add suffix

docs/openai.md

@@ -27,6 +27,11 @@ chat_completion = client.chat.completions.create(
     ],
     model='llama3',
 )
+
+completion = client.completions.create(
+    model="llama3",
+    prompt="Say this is a test"
+)
 ```
 
 ### OpenAI JavaScript library
@@ -45,6 +50,11 @@ const chatCompletion = await openai.chat.completions.create({
   messages: [{ role: 'user', content: 'Say this is a test' }],
   model: 'llama3',
 })
+
+const completion = await openai.completions.create({
+    model: "llama3",
+    prompt: "Say this is a test.",
+})
 ```
 
 ### `curl`
@@ -66,6 +76,12 @@ curl http://localhost:11434/v1/chat/completions \
         ]
     }'
 
+curl http://localhost:11434/v1/completions \
+    -H "Content-Type: application/json" \
+    -d '{
+        "model": "llama3",
+        "prompt": "Say this is a test"
+    }'
 ```
 
 ## Endpoints
@@ -103,8 +119,71 @@ curl http://localhost:11434/v1/chat/completions \
 - [ ] `user`
 - [ ] `n`
 
+### `/v1/completions`
+
+#### Supported features
+
+- [x] Completions
+- [x] Streaming
+- [x] JSON mode
+- [x] Reproducible outputs
+- [ ] Logprobs
+
+#### Supported request fields
+
+- [x] `model`
+- [x] `prompt`
+- [x] `frequency_penalty`
+- [x] `presence_penalty`
+- [x] `seed`
+- [x] `stop`
+- [x] `stream`
+- [x] `temperature`
+- [x] `top_p`
+- [x] `max_tokens`
+- [x] `suffix`
+- [ ] `best_of`
+- [ ] `echo`
+- [ ] `logit_bias`
+- [ ] `user`
+- [ ] `n`
+
 #### Notes
 
+- `prompt` currently only accepts a string
+
+### `/v1/completions`
+
+#### Supported features
+
+- [x] Completions
+- [x] Streaming
+- [x] JSON mode
+- [x] Reproducible outputs
+- [ ] Logprobs
+
+#### Supported request fields
+
+- [x] `model`
+- [x] `prompt`
+- [x] `frequency_penalty`
+- [x] `presence_penalty`
+- [x] `seed`
+- [x] `stop`
+- [x] `stream`
+- [x] `temperature`
+- [x] `top_p`
+- [x] `max_tokens`
+- [ ] `best_of`
+- [ ] `echo`
+- [ ] `suffix`
+- [ ] `logit_bias`
+- [ ] `user`
+- [ ] `n`
+
+#### Notes
+
+- `prompt` currently only accepts a string
 - `usage.prompt_tokens` will be 0 for completions where prompt evaluation is cached
 
 ## Models

server/images.go

@@ -492,12 +492,6 @@ func CreateModel(ctx context.Context, name model.Name, modelFileDir, quantizatio
 				layers = append(layers, baseLayer.Layer)
 			}
 		case "license", "template", "system":
-			if c.Name == "template" {
-				if _, err := template.Parse(c.Args); err != nil {
-					return fmt.Errorf("%w: %s", errBadTemplate, err)
-				}
-			}
-
 			if c.Name != "license" {
 				// replace
 				layers = slices.DeleteFunc(layers, func(layer *Layer) bool {

server/routes.go

@@ -56,7 +56,6 @@ func init() {
 }
 
 var errRequired = errors.New("is required")
-var errBadTemplate = errors.New("template error")
 
 func modelOptions(model *Model, requestOpts map[string]interface{}) (api.Options, error) {
 	opts := api.DefaultOptions()
@@ -614,9 +613,7 @@ func (s *Server) CreateModelHandler(c *gin.Context) {
 		defer cancel()
 
 		quantization := cmp.Or(r.Quantize, r.Quantization)
-		if err := CreateModel(ctx, name, filepath.Dir(r.Path), strings.ToUpper(quantization), f, fn); errors.Is(err, errBadTemplate) {
+		if err := CreateModel(ctx, name, filepath.Dir(r.Path), strings.ToUpper(quantization), f, fn); err != nil {
-			ch <- gin.H{"error": err.Error(), "status": http.StatusBadRequest}
-		} else if err != nil {
 			ch <- gin.H{"error": err.Error()}
 		}
 	}()
@@ -1204,15 +1201,11 @@ func waitForStream(c *gin.Context, ch chan interface{}) {
 				return
 			}
 		case gin.H:
-			status, ok := r["status"].(int)
-			if !ok {
-				status = http.StatusInternalServerError
-			}
 			if errorMsg, ok := r["error"].(string); ok {
-				c.JSON(status, gin.H{"error": errorMsg})
+				c.JSON(http.StatusInternalServerError, gin.H{"error": errorMsg})
 				return
 			} else {
-				c.JSON(status, gin.H{"error": "unexpected error format in progress response"})
+				c.JSON(http.StatusInternalServerError, gin.H{"error": "unexpected error format in progress response"})
 				return
 			}
 		default:

server/routes_create_test.go

@@ -491,42 +491,6 @@ func TestCreateTemplateSystem(t *testing.T) {
 	if string(system) != "Say bye!" {
 		t.Errorf("expected \"Say bye!\", actual %s", system)
 	}
-
-	t.Run("incomplete template", func(t *testing.T) {
-		w := createRequest(t, s.CreateModelHandler, api.CreateRequest{
-			Name:      "test",
-			Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{ .Prompt", createBinFile(t, nil, nil)),
-			Stream:    &stream,
-		})
-	
-		if w.Code != http.StatusBadRequest {
-			t.Fatalf("expected status code 400, actual %d", w.Code)
-		}
-	})
-
-	t.Run("template with unclosed if", func(t *testing.T) {
-		w := createRequest(t, s.CreateModelHandler, api.CreateRequest{
-			Name:      "test",
-			Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{ if .Prompt }}", createBinFile(t, nil, nil)),
-			Stream:    &stream,
-		})
-	
-		if w.Code != http.StatusBadRequest {
-			t.Fatalf("expected status code 400, actual %d", w.Code)
-		}
-	})
-
-	t.Run("template with undefined function", func(t *testing.T) {
-		w := createRequest(t, s.CreateModelHandler, api.CreateRequest{
-			Name:      "test",
-			Modelfile: fmt.Sprintf("FROM %s\nTEMPLATE {{  Prompt }}", createBinFile(t, nil, nil)),
-			Stream:    &stream,
-		})
-	
-		if w.Code != http.StatusBadRequest {
-			t.Fatalf("expected status code 400, actual %d", w.Code)
-		}
-	})
 }
 
 func TestCreateLicenses(t *testing.T) {