Ollama용 Go 클라이언트: SDK 비교 및 Qwen3/GPT-OSS 예제

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
	"net/http"
	"time"
)

// ---- Chat API Types ----

type ChatMessage struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

type ChatRequest struct {
	Model    string        `json:"model"`
	Messages []ChatMessage `json:"messages"`
	// 일부 서버는 사고(thinking) 컨트롤을 불리언 플래그로 노출합니다.
	// 제외되더라도 /think 또는 /no_think 태그를 통해 Qwen3를 제어할 수 있습니다.
	Think   *bool          `json:"think,omitempty"`
	Stream  *bool          `json:"stream,omitempty"`
	Options map[string]any `json:"options,omitempty"`
}

type ChatResponse struct {
	Model     string `json:"model"`
	CreatedAt string `json:"created_at"`
	Message   struct {
		Role     string `json:"role"`
		Content  string `json:"content"`
		Thinking string `json:"thinking,omitempty"` // 사고(thinking)가 켜져 있을 때 존재
	} `json:"message"`
	Done bool `json:"done"`
}

// ---- Generate API Types ----

type GenerateRequest struct {
	Model   string         `json:"model"`
	Prompt  string         `json:"prompt"`
	Think   *bool          `json:"think,omitempty"`
	Stream  *bool          `json:"stream,omitempty"`
	Options map[string]any `json:"options,omitempty"`
}

type GenerateResponse struct {
	Model     string `json:"model"`
	CreatedAt string `json:"created_at"`
	Response  string `json:"response"`           // 비스트림용 최종 텍스트
	Thinking  string `json:"thinking,omitempty"` // 사고(thinking)가 켜져 있을 때 존재
	Done      bool   `json:"done"`
}

// ---- Helper Functions ----

func httpPostJSON(url string, payload any) ([]byte, error) {
	body, err := json.Marshal(payload)
	if err != nil {
		return nil, err
	}
	c := &http.Client{Timeout: 60 * time.Second}
	resp, err := c.Post(url, "application/json", bytes.NewReader(body))
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()
	return io.ReadAll(resp.Body)
}

// bptr은 불리언 값의 포인터를 반환합니다
func bptr(b bool) *bool { return &b }

func chatQwen3Thinking() error {
	endpoint := "http://localhost:11434/api/chat"

	req := ChatRequest{
		Model:   "qwen3:8b-thinking", // 가져온 :*-thinking 태그 중 어떤 것이든 가능
		Think:   bptr(true),
		Stream:  bptr(false),
		Messages: []ChatMessage{
			{Role: "system", Content: "You are a precise assistant."},
			{Role: "user",   Content: "Explain recursion with a short Go example."},
		},
	}

	raw, err := httpPostJSON(endpoint, req)
	if err != nil {
		return err
	}
	var out ChatResponse
	if err := json.Unmarshal(raw, &out); err != nil {
		return err
	}
	fmt.Println("🧠 thinking:\n", out.Message.Thinking)
	fmt.Println("\n💬 answer:\n", out.Message.Content)
	return nil
}

// 다음 턴에서 사고(thinking)를 OFF로 전환하려면:
// (a) Think=false를 설정하고, 그리고/또는
// (b) 가장 최근 시스템/사용자 메시지에 "/no_think"를 추가 (Qwen3 소프트 스위치).
// Qwen3는 멀티턴 챗에서 가장 최근의 /think 또는 /no_think 지시를 따릅니다.
func chatQwen3NoThinking() error {
	endpoint := "http://localhost:11434/api/chat"

	req := ChatRequest{
		Model:  "qwen3:8b-thinking",
		Think:  bptr(false),
		Stream: bptr(false),
		Messages: []ChatMessage{
			{Role: "system", Content: "You are brief. /no_think"},
			{Role: "user",   Content: "Explain recursion in one sentence."},
		},
	}

	raw, err := httpPostJSON(endpoint, req)
	if err != nil {
		return err
	}
	var out ChatResponse
	if err := json.Unmarshal(raw, &out); err != nil {
		return err
	}
// 사고(thinking)가 비어 있을 것으로 예상하지만, 방어적으로 처리합니다.
	if out.Message.Thinking != "" {
		fmt.Println("🧠 thinking (unexpected):\n", out.Message.Thinking)
	}
	fmt.Println("\n💬 answer:\n", out.Message.Content)
	return nil
}

func chatGptOss() error {
	endpoint := "http://localhost:11434/api/chat"

	req := ChatRequest{
		Model:  "gpt-oss:20b",
		Think:  bptr(true),   // 지원되는 경우 분리된 추론(reasoning)을 요청
		Stream: bptr(false),
		Messages: []ChatMessage{
			{Role: "user", Content: "What is dynamic programming? Explain the core idea."},
		},
	}

