Mulai 29 April 2025, model Gemini 1.5 Pro dan Gemini 1.5 Flash tidak tersedia di project yang belum pernah menggunakan model ini, termasuk project baru. Untuk mengetahui detailnya, lihat Versi dan siklus proses model.
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Sesi Vertex AI Agent Engine mempertahankan histori interaksi antara pengguna dan agen. Sesi menyediakan sumber pasti untuk memori jangka panjang dan konteks percakapan.
Anda memiliki beberapa opsi untuk menggunakan Sesi Vertex AI Agent Engine:
Agent Development Kit: Setelah Anda men-deploy agen Agent Development Kit (ADK) ke Vertex AI Agent Engine, pengelolaan sesi akan ditangani secara otomatis.
Panggilan API: Anda dapat melakukan panggilan API langsung ke Sesi Vertex AI Agent Engine jika tidak ingin mengelola sesi menggunakan agen ADK.
Konsep inti
Sesi: Sesi merepresentasikan urutan kronologis pesan dan tindakan (peristiwa) untuk satu interaksi berkelanjutan antara pengguna dan sistem agen Anda.
Peristiwa: Peristiwa menyimpan konten percakapan, serta tindakan yang dilakukan oleh agen seperti panggilan fungsi.
Status: Status menyimpan data sementara yang hanya relevan selama percakapan saat ini.
Memori: Memori adalah informasi yang dipersonalisasi yang dapat diakses di beberapa sesi untuk pengguna tertentu. Agen dapat menggunakan memori untuk mempersonalisasi respons kepada pengguna dan memastikan kesinambungan lintas sesi.
Fungsi inti
Fungsi inti Sesi Vertex AI Agent Engine mencakup hal berikut:
Memulai percakapan baru: Buat sesi baru saat pengguna memulai interaksi dengan agen.
Melanjutkan percakapan yang ada: Mengambil sesi tertentu sehingga agen dapat melanjutkan percakapan yang telah dijeda.
Menyimpan progres: Tambahkan interaksi (peristiwa) baru ke histori sesi untuk memperbarui sesi.
Mencantumkan percakapan: Temukan rangkaian sesi aktif untuk pengguna dan aplikasi tertentu.
Membersihkan: Hapus objek sesi dan data terkaitnya saat percakapan selesai atau tidak lagi diperlukan.
[[["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 2025-08-25 UTC."],[],[],null,["| **Preview**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nVertex AI Agent Engine Sessions maintains the history of interactions between a user and agents. Sessions provide definitive sources for long-term memory and conversation context.\n\nYou have several options to use Vertex AI Agent Engine Sessions:\n\n- [Agent Development Kit](/vertex-ai/generative-ai/docs/agent-engine/sessions/manage-sessions-adk): Once you deploy your Agent Development Kit (ADK) agent to Vertex AI Agent Engine, session management is handled automatically.\n\n- [API calls](/vertex-ai/generative-ai/docs/agent-engine/sessions/manage-sessions-api): You can make direct API calls to Vertex AI Agent Engine Sessions if you don't want to manage sessions using an ADK agent.\n\nCore concepts\n\n- **Session**: A session represents the chronological sequence of messages and actions (events) for a single, ongoing interaction between a user and your agent system.\n\n- **Event**: An event stores the content of the conversation, as well as the actions taken by the agents such as function calls.\n\n- **State**: A state holds temporary data relevant only during the current conversation.\n\n- **Memory**: Memory is personalized information that can be accessed across multiple sessions for a particular user. The agent can use memories to personalize responses to the user and ensure cross-session continuity.\n\nCore functionalities\n\nThe core functionalities of Vertex AI Agent Engine Sessions include the following:\n\n- **Starting new conversations**: Create new sessions when a user begins an interaction with an agent.\n\n- **Resuming existing conversations**: Retrieving a specific session so the agent can resume a conversation that has been paused.\n\n- **Saving progress**: Append new interactions (events) to a session's history to update the session.\n\n- **Listing conversations**: Find the active session threads for a particular user and application.\n\n- **Cleaning up**: Delete session objects and their associated data when conversations are finished or no longer needed.\n\nWhat's next\n\n- [Manage sessions using ADK](/vertex-ai/generative-ai/docs/agent-engine/sessions/manage-sessions-adk).\n- [Manage sessions using API calls](/vertex-ai/generative-ai/docs/agent-engine/sessions/manage-sessions-api)."]]
