Beberapa produk dan fitur sedang dalam proses penggantian nama. Fitur playbook dan alur generatif juga dimigrasikan ke satu konsol gabungan. Lihat detailnya.
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Agen bawaan berbasis playbook Perjalanan
memungkinkan pengguna menelusuri lokasi menarik (POI), mendapatkan rekomendasi perjalanan, dan
memesan hotel. Agen menggunakan data profil pengguna untuk menyesuaikan rekomendasi bagi
pengguna, jika disediakan.
Contoh dialog
Contoh dialog berikut menunjukkan skenario umum yang ditangani oleh
agen bawaan ini.
Penelusuran POI dan pemesanan hotel
Pengguna bertanya tentang restoran di Washington DC. Agen merekomendasikan beberapa
lokasi menarik, dan pengguna meminta untuk memesan hotel. Agen mengumpulkan
informasi yang diperlukan, termasuk hotel, tanggal check-in, tanggal check-out, jumlah
wisatawan, dan jumlah kamar. Pengguna mengonfirmasi informasi dan
agen memesan masa inap, memberikan nomor konfirmasi kepada pengguna.
Input pengguna
Respons agen
apakah ada restoran seafood yang bagus di Washington DC?
Berikut beberapa restoran seafood di Washington DC: - The Oceanaire Seafood Room - Tony and Joe's Seafood Place - Joe's Seafood, Prime Steak & Stone Crab
Ada lagi yang bisa saya bantu?
Saya ingin memesan penginapan selama empat malam di DC
Berikut beberapa hotel di Washington DC yang saya temukan. Manakah yang ingin Anda pesan?: - Cambria Hotel Washington D.C. Navy Yard Riverfront - Beacon Hotel & Corporate Quarters - Holiday Inn Washington Capitol - Natl Mall, an IHG Hotel
Beacon Hotel terdengar bagus
Baik, izinkan kami mengonfirmasi beberapa detail. Anda akan menginap 4 malam, dari 11-06 hingga 11-10, benar?
sebenarnya saya akan check in pada tanggal 8
Oke, jadi Anda akan check in pada 08-11 dan check out pada 12-11?
ya, itu sempurna
Baik, izinkan kami mengonfirmasi detail pemesanan Anda Nama Hotel = Beacon Hotel & Corporate Quarters Tanggal Check In = 8 November Tanggal Check Out = 12 November # Kamar = 1 # Wisatawan = 1
Apakah sudah benar?
anak saya akan ikut
Oke, jadi 2 wisatawan. Mari kita perbarui detail pemesanan Anda Nama Hotel = Beacon Hotel & Corporate Quarters Tanggal Check In = 8 November Tanggal Check Out = 12 November # Kamar = 1 # Wisatawan = 2
Apakah sudah benar?
ya, tolong pesankan untuk saya
Bagus! Kami telah mengonfirmasi pemesanan Anda dan memiliki Konfirmasi # 2UDVXUUV untuk catatan Anda.
Ada lagi yang bisa saya bantu?
tidak, cukup itu saja, terima kasih
Terima kasih telah bepergian dengan Google. Semoga hari Anda menyenangkan.
Inspirasi perjalanan
Pengguna mengatakan bahwa ia ingin mengajak keluarganya dalam perjalanan ski. Agen
menyarankan beberapa tujuan ski di Amerika Serikat, dan pengguna bertanya apakah
agen memiliki rekomendasi di luar negara tersebut. Agen menampilkan daftar
tujuan di luar Amerika Serikat. Terakhir, pengguna meminta agen untuk
memesan penginapan di salah satu tujuan dan agen menampilkan daftar hotel
di sekitar.
Input pengguna
Respons agen
Saya ingin mengajak keluarga saya untuk melakukan perjalanan ski, ada saran?
Saya suka bermain ski. Berikut beberapa tujuan ski populer di Amerika Serikat: - Arapahoe Basin - Aspen Highlands - Beaver Creek - Breckenridge - Sun Peaks Resort
Saya ingin ke luar negeri, apakah Anda punya saran?