	raw, err := httpPostJSON(endpoint, req)
	if err != nil {
		return err
	}
	var out ChatResponse
	if err := json.Unmarshal(raw, &out); err != nil {
		return err
	}
// 알려진 특이점: 사고(thinking)를 비활성화해도 gpt-oss:20b에서 추론(reasoning)이 완전히 억제되지 않을 수 있습니다.
// 노출하지 않으려면 항상 UI에서 사고(thinking)를 필터링/숨기세요.
	fmt.Println("🧠 thinking:\n", out.Message.Thinking)
	fmt.Println("\n💬 answer:\n", out.Message.Content)
	return nil
}

func generateQwen3() error {
	endpoint := "http://localhost:11434/api/generate"
	req := GenerateRequest{
		Model:  "qwen3:4b-thinking",
		Prompt: "In 2–3 sentences, what are B-Trees used for in databases?",
		Think:  bptr(true),
	}
	raw, err := httpPostJSON(endpoint, req)
	if err != nil {
		return err
	}
	var out GenerateResponse
	if err := json.Unmarshal(raw, &out); err != nil {
		return err
	}
	if out.Thinking != "" {
		fmt.Println("🧠 thinking:\n", out.Thinking)
	}
	fmt.Println("\n💬 answer:\n", out.Response)
	return nil
}

func generateGptOss() error {
	endpoint := "http://localhost:11434/api/generate"
	req := GenerateRequest{
		Model:  "gpt-oss:20b",
		Prompt: "Briefly explain backpropagation in neural networks.",
		Think:  bptr(true),
	}
	raw, err := httpPostJSON(endpoint, req)
	if err != nil {
		return err
	}
	var out GenerateResponse
	if err := json.Unmarshal(raw, &out); err != nil {
		return err
	}
	if out.Thinking != "" {
		fmt.Println("🧠 thinking:\n", out.Thinking)
	}
	fmt.Println("\n💬 answer:\n", out.Response)
	return nil
}

go get github.com/ollama/ollama/api

package main

import (
	"context"
	"fmt"
	"log"

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

func chatWithQwen3Thinking(ctx context.Context, thinking bool) error {
	client, err := api.ClientFromEnvironment() // 설정된 경우 OLLAMA_HOST를 따름
	if err != nil {
		return err
	}

	req := &api.ChatRequest{
		Model: "qwen3:8b-thinking",
		// 많은 서버 빌드에서 사고(thinking)를 최상위 플래그로 노출합니다.
		// 추가로, 메시지 내의 /think 또는 /no_think를 통해 Qwen3를 제어할 수 있습니다.
		Think: api.Ptr(thinking),
		Messages: []api.Message{
			{Role: "system", Content: "You are a precise assistant."},
			{Role: "user",   Content: "Explain merge sort with a short Go snippet."},
		},
	}

	var resp api.ChatResponse
	if err := client.Chat(ctx, req, &resp); err != nil {
		return err
	}

	if resp.Message.Thinking != "" {
		fmt.Println("🧠 thinking:\n", resp.Message.Thinking)
	}
	fmt.Println("\n💬 answer:\n", resp.Message.Content)
	return nil
}

func main() {
	ctx := context.Background()
	if err := chatWithQwen3Thinking(ctx, true); err != nil {
		log.Fatal(err)
	}
// 예제: 비사고(non-thinking)
	if err := chatWithQwen3Thinking(ctx, false); err != nil {
		log.Fatal(err)
	}
}

func chatWithGptOss(ctx context.Context) error {
	client, err := api.ClientFromEnvironment()
	if err != nil {
		return err
	}
	req := &api.ChatRequest{
		Model: "gpt-oss:20b",
		Think: api.Ptr(true),
		Messages: []api.Message{
			{Role: "user", Content: "What is memoization and when is it useful?"},
		},
	}
	var resp api.ChatResponse
	if err := client.Chat(ctx, req, &resp); err != nil {
		return err
	}
// 추론(reasoning)을 숨기려는 경우, 플래그와 무관하게 여기서 처리하세요.
	if resp.Message.Thinking != "" {
		fmt.Println("🧠 thinking:\n", resp.Message.Thinking)
	}
	fmt.Println("\n💬 answer:\n", resp.Message.Content)
	return nil
}

