流模式模型生成

源码

main.go

package main

import (
    "context"
    "fmt"
    "log"

    "github.com/ollama/ollama/api"
)

func main() {
    client, err := api.ClientFromEnvironment()
    if err != nil {
        log.Fatal(err)
    }

    // By default, GenerateRequest is streaming.
    req := &api.GenerateRequest{
        Model:  "gemma",
        Prompt: "how many planets are there?",
    }

    ctx := context.Background()
    respFunc := func(resp api.GenerateResponse) error {
        // Only print the response here; GenerateResponse has a number of other
        // interesting fields you want to examine.

        // In streaming mode, responses are partial so we call fmt.Print (and not
        // Println) in order to avoid spurious newlines being introduced. The
        // model will insert its own newlines if it wants.
        fmt.Print(resp.Response)
        return nil
    }

    err = client.Generate(ctx, req, respFunc)
    if err != nil {
        log.Fatal(err)
    }
    fmt.Println()
}

仓库地址

go-generate-streaming