mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

cmd: defer stating model info until necessary (#5248)

Browse source 
This commit changes the 'ollama run' command to defer fetching model
information until it really needs it. That is, when in interactive mode.

It also removes one such case where the model information is fetch in
duplicate, just before calling generateInteractive and then again, first
thing, in generateInteractive.

This positively impacts the performance of the command:

    ; time ./before run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./before run llama3 'hi'  0.02s user 0.01s system 2% cpu 1.168 total
    ; time ./before run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./before run llama3 'hi'  0.02s user 0.01s system 2% cpu 1.220 total
    ; time ./before run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./before run llama3 'hi'  0.02s user 0.01s system 2% cpu 1.217 total
    ; time ./after run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./after run llama3 'hi'  0.02s user 0.01s system 4% cpu 0.652 total
    ; time ./after run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./after run llama3 'hi'  0.01s user 0.01s system 5% cpu 0.498 total
    ; time ./after run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with or would you like to chat?

    ./after run llama3 'hi'  0.01s user 0.01s system 3% cpu 0.479 total
    ; time ./after run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./after run llama3 'hi'  0.02s user 0.01s system 5% cpu 0.507 total
    ; time ./after run llama3 'hi'
    Hi! It's nice to meet you. Is there something I can help you with, or would you like to chat?

    ./after run llama3 'hi'  0.02s user 0.01s system 5% cpu 0.507 total
This commit is contained in:
Blake Mizerany 2024-06-24 20:14:03 -07:00 • committed by GitHub
parent ccef9431c8
commit 2aa91a937b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 46 additions and 70 deletions
Download patch file Download diff file Expand all files Collapse all files

51
cmd/interactive.go
View file

@ -31,65 +31,40 @@ const (
)
func loadModel(cmd *cobra.Command, opts *runOptions) error {
client, err := api.ClientFromEnvironment()
if err != nil {
return err
}
p := progress.NewProgress(os.Stderr)
defer p.StopAndClear()
spinner := progress.NewSpinner("")
p.Add("", spinner)
showReq := api.ShowRequest{Name: opts.Model}
showResp, err := client.Show(cmd.Context(), &showReq)
client, err := api.ClientFromEnvironment()
if err != nil {
return err
}
opts.MultiModal = slices.Contains(showResp.Details.Families, "clip")
opts.ParentModel = showResp.Details.ParentModel
if len(showResp.Messages) > 0 {
opts.Messages = append(opts.Messages, showResp.Messages...)
}
chatReq := &api.ChatRequest{
Model: opts.Model,
Messages: []api.Message{},
Model: opts.Model,
KeepAlive: opts.KeepAlive,
}
if opts.KeepAlive != nil {
chatReq.KeepAlive = opts.KeepAlive
}
err = client.Chat(cmd.Context(), chatReq, func(resp api.ChatResponse) error {
return client.Chat(cmd.Context(), chatReq, func(resp api.ChatResponse) error {
p.StopAndClear()
if len(opts.Messages) > 0 {
for _, msg := range opts.Messages {
switch msg.Role {
case "user":
fmt.Printf(">>> %s\n", msg.Content)
case "assistant":
state := &displayResponseState{}
displayResponse(msg.Content, opts.WordWrap, state)
fmt.Println()
fmt.Println()
}
for _, msg := range opts.Messages {
switch msg.Role {
case "user":
fmt.Printf(">>> %s\n", msg.Content)
case "assistant":
state := &displayResponseState{}
displayResponse(msg.Content, opts.WordWrap, state)
fmt.Println()
fmt.Println()
}
}
return nil
})
if err != nil {
return err
}
return nil
}
func generateInteractive(cmd *cobra.Command, opts runOptions) error {
opts.Messages = make([]api.Message, 0)
err := loadModel(cmd, &opts)
if err != nil {
return err