Alibaba Cloud Model Studio:Deep research (Qwen-Deep-Research)

import os
import dashscope

# 以下为华北2（北京）地域的URL，各地域的URL不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1'

# Konfigurasikan API key
# Jika tidak disetel, ganti baris berikut dengan Kunci API Model Studio Anda (format: sk-xxx)
API_KEY = os.getenv('DASHSCOPE_API_KEY')

def call_deep_research_model(messages, step_name):
    print(f"\n=== {step_name} ===")

    try:
        responses = dashscope.Generation.call(
            api_key=API_KEY,
            model="qwen-deep-research",
            messages=messages,
            # Model qwen-deep-research saat ini hanya mendukung keluaran streaming
            stream=True
            # incremental_output=True Tambahkan parameter ini untuk keluaran inkremental
        )

        return process_responses(responses, step_name)

    except Exception as e:
        print(f"Terjadi kesalahan saat memanggil API: {e}")
        return ""

# Menampilkan konten fase
def display_phase_content(phase, content, status):
    if content:
        print(f"\n[{phase}] {status}: {content}")
    else:
        print(f"\n[{phase}] {status}")

# Memproses respons
def process_responses(responses, step_name):
    current_phase = None
    phase_content = ""
    research_goal = ""
    web_sites = []
    references = []
    keepalive_shown = False  # Bendera untuk memeriksa apakah prompt KeepAlive telah ditampilkan

    for response in responses:
        # Periksa kode status respons
        if hasattr(response, 'status_code') and response.status_code != 200:
            print(f"Kode respons HTTP: {response.status_code}")
            if hasattr(response, 'code'):
                print(f"Kode error: {response.code}")
            if hasattr(response, 'message'):
                print(f"Pesan error: {response.message}")
            print("Untuk informasi lebih lanjut, lihat: https://www.alibabacloud.com/help/en/model-studio/error-code")
            continue

        if hasattr(response, 'output') and response.output:
            message = response.output.get('message', {})
            phase = message.get('phase')
            content = message.get('content', '')
            status = message.get('status')
            extra = message.get('extra', {})

            # Deteksi perubahan fase
            if phase != current_phase:
                if current_phase and phase_content:
                    # Menampilkan deskripsi penyelesaian berbeda berdasarkan fase dan nama langkah
                    if step_name == "Step 1: Model query confirmation" and current_phase == "answer":
                        print(f"\n Fase konfirmasi kueri selesai")
                    else:
                        print(f"\n Fase {current_phase} selesai")
                current_phase = phase
                phase_content = ""
                keepalive_shown = False  # Reset bendera prompt KeepAlive

                # Menampilkan deskripsi berbeda berdasarkan fase dan nama langkah
                if step_name == "Step 1: Model query confirmation" and phase == "answer":
                    print(f"\n Memasuki fase konfirmasi kueri")
                else:
                    print(f"\n Memasuki fase {phase}")

            # Memproses informasi referensi dalam fase Answer
            if phase == "answer":
                if extra.get('deep_research', {}).get('references'):
                    new_references = extra['deep_research']['references']
                    if new_references and new_references != references:  # Hindari tampilan duplikat
                        references = new_references
                        print(f"\n   Referensi ({len(references)}):")
                        for i, ref in enumerate(references, 1):
                            print(f"     {i}. {ref.get('title', 'Tidak ada judul')}")
                            if ref.get('url'):
                                print(f"        URL: {ref['url']}")
                            if ref.get('description'):
                                print(f"        Deskripsi: {ref['description'][:100]}...")
                            print()

            # Memproses informasi khusus dalam fase WebResearch
            # Catatan: Model qwen-deep-research-2025-12-15 menggunakan status streamingThinking
            # alih-alih streamingQueries dan streamingWebResult
            if phase == "WebResearch":
                if extra.get('deep_research', {}).get('research'):
                    research_info = extra['deep_research']['research']

                    # Memproses status streamingThinking (model snapshot) atau streamingQueries (model mainline)
                    if status in ("streamingThinking", "streamingQueries"):
                        if 'researchGoal' in research_info:
                            goal = research_info['researchGoal']
                            if goal:
                                research_goal += goal
                                print(f"\n   Tujuan penelitian: {goal}", end='', flush=True)

