Ein neuer Leitfaden mit Best Practices soll Ihnen helfen, für Ihre Kundenservicemitarbeiter effektiven Geschäfts- und Datenkontext bereitzustellen. Weitere Informationen finden Sie unter Agent-Verhalten mit selbst erstelltem Kontext steuern.
Mit dem Data Agent Service können Sie programmatisch persistente, kontextbezogene KI-Agents mit Looker, Looker Studio und BigQuery erstellen, konfigurieren und verwalten.
Mit dem Data Chat Service können Sie mit Ihrem Agent in verschiedenen Chat-Modi interagieren. Zu diesen Modi gehören ein zustandsorientierter Modus, in dem Google den Unterhaltungsverlauf verwaltet, eine zustandsorientierte Option, in der Ihre Anwendung die Unterhaltung verwaltet, und ein zustandsloser Modus, in dem Ihre Anwendung bei jeder Anfrage den vollständigen Kontext bereitstellt.
Die API für konversationelle Analyse (geminidataanalytics.googleapis.com) ersetzt die eingestellte Data QnA API (dataqna.googleapis.com). Dies umfasst auch die Migration des DataQuestionService zum neuen DataChatService. Eine ausführliche Anleitung zum Aktualisieren Ihrer Anfragen finden Sie in der Migrationsanleitung.
[[["Leicht verständlich","easyToUnderstand","thumb-up"],["Mein Problem wurde gelöst","solvedMyProblem","thumb-up"],["Sonstiges","otherUp","thumb-up"]],[["Schwer verständlich","hardToUnderstand","thumb-down"],["Informationen oder Beispielcode falsch","incorrectInformationOrSampleCode","thumb-down"],["Benötigte Informationen/Beispiele nicht gefunden","missingTheInformationSamplesINeed","thumb-down"],["Problem mit der Übersetzung","translationIssue","thumb-down"],["Sonstiges","otherDown","thumb-down"]],["Zuletzt aktualisiert: 2025-08-22 (UTC)."],[],[],null,["# Conversational Analytics API release notes\n\n| **Preview**\n|\n|\n| This product or 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 products and 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\nThese release notes are for updates to the [Conversational Analytics API](/gemini/docs/conversational-analytics-api/overview).\n\nAugust 25, 2025\n---------------\n\n**The Conversational Analytics API is now available in Public Preview.**\n\n**Client library updates:** \nThe following client libraries are now available for multiple languages:\n\n- [PHP (v1beta)](/php/docs/reference/cloud-geminidataanalytics/latest)\n- [DotNet (v1beta)](/dotnet/docs/reference/Google.Cloud.GeminiDataAnalytics.V1Beta/latest)\n- [Python (v1beta)](/python/docs/reference/google-cloud-geminidataanalytics/latest)\n\n**Conversational Analytics API updates:** \nSupport for v1beta endpoints for [HTTP REST](/gemini/docs/conversational-analytics-api/reference/rest) are now available. \nSupport for [`GetLocation`](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations/get) and [`ListLocations`](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations/list) API methods has been added to the REST APIs and SDK. \nYou can now share data agents using the [`GetIamPolicy` and `SetIamPolicy` API methods](/gemini/docs/conversational-analytics-api/overview#key_api_operations). \nYou can now build data agents from Looker data sources that are based on Looker (Google Cloud core) instances that use private IP networks. (The Conversational Analytics API doesn't support data sources based on Looker (Google Cloud core) instances that are inside Virtual Private Cloud perimeters.) \n[Structured context for BigQuery data sources](/gemini/docs/conversational-analytics-api/data-agent-authored-context-bq) is now available. This includes the ability to add example question/query pairs, table descriptions, synonyms, and tags at the table and field levels using the API. \n[Location and operation APIs](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations.operations) are now supported. `DataAgentCreator` and `DataAgentEditor` Identity and Access Management roles will now have permissions for operation APIs. \nAn enhancement has been made for the automatic storage of `Last Published Context` in the server layer whenever a data agent's published context is updated. \nThe display names for Identity and Access Management roles have been updated to \"Gemini Data Analytics Stateless Chat User\" and \"Gemini Data Analytics Data Agent Creator\". For more information about the Identity and Access Management roles that are used with the Conversational Analytics API, see the [Grant Conversational Analytics API Identity and Access Management roles and permissions](/gemini/docs/conversational-analytics-api/access-control) documentation page. \nColaboratory version 1.1 is now available. \nUpdates to error handling have been made to handle conversation-related 500 internal errors for stateful chat. \nBetter exception handling messages have been implemented for 400 client errors.