perf: add HTTP connection pooling across providers and disable proxy buffering on SSE streams
This commit is contained in:
@@ -403,6 +403,7 @@ func (s *Server) handleResponses(c *gin.Context) {
|
||||
c.Header("Content-Type", "text/event-stream")
|
||||
c.Header("Cache-Control", "no-cache")
|
||||
c.Header("Connection", "keep-alive")
|
||||
c.Header("X-Accel-Buffering", "no")
|
||||
|
||||
var lastUsage *models.ResponsesUsage
|
||||
c.Stream(func(w io.Writer) bool {
|
||||
@@ -765,6 +766,7 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
|
||||
c.Header("Content-Type", "text/event-stream")
|
||||
c.Header("Cache-Control", "no-cache")
|
||||
c.Header("Connection", "keep-alive")
|
||||
c.Header("X-Accel-Buffering", "no")
|
||||
|
||||
var lastUsage *models.Usage
|
||||
c.Stream(func(w io.Writer) bool {
|
||||
|
||||
Reference in New Issue
Block a user