perf: use max_tokens to reduce token consuming

This commit is contained in:
JustSong
2023-05-16 16:22:25 +08:00
parent 4a64fede39
commit b77eb0c65d
2 changed files with 6 additions and 4 deletions
+2 -1
View File
@@ -211,10 +211,11 @@ func buildTestRequest(c *gin.Context) *ChatRequest {
model_ := c.Query("model")
testRequest := &ChatRequest{
Model: model_,
MaxTokens: 1,
}
testMessage := Message{
Role: "user",
Content: "echo hi",
Content: "hi",
}
testRequest.Messages = append(testRequest.Messages, testMessage)
return testRequest
+1
View File
@@ -23,6 +23,7 @@ type Message struct {
type ChatRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`
MaxTokens int `json:"max_tokens"`
}
type TextRequest struct {