUT,WATCHDOG_BUSY_TIMEOUT" default:"5m" help:"Threshold beyond which a busy backend should be stopped" group:"backends"`
 	Federated                          bool     `env:"LOCALAI_FEDERATED,FEDERATED" help:"Enable federated instance" group:"federated"`
 	DisableGalleryEndpoint             bool     `env:"LOCALAI_DISABLE_GALLERY_ENDPOINT,DISABLE_GALLERY_ENDPOINT" help:"Disable the gallery endpoints" group:"api"`
-	MachineTag                         string   `env:"LOCALAI_MACHINE_TAG" help:"Add Machine-Tag header to each response which is useful to track the machine in the P2P network" group:"api"`
+	MachineTag                         string   `env:"LOCALAI_MACHINE_TAG,MACHINE_TAG" help:"Add Machine-Tag header to each response which is useful to track the machine in the P2P network" group:"api"`
 	LoadToMemory                       []string `env:"LOCALAI_LOAD_TO_MEMORY,LOAD_TO_MEMORY" help:"A list of models to load into memory at startup" group:"models"`
 }
 

core/http/endpoints/openai/chat.go

@@ -182,7 +182,7 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
 		c.Set("X-Correlation-ID", correlationID)
 
 		// Opt-in extra usage flag
-		extraUsage := c.Get("LocalAI-Extra-Usage", "") != ""
+		extraUsage := c.Get("Extra-Usage", "") != ""
 
 		modelFile, input, err := readRequest(c, cl, ml, startupOptions, true)
 		if err != nil {

core/http/endpoints/openai/completion.go

@@ -67,7 +67,7 @@ func CompletionEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, e
 		c.Set("X-Correlation-ID", id)
 
 		// Opt-in extra usage flag
-		extraUsage := c.Get("LocalAI-Extra-Usage", "") != ""
+		extraUsage := c.Get("Extra-Usage", "") != ""
 
 		modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
 		if err != nil {

core/http/endpoints/openai/edit.go

@@ -26,7 +26,7 @@ func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
 
 	return func(c *fiber.Ctx) error {
 		// Opt-in extra usage flag
-		extraUsage := c.Get("LocalAI-Extra-Usage", "") != ""
+		extraUsage := c.Get("Extra-Usage", "") != ""
 
 		modelFile, input, err := readRequest(c, cl, ml, appConfig, true)
 		if err != nil {

docs/content/docs/advanced/advanced-usage.md

@@ -520,6 +520,7 @@ In the help text below, BASEPATH is the location that local-ai is being executed
 | --upload-limit | 15 | Default upload-limit in MB | $LOCALAI_UPLOAD_LIMIT |
 | --api-keys | API-KEYS,... | List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys | $LOCALAI_API_KEY |
 | --disable-welcome |  | Disable welcome pages | $LOCALAI_DISABLE_WELCOME |
+| --machine-tag |  | If not empty - put that string to Machine-Tag header in each response. Useful to track response from different machines using multiple P2P federated nodes | $LOCALAI_MACHINE_TAG |
 
 #### Backend Flags
 | Parameter | Default | Description | Environment Variable |
@@ -553,6 +554,34 @@ LOCALAI_MODELS_PATH=/mnt/storage/localai/models
 LOCALAI_F16=true
 ```
 
+### Request headers
+
+You can use 'Extra-Usage' request header key presence ('Extra-Usage: true') to receive inference timings in milliseconds extending default OpenAI response model in the usage field:   
+```
+...
+{
+  "id": "...",
+  "created": ...,
+  "model": "...",
+  "choices": [
+    {
+      ...
+    },
+    ...
+  ],
+  "object": "...",
+  "usage": {
+    "prompt_tokens": ...,
+    "completion_tokens": ...,
+    "total_tokens": ...,
+    // Extra-Usage header key will include these two float fields:
+    "timing_prompt_processing: ...,
+    "timing_token_generation": ...,
+  },
+}
+...
+```
+
 ### Extra backends
 
 LocalAI can be extended with extra backends. The backends are implemented as `gRPC` services and can be written in any language. The container images that are built and published on [quay.io](https://quay.io/repository/go-skynet/local-ai?tab=tags) contain a set of images split in core and extra. By default Images bring all the dependencies and backends supported by LocalAI (we call those `extra` images). The `-core` images instead bring only the strictly necessary dependencies to run LocalAI without only a core set of backends.