                    # Memproses status streamingWebResult (model mainline)
                    # Model snapshot menggabungkan status ini menggunakan streamingThinking
                    elif status == "streamingWebResult":
                        if 'webSites' in research_info:
                            sites = research_info['webSites']
                            if sites and sites != web_sites:  # Hindari tampilan duplikat
                                web_sites = sites
                                print(f"\n   Ditemukan {len(sites)} situs web relevan:")
                                for i, site in enumerate(sites, 1):
                                    print(f"     {i}. {site.get('title', 'Tidak ada judul')}")
                                    print(f"        Deskripsi: {site.get('description', 'Tidak ada deskripsi')[:100]}...")
                                    print(f"        URL: {site.get('url', 'Tidak ada tautan')}")
                                    if site.get('favicon'):
                                        print(f"        Ikon: {site['favicon']}")
                                    print()

                    # Memproses status WebResultFinished
                    elif status == "WebResultFinished":
                        print(f"\n   Pencarian web selesai. Ditemukan {len(web_sites)} sumber referensi.")
                        if research_goal:
                            print(f"   Tujuan penelitian: {research_goal}")

            # Mengakumulasi dan menampilkan konten
            if content:
                phase_content += content
                # Menampilkan konten secara real-time
                print(content, end='', flush=True)

            # Menampilkan perubahan status fase
            if status and status != "typing":
                print(f"\n   Status: {status}")

                # Menampilkan deskripsi status
                if status == "streamingThinking":
                    print("   → Mendekomposisi tugas penelitian dan meringkas konten web (fase WebResearch)")
                elif status == "streamingQueries":
                    print("   → Menghasilkan tujuan penelitian dan kueri pencarian (fase WebResearch)")
                elif status == "streamingWebResult":
                    print("   → Melakukan pencarian, membaca halaman web, dan eksekusi kode (fase WebResearch)")
                elif status == "WebResultFinished":
                    print("   → Fase pencarian web selesai (fase WebResearch)")

            # Saat status finished, tampilkan konsumsi token
            if status == "finished":
                if hasattr(response, 'usage') and response.usage:
                    usage = response.usage
                    print(f"\n    Statistik konsumsi token:")
                    print(f"      Token input: {usage.get('input_tokens', 0)}")
                    print(f"      Token output: {usage.get('output_tokens', 0)}")
                    print(f"      ID Permintaan: {response.get('request_id', 'Tidak diketahui')}")

            if phase == "KeepAlive":
                # Hanya tampilkan prompt saat pertama kali memasuki fase KeepAlive
                if not keepalive_shown:
                    print("Langkah saat ini selesai. Mempersiapkan langkah berikutnya.")
                    keepalive_shown = True
                continue

    if current_phase and phase_content:
        if step_name == "Step 1: Model query confirmation" and current_phase == "answer":
            print(f"\n Fase konfirmasi kueri selesai")
        else:
            print(f"\n Fase {current_phase} selesai")

    return phase_content

def main():
    # Periksa API key
    if not API_KEY:
        print("Error: Variabel lingkungan DASHSCOPE_API_KEY belum disetel")
        print("Setel variabel lingkungan atau modifikasi variabel API_KEY langsung di kode")
        return

    print("Pengguna memulai percakapan: Teliti penerapan artificial intelligence dalam pendidikan")

    # Langkah 1: Konfirmasi kueri model
    # Model menganalisis pertanyaan pengguna dan mengajukan pertanyaan klarifikasi untuk menentukan arah penelitian
    messages = [{'role': 'user', 'content': 'Teliti penerapan artificial intelligence dalam pendidikan'}]
    step1_content = call_deep_research_model(messages, "Step 1: Model query confirmation")

