fix(completionEndpoint): don't remove existing functionality

api/openai.go

@@ -190,6 +190,11 @@ func completionEndpoint(cm *ConfigMerger, o *Option) func(c *fiber.Ctx) error {
 			templateFile = config.TemplateConfig.Completion
 		}
 
+		if input.Stream {
+			if (len(config.PromptStrings) > 1) {
+				return errors.New("cannot handle more than 1 `PromptStrings` when `Stream`ing")
+			}
+
 			predInput := config.PromptStrings[0]
 
 			// A model can have a "file.bin.tmpl" file associated with a prompt template prefix
@@ -201,11 +206,6 @@ func completionEndpoint(cm *ConfigMerger, o *Option) func(c *fiber.Ctx) error {
 				log.Debug().Msgf("Template found, input modified to: %s", predInput)
 			}
 
-		if input.Stream {
-			if (len(config.PromptStrings) > 1) {
-				return errors.New("cannot handle more than 1 `PromptStrings` when `Stream`ing")
-			}
-
 			responses := make(chan OpenAIResponse)
 
 			go process(predInput, input, config, o.loader, responses)
@@ -235,13 +235,27 @@ func completionEndpoint(cm *ConfigMerger, o *Option) func(c *fiber.Ctx) error {
 			return nil
 		}
 
-		result, err := ComputeChoices(predInput, input, config, o.loader, func(s string, c *[]Choice) {
+		var result []Choice
+		for _, i := range config.PromptStrings {
+			// A model can have a "file.bin.tmpl" file associated with a prompt template prefix
+			templatedInput, err := o.loader.TemplatePrefix(templateFile, struct {
+				Input string
+			}{Input: i})
+			if err == nil {
+				i = templatedInput
+				log.Debug().Msgf("Template found, input modified to: %s", i)
+			}
+
+			r, err := ComputeChoices(i, input, config, o.loader, func(s string, c *[]Choice) {
 				*c = append(*c, Choice{Text: s})
 			}, nil)
 			if err != nil {
 				return err
 			}
 
+			result = append(result, r...)
+		}
+
 		resp := &OpenAIResponse{
 			Model:   input.Model, // we have to return what the user sent here, due to OpenAI spec.
 			Choices: result,