perf: use max_tokens to reduce token consuming

This commit is contained in:
JustSong 2023-05-16 16:22:25 +08:00
parent c9ac5e391f
commit 58fe923c85
2 changed files with 6 additions and 4 deletions

View File

@ -210,11 +210,12 @@ func testChannel(channel *model.Channel, request *ChatRequest) error {
func buildTestRequest(c *gin.Context) *ChatRequest { func buildTestRequest(c *gin.Context) *ChatRequest {
model_ := c.Query("model") model_ := c.Query("model")
testRequest := &ChatRequest{ testRequest := &ChatRequest{
Model: model_, Model: model_,
MaxTokens: 1,
} }
testMessage := Message{ testMessage := Message{
Role: "user", Role: "user",
Content: "echo hi", Content: "hi",
} }
testRequest.Messages = append(testRequest.Messages, testMessage) testRequest.Messages = append(testRequest.Messages, testMessage)
return testRequest return testRequest

View File

@ -21,8 +21,9 @@ type Message struct {
} }
type ChatRequest struct { type ChatRequest struct {
Model string `json:"model"` Model string `json:"model"`
Messages []Message `json:"messages"` Messages []Message `json:"messages"`
MaxTokens int `json:"max_tokens"`
} }
type TextRequest struct { type TextRequest struct {