Tentu saja! Berikut beberapa tujuan ski populer di luar Amerika Serikat: - St. Moritz - Niseko United - Hakuba Valley - Nozawa Onsen - Whistler Blackcomb - Big White Ski Resort - Sun Peaks Resort
Baik, terima kasih. Bisakah Anda memesan penginapan untuk saya di Whistler Blackcomb?
Berikut adalah beberapa hotel di Whistler Blackcomb. Manakah yang ingin Anda pesan?: - Blackcomb Lodge - Blackcomb Springs Suites - True Ski-in, Ski-out Resort - Pinnacle Hotel Whistler - Fairmont Château Whistler
Konfigurasikan alat yang disediakan dengan layanan eksternal Anda, lihat Penyiapan alat.
Penyiapan alat
Agen ini mencakup alat yang
digunakan untuk berintegrasi dengan layanan eksternal. Anda dapat menggunakan penginstal alat bawaan untuk men-deploy kode dan data contoh untuk agen bawaan.
Untuk men-deploy dan mengonfigurasi contoh kode dan data untuk agen bawaan Perjalanan, luaskan untuk mengetahui petunjuknya.
Buka direktori lokal tempat Anda mendownload installer.zip.
Ekstrak installer.zip dan buka folder installer.
Tinjau README.md untuk mengetahui ringkasan mendetail tentang penginstal dan persyaratannya.
Jalankan pip install -r requirements.txt untuk menginstal persyaratan.
Jalankan gcloud auth application-default login untuk melakukan autentikasi menggunakan gcloud auth.
Jalankan penginstal menggunakan
python installer.py --project-id=YOUR_GCP_PROJECT_ID --prebuilt-id=travel
Setelah men-deploy semua layanan yang diperlukan, konfigurasikan setiap alat di agen bawaan dengan URL yang diberikan yang dicatat ke dalam log oleh penginstal:
Berikan peran Cloud Datastore User ke akun layanan Compute Engine (your-project-number-) sehingga fungsi Cloud Run yang baru di-deploy dapat mengakses Firestore.
Penelusuran Places
Alat places_search digunakan untuk mendapatkan informasi tentang lokasi menarik,
termasuk lokasi menarik di dekat lokasi.
Penelusuran hotel
Alat hotel_search digunakan untuk mendapatkan informasi tentang hotel, termasuk
hotel di dekat lokasi.
Pemesanan hotel
Alat hotel_booking digunakan untuk membuat dan mendapatkan informasi tentang pemesanan
hotel.
Mendapatkan profil pengguna
Alat get_user_profile digunakan untuk mengambil profil pengguna yang dapat digunakan
untuk menyesuaikan rekomendasi bagi pengguna.
Selesai
Agen dan integrasinya kini telah disiapkan dan siap diuji.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-04 UTC."],[[["\u003cp\u003eThis Travel prebuilt agent allows users to search for points of interest, get travel recommendations, and book hotels.\u003c/p\u003e\n"],["\u003cp\u003eThe agent uses a user's profile data to customize recommendations when available.\u003c/p\u003e\n"],["\u003cp\u003eThis feature is currently in a Pre-GA stage, meaning it is available "as is" with potentially limited support.\u003c/p\u003e\n"],["\u003cp\u003eSetting up the agent involves importing it, and then using a prebuilt tool installer to deploy sample code and data to integrate with external services.\u003c/p\u003e\n"],["\u003cp\u003eThe agent has multiple tools, such as \u003ccode\u003eplaces_search\u003c/code\u003e, \u003ccode\u003ehotel_search\u003c/code\u003e, \u003ccode\u003ehotel_booking\u003c/code\u003e, and \u003ccode\u003eget_user_profile\u003c/code\u003e to search POIs, hotels, book stays, and get user profile information for recommendations.\u003c/p\u003e\n"]]],[],null,["# Travel prebuilt agent\n\nThe Travel\n[playbook-based prebuilt agent](/dialogflow/cx/docs/concept/playbook/prebuilt)\nallows users to search for points of interest (POI), get travel recommendations, and\nbook hotels. The agent uses user profile data to customize recommendations for\nthe user, if provided.\n\nSample dialogs\n--------------\n\nThe following sample dialogs demonstrate common scenarios handled by this\nprebuilt agent.\n\n### POI search and hotel booking\n\nThe user asks about restaurants in Washington DC. The agent recommends a few\npoints of interest, and the user asks to book a hotel. The agent collects\nrequired information, including the hotel, check-in date, check-out date, number\nof travelers, and number of rooms. The user confirms the information and the\nagent books the stay, providing the user with a confirmation number.