\n\n**Documentation updates:** \nYou can now use the new [Streamlit Quickstart Application on GitHub](https://github.com/looker-open-source/ca-api-quickstarts) to set up a demo of the Conversational Analytics API in minutes. \nThe [Conversational Analytics API Golden Demo](https://github.com/looker-open-source/ca-demos-and-tools/blob/main/ca-api-golden-demo/README.md) is now available on GitHub. With the Conversational Analytics API Golden Demo, you can view examples to integrate the Conversational Analytics API into web applications as well as a full production demo in TypeScript. This project is intended for demonstration purposes only. It is not intended for use in a production environment. \nRequest payload code samples have been added for the [REST APIs](/gemini/docs/conversational-analytics-api/build-agent-http#manage-data-agents-and-conversations) and [SDK](/gemini/docs/conversational-analytics-api/build-agent-sdk#manage-data-agents-and-conversations). \n[Conversational Analytics API architecture, workflows, and roles](/gemini/docs/conversational-analytics-api/key-concepts): Learn more about key concepts for using the Conversational Analytics API, including how data agents work, typical data agent workflows, conversation modes, Identity and Access Management roles, and how to design systems that use multiple data agents. \n[Conversational Analytics API known limitations](/gemini/docs/conversational-analytics-api/known-limitations): Learn more about limitations on the number of data sources, style of visualizations, and size of datasets. \n[Troubleshoot Conversational Analytics API errors](/gemini/docs/conversational-analytics-api/troubleshoot-ca-errors): Learn more about potential issues or errors with the Conversational Analytics API, as well as proposed solutions. \n[Monitor and manage BigQuery costs for your Conversational Analytics API agents](/gemini/docs/conversational-analytics-api/manage-costs): Learn more about how to implement cost controls for your Conversational Analytics API agents. \n`SetIAMPolicy` and `GetIAMPolicy` methods are available on the [Conversational Analytics API overview](/gemini/docs/conversational-analytics-api/overview#key_api_operations) documentation page for use in sharing data agents. \nA new documentation page containing [answers to frequently asked questions about the Conversational Analytics API](/gemini/docs/conversational-analytics-api/frequently-asked-questions) is now available. \n[Guide agent behavior with authored context for BigQuery data sources](/gemini/docs/conversational-analytics-api/data-agent-authored-context-bq): Learn more about how to write system instructions for BigQuery data sources. \n[Guide agent behavior with authored context for Looker data sources](/gemini/docs/conversational-analytics-api/data-agent-authored-context-looker): Learn more about how to write system instructions for Looker data sources.\n\nJuly 15, 2025\n-------------\n\nYou can now invite users to collaborate on specific data agents by assigning predefined IAM roles. For details, see [Conversational Analytics API IAM roles and permissions](/gemini/docs/conversational-analytics-api/access-control). \nA new best practices guide helps you provide effective business and data context to your agents. For more information, see [Guide agent behavior with authored context](/gemini/docs/conversational-analytics-api/data-agent-system-instructions).\n\n**SDK updates:** \nYou can now install the Python SDK from the [Python Package Index (PyPI)](https://pypi.org/project/google-cloud-geminidataanalytics/).\n\nJune 25, 2025\n-------------\n\n**API updates:** \nNew predefined IAM roles control access for creating, managing, and interacting with data agents:\n\n- `geminidataanalytics.dataAgentCreator`\n- `geminidataanalytics.dataAgentOwner`\n- `geminidataanalytics.dataAgentEditor`\n- `geminidataanalytics.dataAgentUser`\n- `geminidataanalytics.dataAgentViewer`\n- `geminidataanalytics.dataAgentStatelessUser`\n\nFor a full list of roles and their permissions, see the [Grant Conversational Analytics API IAM roles and permissions](/gemini/docs/conversational-analytics-api/access-control).\n\nJune 5, 2025\n------------\n\nThe initial Private Preview of the Conversational Analytics API introduced capabilities for creating and interacting with data agents. \nThe following interactive Colaboratory notebooks are available for getting started with both REST and the Python SDK:\n\n- [HTTP Colab notebook](https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/agents/gemini_data_analytics/intro_gemini_data_analytics_http.ipynb)\n- [Python SDK Colab notebook](https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/agents/gemini_data_analytics/intro_gemini_data_analytics_sdk.ipynb)\n\n**API updates:** \nThe [**Data Agent Service**](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations.dataAgents) lets you programmatically create, configure, and manage persistent, context-aware AI agents with Looker, Looker Studio, and BigQuery. \nThe [**Data Chat Service**](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations/chat) lets you engage in conversations with your agent by using multiple chat modes. These modes include a stateful mode where Google manages the conversation history, a stateful option where your application manages the conversation, and a stateless mode where your application provides the full context with each request. \nThe API supports [advanced analysis using Python](/gemini/docs/conversational-analytics-api/reference/rest/v1beta/projects.locations.dataAgents#python) and automatically retries failed queries. \nThe Conversational Analytics API (`geminidataanalytics.googleapis.com`) replaces the deprecated Data QnA API (`dataqna.googleapis.com`). This includes the migration from `DataQuestionService` to the new `DataChatService`. For detailed instructions on how to update your requests, see the [migration guide](/gemini/docs/conversational-analytics-api/migration-guide)."]]
