diff --git a/README.md b/README.md
index 11b1be61..723d760a 100644
--- a/README.md
+++ b/README.md
@@ -38,7 +38,9 @@ curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d
```
-Note: You can use a default template for every model in your model path, by creating a corresponding file with the `.tmpl` suffix next to your model. For instance, if the model is called `foo.bin`, you can create a sibiling file, `foo.bin.tmpl` which will be used as a default prompt, for instance this can be used with alpaca:
+Note: The API doesn't inject a default prompt for talking to the model, while the CLI does. You have to use a prompt similar to what's described in the standford-alpaca docs: https://github.com/tatsu-lab/stanford_alpaca#data-release.
+
+You can use a default template for every model present in your model path, by creating a corresponding file with the `.tmpl` suffix next to your model. For instance, if the model is called `foo.bin`, you can create a sibiling file, `foo.bin.tmpl` which will be used as a default prompt, for instance this can be used with alpaca:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -187,22 +189,6 @@ You can list all the models available with:
curl http://localhost:8080/v1/models
```
-## Web interface
-
-There is also available a simple web interface (for instance, http://localhost:8080/) which can be used as a playground.
-
-Note: The API doesn't inject a template for talking to the instance, while the CLI does. You have to use a prompt similar to what's described in the standford-alpaca docs: https://github.com/tatsu-lab/stanford_alpaca#data-release, for instance:
-
-```
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{instruction}
-
-### Response:
-```
-
-
## Using other models
gpt4all (https://github.com/nomic-ai/gpt4all) works as well, however the original model needs to be converted (same applies for old alpaca models, too):
diff --git a/api/api.go b/api/api.go
index 3667d395..b4781cd0 100644
--- a/api/api.go
+++ b/api/api.go
@@ -1,9 +1,7 @@
package api
import (
- "embed"
"fmt"
- "net/http"
"strings"
"sync"
@@ -12,7 +10,6 @@ import (
llama "github.com/go-skynet/go-llama.cpp"
"github.com/gofiber/fiber/v2"
"github.com/gofiber/fiber/v2/middleware/cors"
- "github.com/gofiber/fiber/v2/middleware/filesystem"
"github.com/gofiber/fiber/v2/middleware/recover"
)
@@ -65,9 +62,6 @@ type OpenAIRequest struct {
IgnoreEOS bool `json:"ignore_eos"`
}
-//go:embed index.html
-var indexHTML embed.FS
-
// https://platform.openai.com/docs/api-reference/completions
func openAIEndpoint(chat bool, loader *model.ModelLoader, threads int, defaultMutex *sync.Mutex, mutexMap *sync.Mutex, mutexes map[string]*sync.Mutex) func(c *fiber.Ctx) error {
return func(c *fiber.Ctx) error {
@@ -234,11 +228,6 @@ func Start(loader *model.ModelLoader, listenAddr string, threads int) error {
})
})
- app.Use("/", filesystem.New(filesystem.Config{
- Root: http.FS(indexHTML),
- NotFoundFile: "index.html",
- }))
-
// Start the server
app.Listen(listenAddr)
return nil
diff --git a/api/index.html b/api/index.html
deleted file mode 100644
index 89b455f0..00000000
--- a/api/index.html
+++ /dev/null
@@ -1,120 +0,0 @@
-
-
-
- llama-cli
-
-
-
-
-
-
-
-
-