\n\n### Travel inspiration\n\nThe user says that they would like to take their family on a ski trip. The agent\nsuggests some ski destinations in the United States, and the user asks if the\nagent has any recommendations out of the country. The agent presents a list of\ndestinations outside of the United States. Finally, the user asks the agent to\nbook a stay at one of the destinations and the agent presents a list of hotels\nnearby.\n\nBasic setup\n-----------\n\nTo set up this prebuilt agent:\n\n1. [Import the prebuilt agent](/dialogflow/cx/docs/concept/playbook/prebuilt#import).\n2. Configure the provided [tools](/dialogflow/cx/docs/concept/playbook/tool) with your external services, see [Tool setup](#tool-setup).\n\nTool setup\n----------\n\nThis agent includes [tools](/dialogflow/cx/docs/concept/playbook/tool) that are\nused to integrate with external services. You can use the prebuilt tool installer\nto deploy sample code and data for your prebuilt agent. \n\n#### To deploy and configure sample code and data for the Travel\nprebuilt agent, expand for instructions.\n\n1. Download the [prebuilt tool installer](https://storage.googleapis.com/gassets-api-ai/prebuilt_agents/generative-prebuilt-agents/installer.zip) to a local directory.\n2. Navigate to the local directory where you downloaded **installer.zip**.\n3. Unzip **installer.zip** and open the `installer` folder.\n4. Review README.md for a detailed overview of the installer and its requirements.\n5. Run `pip install -r requirements.txt` to install requirements.\n6. Run `gcloud auth application-default login` to authenticate using [gcloud auth](https://cloud.google.com/sdk/gcloud/reference/auth).\n7. Run the installer using `python installer.py --project-id=`\u003cvar translate=\"no\"\u003eYOUR_GCP_PROJECT_ID\u003c/var\u003e` --prebuilt-id=travel`\n8. After deploying all required services, configure each tool in the prebuilt agent with the provided URL(s) logged by the installer:\n\n ### AI Applications console\n\n 1. If you have not yet imported the prebuilt agent, [import the agent into your project](/dialogflow/cx/docs/concept/playbook/prebuilt#import).\n 2. Go to the **AI Applications console** .\n\n\n [AI Applications console](https://console.cloud.google.com/gen-app-builder//start)\n 3. Select your project from the console drop-down.\n 4. Select your app.\n 5. Click on the icon for **Tools**.\n 6. For each tool in the agent, edit the schema to replace the URL in the `servers:` field with the endpoint logged by the installer.\n 7. Click **Save**.\n\n ### Dialogflow CX\n\n 1. If you have not yet imported the prebuilt agent, [import the agent into your project](/dialogflow/cx/docs/concept/playbook/prebuilt#import).\n 2. Open the [Dialogflow CX console](https://dialogflow.cloud.google.com/cx/projects).\n 3. Choose your Google Cloud project.\n 4. Select your agent.\n 5. Click on the icon for **Generative resources**.\n 6. Click **Tools**.\n 7. For each tool in the agent, edit the schema to replace the URL in the `servers` field with the endpoint logged by the installer.\n 8. Click **Save**.\n9. Grant the Compute Engine service account (`your-project-number-developer.gserviceaccount.com`) the **Cloud Datastore User** role, so the newly deployed Cloud Run functions can access Firestore.\n\n### Places search\n\nThe `places_search` tool is used to get information about points of interest,\nincluding points of interest near a location.\n\n### Hotel search\n\nThe `hotel_search` tool is used to get information about hotels, including\nhotels near a location.\n\n### Hotel booking\n\nThe `hotel_booking` tool is used to create and get information about hotel\nbookings.\n\n### Get user profile\n\nThe `get_user_profile` tool is used to retrieve user profiles that can be used\nto customize recommendations for the user.\n\n### Complete\n\nYour agent and its integrations should now be set up and ready to test."]]