    # Langkah 2: Deep research
    # Berdasarkan konfirmasi kueri dari Langkah 1, model melakukan proses penelitian lengkap
    messages = [
        {'role': 'user', 'content': 'Teliti penerapan artificial intelligence dalam pendidikan'},
        {'role': 'assistant', 'content': step1_content},  # Menyertakan konten konfirmasi kueri model
        {'role': 'user', 'content': 'Saya terutama fokus pada pembelajaran personalisasi dan penilaian cerdas'}
    ]

    call_deep_research_model(messages, "Step 2: Deep research")
    print("\n Penelitian selesai!")

if __name__ == "__main__":
    main()

echo "Step 1: Model query confirmation"
# 以下为华北2（北京）地域的URL，各地域的URL不同。
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'X-DashScope-SSE: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "input": {
        "messages": [
            {
                "content": "Teliti penerapan artificial intelligence dalam pendidikan",
                "role": "user"
            }
        ]
    },
    "model": "qwen-deep-research"
}'

echo -e "\n\n"
echo "Step 2: Deep research"
# 以下为华北2（北京）地域的URL，各地域的URL不同。
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'X-DashScope-SSE: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "input": {
        "messages": [
            {
                "content": "Teliti penerapan artificial intelligence dalam pendidikan",
                "role": "user"
            },
            {
                "content": "Beritahu saya skenario penerapan spesifik artificial intelligence dalam pendidikan yang ingin Anda fokuskan?",
                "role": "assistant"
            },
            {
                "content": "Saya terutama fokus pada pembelajaran personalisasi",
                "role": "user"
            }
        ]
    },
    "model": "qwen-deep-research"
}'

import os
import dashscope

# 以下为华北2（北京）地域的URL，各地域的URL不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1'

API_KEY = os.getenv('DASHSCOPE_API_KEY')

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://example.aliyuncs.com/example.png"},
            {"text": "Analisis tren data dalam grafik ini dan lakukan penelitian mendalam mengenai temuan utamanya"}
        ]
    }
]

responses = dashscope.Generation.call(
    api_key=API_KEY,
    model="qwen-deep-research",
    messages=messages,
    stream=True
)

for response in responses:
    if hasattr(response, 'output') and response.output:
        message = response.output.get('message', {})
        content = message.get('content', '')
        if content:
            print(content, end='', flush=True)

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'X-DashScope-SSE: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "input": {
        "messages": [
            {
                "content": [
                    {"image": "https://example.aliyuncs.com/example.png"},
                    {"text": "Analisis tren data dalam grafik ini dan lakukan penelitian mendalam mengenai temuan utamanya"}
                ],
                "role": "user"
            }
        ]
    },
    "model": "qwen-deep-research"
}'

import os
import dashscope

# 以下为华北2（北京）地域的URL，各地域的URL不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1'

API_KEY = os.getenv('DASHSCOPE_API_KEY')

messages = [
    {
        "role": "user",
        "content": "Gunakan basis pengetahuan untuk mencari pengumuman pembaruan produk yang baru diterbitkan dan susun menjadi laporan penelitian"
    }
]

responses = dashscope.Generation.call(
    api_key=API_KEY,
    model="qwen-deep-research-2025-12-15",
    messages=messages,
    stream=True,
    enable_feedback=False,
    research_tools=[{
        "type": "mcp",
        "server_label": "my-server",
        "server_url": "https://your-mcp-server.example.com/sse",
        "allowed_tools": ["search", "fetch"],
        "authentication": {
            "bearer": "your_jwt_token_here"
        }
    }]
)

for response in responses:
    if hasattr(response, 'output') and response.output:
        message = response.output.get('message', {})
        content = message.get('content', '')
        if content:
            print(content, end='', flush=True)

curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'X-DashScope-SSE: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "input": {
        "messages": [
            {
                "content": "Gunakan basis pengetahuan untuk mencari pengumuman pembaruan produk yang baru diterbitkan dan susun menjadi laporan penelitian",
                "role": "user"
            }
        ]
    },
    "model": "qwen-deep-research-2025-12-15",
    "parameters": {
        "enable_feedback": false,
        "research_tools": [{
            "type": "mcp",
            "server_label": "my-server",
            "server_url": "https://your-mcp-server.example.com/sse",
            "allowed_tools": ["search", "fetch"],
            "authentication": {
                "bearer": "your_jwt_token_here"
            }
        }]
    }
}'