> ## Documentation Index > Fetch the complete documentation index at: https://sitegpt.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Knowledge > Add, inspect, resync, delete, and maintain chatbot knowledge from links, websites, sitemaps, files, text, YouTube, and custom responses. Knowledge commands manage the content SiteGPT uses to answer questions. Run this first when exploring: ```bash theme={null} sitegpt knowledge --help ``` ## Knowledge resources | Resource | Purpose | | ---------------------------- | --------------------------------------------------------------------------------------------- | | `knowledge documents` | List, inspect, edit, resync, delete, and measure ingested documents. Alias: `knowledge docs`. | | `knowledge links` | Add one or more exact URLs. | | `knowledge website` | Crawl a website from a starting URL. | | `knowledge sitemap` | Add URLs from a sitemap. | | `knowledge youtube` | Add YouTube video URLs. | | `knowledge text` | Replace the chatbot text knowledge document. | | `knowledge files` | Upload local files. | | `knowledge sync-jobs` | Manage recurring content sync and sitemap scan jobs. | | `knowledge sources` | Manage external data-source connections. Alias: `knowledge connections`. | | `knowledge custom-responses` | Manage dashboard Custom Responses. | ## Add knowledge ### Add exact links Use this when you know the exact pages to train: ```bash theme={null} sitegpt knowledge links add --chatbot https://example.com/a https://example.com/b sitegpt knowledge links add --chatbot https://example.com/a --only-main-content true sitegpt knowledge links add --chatbot https://example.com/a --sync WEEKLY ``` ### Crawl a website Use this when you have a starting URL and want SiteGPT to discover pages: ```bash theme={null} sitegpt knowledge website add --chatbot https://docs.example.com sitegpt knowledge website add --chatbot https://docs.example.com --depth 3 --max-links 200 sitegpt knowledge website add --chatbot https://docs.example.com --include-path /docs --exclude-path /blog sitegpt knowledge website add --chatbot https://docs.example.com --allowed-domain docs.example.com ``` Website options: | Option | Description | | --------------------------- | ---------------------------------------------------------------- | | `--depth <1-5>` | Maximum crawl depth. Default: `3`. | | `--max-links <1-1000>` | Maximum URLs to queue. Default: `50`, capped by remaining quota. | | `--include-path ` | Include path pattern. Repeatable. | | `--exclude-path ` | Exclude path pattern. Repeatable. | | `--allowed-domain ` | Allowed domain. Repeatable. | ### Add a sitemap Prefer sitemap ingestion when the website exposes a sitemap: ```bash theme={null} sitegpt knowledge sitemap add --chatbot https://example.com/sitemap.xml sitegpt knowledge sitemap add --chatbot https://example.com/sitemap.xml --max-links 500 sitegpt knowledge sitemap add --chatbot https://example.com/sitemap.xml --scan WEEKLY --sync WEEKLY ``` Sitemap options: | Option | Description | | ----------------------- | ----------------------------------------------------------------------------------------------------- | | `--max-links <1-1000>` | Maximum URLs to queue. Default: `50`, capped by remaining quota. | | `--include-path ` | Include path pattern. Repeatable. | | `--exclude-path ` | Exclude path pattern. Repeatable. | | `--sync ` | Refresh known page content. Values: `NEVER`, `DAILY`, `WEEKLY`, `MONTHLY`. Default: `NEVER`. | | `--scan ` | Scan sitemap for added/deleted URLs. Values: `NEVER`, `DAILY`, `WEEKLY`, `MONTHLY`. Default: `NEVER`. | Sync and scan frequencies are plan-gated. Unsupported requests may be downgraded by the API with warnings. ### Add YouTube videos ```bash theme={null} sitegpt knowledge youtube add --chatbot https://www.youtube.com/watch?v=... sitegpt knowledge youtube add --chatbot https://www.youtube.com/watch?v=... --sync MONTHLY ``` ### Upload local files ```bash theme={null} sitegpt knowledge files add --chatbot ./guide.pdf sitegpt knowledge files add --chatbot ./pricing.pdf ./faq.docx ``` The CLI reads local files and uploads them. Pass file paths, not remote URLs. ### Add or update text knowledge `text update` creates or replaces the chatbot's text knowledge document: ```bash theme={null} sitegpt knowledge text update --chatbot "Refund policy: ..." sitegpt knowledge text update --chatbot --name FAQ --file ./faq.md ``` `text add` is accepted as an alias, but `text update` is clearer because the text block is replaced. ## Scrape options These options work with links, website, sitemap, and document config updates: | Option | Description | | ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | | `--only-main-content ` | Extract main content only. Accepts `true`, `false`, `1`, `0`, `yes`, `no`, `on`, `off`. Default: `true` for new URL ingestion. | | `--include-selector ` | CSS selector to include. Repeatable. | | `--exclude-selector ` | CSS selector to exclude. Repeatable. | | `--header "Name: value"` | Send request header. Repeatable. Allowed names: `User-Agent`, `Accept`, `Accept-Language`. | | `--sync ` | Auto-sync page content. Values: `NEVER`, `DAILY`, `WEEKLY`, `MONTHLY`. | Example: ```bash theme={null} sitegpt knowledge links add \ --chatbot \ https://example.com/docs \ --only-main-content true \ --include-selector main \ --exclude-selector nav \ --header "User-Agent: SiteGPT" ``` ## Documents Documents are individual trained, pending, failed, or queued knowledge items. ### List documents ```bash theme={null} sitegpt knowledge documents list --chatbot sitegpt knowledge documents list --chatbot --json sitegpt knowledge documents list --chatbot --status SUCCESS sitegpt knowledge documents list --chatbot --source LOCAL_FILE sitegpt knowledge documents list --chatbot --state failed sitegpt knowledge documents list --chatbot --query "refund" ``` `knowledge docs` is accepted as an alias for `knowledge documents`. Filters: | Option | Description | | ------------------- | --------------------------------------- | | `--query ` | Search by document name/content. | | `--source ` | Filter by source. Repeatable. | | `--status ` | Filter by ingestion status. Repeatable. | | `--type ` | Filter by document type. Repeatable. | | `--limit <1-100>` | Limit results. Default: `50`. | | `--cursor ` | Continue from a previous response. | Allowed source values: ```text theme={null} TEXT, URLS_LIST, YOUTUBE, SITEMAP, WEBSITE, LOCAL_FILE, NOTION, GOOGLE_DRIVE, DROPBOX, ONEDRIVE, BOX, SHAREPOINT, CONFLUENCE, GITHUB ``` Allowed status values: ```text theme={null} BACKLOG, QUEUED, QUEUED_FOR_RESYNC, QUEUED_FOR_UPDATE, QUEUED_FOR_DELETION, PROCESSING, SUCCESS, FAILED, CANCELLED ``` Allowed type values: ```text theme={null} TEXT, URL, FILE, NOTION_DOCUMENT, GOOGLE_DRIVE_DOCUMENT, DROPBOX_DOCUMENT, ONEDRIVE_DOCUMENT, BOX_DOCUMENT, SHAREPOINT_DOCUMENT, CONFLUENCE_DOCUMENT, GITHUB_DOCUMENT ``` ### Get document details ```bash theme={null} sitegpt knowledge documents get --chatbot sitegpt knowledge documents get --chatbot --content sitegpt knowledge documents get --chatbot --include-content --max-content-chars 50000 --json ``` `--content` includes raw and parsed text when available. Use `--max-content-chars <1-500000>` to limit included text. ### Edit document content ```bash theme={null} sitegpt knowledge documents edit --chatbot --content "Updated content" sitegpt knowledge documents edit --chatbot --file ./updated-content.md ``` `documents update` is accepted as an alias for `documents edit`. ### Resync documents ```bash theme={null} sitegpt knowledge documents resync --chatbot sitegpt knowledge documents resync --chatbot --document sitegpt knowledge documents resync --chatbot --state failed sitegpt knowledge documents resync --chatbot --source WEBSITE --status FAILED ``` ### Delete documents ```bash theme={null} sitegpt knowledge documents delete --chatbot --yes sitegpt knowledge documents delete --chatbot --document --yes sitegpt knowledge documents delete --chatbot --state failed --yes sitegpt knowledge documents delete --chatbot --all --yes ``` `documents remove` is an alias for `documents delete`. Bulk selector options: | Option | Description | | -------------------- | --------------------------------------------------------------------------- | | `--document ` | Select a document ID. Repeatable. | | `--document-id ` | Alias for `--document`. Repeatable. | | `--state ` | Values: `all`, `trained`, `pending`, `failed`. | | `--all` | Select every matching document. Use carefully. | | Filters | `--query`, `--source`, `--status`, and `--type` can narrow bulk operations. | ### Update document config ```bash theme={null} sitegpt knowledge documents update-config --chatbot --document --sync WEEKLY sitegpt knowledge documents update-config --chatbot --document --only-main-content false sitegpt knowledge documents update-config --chatbot --document --include-selector main sitegpt knowledge documents update-config --chatbot --document --exclude-selector nav sitegpt knowledge documents update-config --chatbot --document --header "User-Agent: SiteGPT" ``` ### Document stats ```bash theme={null} sitegpt knowledge documents stats --chatbot sitegpt knowledge documents stats --chatbot --source LOCAL_FILE ``` ## Sync jobs Sync jobs are recurring maintenance jobs. Auto-sync refreshes known content. Sitemap auto-scan discovers URL additions/deletions. ```bash theme={null} sitegpt knowledge sync-jobs list --chatbot sitegpt knowledge sync-jobs get --chatbot sitegpt knowledge sync-jobs update --chatbot --sync WEEKLY sitegpt knowledge sync-jobs update --chatbot --scan MONTHLY sitegpt knowledge sync-jobs delete --chatbot --yes ``` Aliases: * `knowledge jobs` → `knowledge sync-jobs` * `knowledge sync-jobs disable` → `knowledge sync-jobs delete` List filters: | Option | Values | | -------------------- | ------------------------------------------------------------------ | | `--source ` | `URLS_LIST`, `SITEMAP`, `WEBSITE`, `YOUTUBE`, `GITHUB`; repeatable | | `--sync ` | `DAILY`, `WEEKLY`, `MONTHLY`; repeatable | | `--scan ` | `NEVER`, `DAILY`, `WEEKLY`, `MONTHLY`; repeatable | | `--limit <1-100>` | Default: `50` | | `--cursor ` | Continue pagination | Deleting a sync job disables recurring sync/scan. It does not delete existing knowledge documents. ## Custom responses Custom Responses are manual question-and-answer overrides in the Knowledge section. ```bash theme={null} sitegpt knowledge custom-responses list --chatbot sitegpt knowledge custom-responses list --chatbot --state OPEN sitegpt knowledge custom-responses list --chatbot --source MANUALLY_ADDED sitegpt knowledge custom-responses get --chatbot sitegpt knowledge custom-responses add --chatbot --question "What is your refund policy?" --answer "..." sitegpt knowledge custom-responses update --chatbot --answer "Updated answer." sitegpt knowledge custom-responses delete --chatbot --yes ``` Filters: | Option | Values | | ------------------- | --------------------------------------------------------------------- | | `--query ` | Search questions. | | `--state ` | `ALL`, `OPEN`, `UPDATED`. Default: `ALL`. | | `--source ` | `DOWNVOTED_BY_USER`, `MANUALLY_ADDED`, `MARKED_BY_ADMIN`. Repeatable. | Fields: | Option | Description | | ---------------------------- | ------------------------------------------------------- | | `--question ` | Custom response question. | | `--answer ` | Custom response answer. | | `--original-answer ` | Optional original answer when adding a custom response. | ## Full reference * [Knowledge documents](/cli/command-reference#knowledge-documents) * [Knowledge links](/cli/command-reference#knowledge-links) * [Knowledge website](/cli/command-reference#knowledge-website) * [Knowledge sitemap](/cli/command-reference#knowledge-sitemap) * [Knowledge YouTube](/cli/command-reference#knowledge-youtube) * [Knowledge text](/cli/command-reference#knowledge-text) * [Knowledge files](/cli/command-reference#knowledge-files) * [Knowledge sync jobs](/cli/command-reference#knowledge-sync-jobs) * [Custom responses](/cli/command-reference#custom-responses)