func generateWithQwen3(ctx context.Context) error {
	client, err := api.ClientFromEnvironment()
	if err != nil {
		return err
	}
	req := &api.GenerateRequest{
		Model:  "qwen3:4b-thinking",
		Prompt: "Summarize the role of a B-Tree in indexing.",
		Think:  api.Ptr(true),
	}
	var resp api.GenerateResponse
	if err := client.Generate(ctx, req, &resp); err != nil {
		return err
	}
	if resp.Thinking != "" {
		fmt.Println("🧠 thinking:\n", resp.Thinking)
	}
	fmt.Println("\n💬 answer:\n", resp.Response)
	return nil
}

func generateWithGptOss(ctx context.Context) error {
	client, err := api.ClientFromEnvironment()
	if err != nil {
		return err
	}
	req := &api.GenerateRequest{
		Model:  "gpt-oss:20b",
		Prompt: "Explain gradient descent in simple terms.",
		Think:  api.Ptr(true),
	}
	var resp api.GenerateResponse
	if err := client.Generate(ctx, req, &resp); err != nil {
		return err
	}
	if resp.Thinking != "" {
		fmt.Println("🧠 thinking:\n", resp.Thinking)
	}
	fmt.Println("\n💬 answer:\n", resp.Response)
	return nil
}

func streamChatExample() error {
	endpoint := "http://localhost:11434/api/chat"
	req := ChatRequest{
		Model:  "qwen3:8b-thinking",
		Think:  bptr(true),
		Stream: bptr(true), // 스트리밍 활성화
		Messages: []ChatMessage{
			{Role: "user", Content: "Explain quicksort algorithm step by step."},
		},
	}

	body, _ := json.Marshal(req)
	resp, err := http.Post(endpoint, "application/json", bytes.NewReader(body))
	if err != nil {
		return err
	}
	defer resp.Body.Close()

	decoder := json.NewDecoder(resp.Body)
	for {
		var chunk ChatResponse
		if err := decoder.Decode(&chunk); err == io.EOF {
			break
		} else if err != nil {
			return err
		}
		
		// 도착한 사고(thinking)와 콘텐츠(content)를 처리
		if chunk.Message.Thinking != "" {
			fmt.Print(chunk.Message.Thinking)
		}
		fmt.Print(chunk.Message.Content)
		
		if chunk.Done {
			break
		}
	}
	return nil
}

func streamWithOfficialSDK(ctx context.Context) error {
	client, _ := api.ClientFromEnvironment()
	
	req := &api.ChatRequest{
		Model: "qwen3:8b-thinking",
		Think: api.Ptr(true),
		Messages: []api.Message{
			{Role: "user", Content: "Explain binary search trees."},
		},
	}
	
	err := client.Chat(ctx, req, func(resp api.ChatResponse) error {
		if resp.Message.Thinking != "" {
			fmt.Print(resp.Message.Thinking)
		}
		fmt.Print(resp.Message.Content)
		return nil
	})
	
	return err
}

func robustChatRequest(ctx context.Context, model string, messages []api.Message) (*api.ChatResponse, error) {
	// 합리적인 타임아웃 설정
	ctx, cancel := context.WithTimeout(ctx, 2*time.Minute)
	defer cancel()
	
	client, err := api.ClientFromEnvironment()
	if err != nil {
		return nil, fmt.Errorf("creating client: %w", err)
	}
	
	req := &api.ChatRequest{
		Model:    model,
		Messages: messages,
		Options: map[string]interface{}{
			"temperature": 0.7,
			"num_ctx":     4096, // 컨텍스트 윈도우 크기
		},
	}
	
	var resp api.ChatResponse
	if err := client.Chat(ctx, req, &resp); err != nil {
		return nil, fmt.Errorf("chat request failed: %w", err)
	}
	
	return &resp, nil
}

type OllamaService struct {
	client *api.Client
}

func NewOllamaService() (*OllamaService, error) {
	client, err := api.ClientFromEnvironment()
	if err != nil {
		return nil, err
	}
	return &OllamaService{client: client}, nil
}

func (s *OllamaService) Chat(ctx context.Context, req *api.ChatRequest) (*api.ChatResponse, error) {
	var resp api.ChatResponse
	if err := s.client.Chat(ctx, req, &resp); err != nil {
		return nil, err
	}
	return &resp, nil
}

export OLLAMA_HOST=http://localhost:11434
export OLLAMA_NUM_PARALLEL=2
export OLLAMA_MAX_LOADED_MODELS=2

func loggedChat(ctx context.Context, logger *log.Logger, req *api.ChatRequest) error {
	start := time.Now()
	client, _ := api.ClientFromEnvironment()
	
	var resp api.ChatResponse
	err := client.Chat(ctx, req, &resp)
	
	duration := time.Since(start)
	logger.Printf("model=%s duration=%v error=%v tokens=%d", 
		req.Model, duration, err, len(resp.Message.Content))
	
	return err
}