多模态

源码

main.go

package main

import (
    "context"
    "fmt"
    "log"
    "os"

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

func main() {
    if len(os.Args) <= 1 {
        log.Fatal("usage: <image name>")
    }

    imgData, err := os.ReadFile(os.Args[1])
    if err != nil {
        log.Fatal(err)
    }

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

    req := &api.GenerateRequest{
        Model:  "llava",
        Prompt: "describe this image",
        Images: []api.ImageData{imgData},
    }

    ctx := context.Background()
    respFunc := func(resp api.GenerateResponse) error {
        // 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-multimodal