> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/pre-basic/settings/data-settings.md). # Data Settings Data Settings are Cherry Studio's **Data Hub**: all about **backup, restore, cross-device sync, third-party note integration** features are all here. > In one sentence:**If you're afraid of losing data, just set it up here once.** ## What backup plan should I use? | Your scenario | Recommended solution | | ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Personal single-computer use, worried about the hard drive failing | [WebDAV backup](/docs/en-us/pre-basic/settings/data-settings/webdav.md)(using Nutstore, 123 Pan, etc.) | | Want to sync chats/assistants across multiple computers | [WebDAV backup](/docs/en-us/pre-basic/settings/data-settings/webdav.md) — back up on computer A, restore on computer B | | Already have S3-compatible storage such as AWS / Alibaba Cloud OSS | [S3-compatible storage backup](/docs/en-us/pre-basic/settings/data-settings/s3-compatible.md) | | Want to automatically archive conversation content to note-taking software | [Notion](/docs/en-us/pre-basic/settings/data-settings/notion.md) / [Obsidian](/docs/en-us/pre-basic/settings/data-settings/obsidian.md) / [SiYuan Notes](/docs/en-us/pre-basic/settings/data-settings/siyuan.md) | | Only want to back up to another folder on the local machine / an external hard drive | **Local backup**(Choose a backup directory; supports automatic backups + backup file management) | ## What is backed up? **Default full backup**: * Chat history and topics * Assistants and preset settings * Knowledge base (including vector database content) * Attachments such as notes, drawings, files, etc. * Preferences and personalization settings * Provider configuration (API keys are also included) **Slim backup**(Optional): the backup screen has a **Slim backup** toggle that, when enabled, will **skip data files such as images and knowledge bases, and only back up chat records and settings**, small in size and fast, suitable for frequent quick backups. {% hint style="warning" %} Backup files will contain sensitive information such as Provider API keys.**Do not share backup files with others, and do not store them on untrusted shared cloud drives**. {% endhint %} ## How often should I back up? * **Manual backup**: click the "Backup" button anytime * **Automatic backup**: once enabled, according to the set **time interval** it runs automatically (optional intervals from a few minutes to 24 hours, such as 5 minutes / 30 minutes / 1 hour / 24 hours), rather than fixed "daily / weekly" ## Where is the data stored? If you want to change the hard drive location, see [Change storage location](/docs/en-us/pre-basic/settings/data-settings/storage.md). ## Import ChatGPT or Claude conversations Path: \[Settings] → \[Data] → \[Import external app data]. Choose \[Import ChatGPT data] or \[Import Claude data], then follow the prompts to select `conversations.json`. Claude export steps: 1. Log in to Claude, open \[Settings] → \[Privacy] → \[Export data]; 2. Wait for the email and download the export file; 3. Unzip the file and select the `conversations.json`. Claude data will import text, reasoning process, tool calls, and tool results; available branches in ChatGPT and Claude conversations will also be preserved. Images and attachments will not be imported. ## Clear cache by category Path: \[Settings] → \[Data] → \[Clear cache]. The pop-up will calculate the size of each category separately; when the statistics are not yet complete or can only be estimated, follow the page prompt. | Category | What will be cleared | Impact | | ------------------------------------ | -------------------------------------------------------------------------------------- | ------------------------------------------------------ | | \[App cache] | Cache and temporary files generated while the app is running | Does not delete chat history and settings | | \[Website and Mini Program data] | Cookies and site storage | Websites or Mini Apps may require you to log in again | | \[Residual files and knowledge base] | No-longer-used files, knowledge base leftovers, and temporary files for backup restore | Only cleans up residual items identified by the system | | \[v1 legacy data] | Old V1 conversations and settings kept on the local machine | Permanently deleted, cannot be recovered | {% hint style="danger" %} The \[v1 legacy data] option is shown only when retained V1 data is detected. Selecting it will delete the V1 data source required for \[re-migration]; before confirming that the V1 data has been fully migrated and keeping a complete backup and the V1 data directory,**do not select this item**. If you are not using \[re-migration] to fix a V1 migration failure, regular users should not use \[re-migration] either. See [V2 breaking update notice](/docs/en-us/cherry-studio/installation/v2-breaking-update-notice.md). {% endhint %} ## Reset app data \[Reset data] will clear chats, assistants, knowledge base, files, and settings and restart the app, and cannot be undone. It is not a routine troubleshooting step; create a full backup before proceeding. In addition, the Data Settings page also provides \[Export menu settings], used to control the export destination for conversations or notes. *** ### Get help and submit feedback If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) for the official channels provided. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.cherryai.com.cn/docs/en-us/pre-basic/settings/data-settings.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.