Add Knowledge

Knowledge is the content DocsGPT searches and cites when it answers: files you upload, web pages, GitHub repositories, wikis, and content synced from services you connect. When you add a source, DocsGPT parses it, splits it into chunks and embeds them into the vector store. At question time it retrieves the most relevant chunks and passes them to the model with the question. The model itself is not changed.

The recording opens Settings > Knowledge and clicks Add knowledge. It picks Upload File, selects a PDF product handbook, names it “Espresso One handbook” and clicks Add to Knowledge. A progress panel shows the upload, and the handbook appears on the Knowledge page. It then adds a single web page with Link, named “DocsGPT quickstart”, and both sources are listed when indexing finishes.

Open the Add knowledge dialog

Open Knowledge

Go to Settings > Knowledge and click Add knowledge. From a chat, you can also open the composer’s Knowledge menu and choose Upload new.

Pick a source type

Option	What it adds
Upload File	Files from your computer, including `.zip` archives. See Upload files.
Link	One web page, by URL.
Crawler	A website: starts at a URL and follows links on the same host, up to 10 pages.
GitHub	A public repository, by its URL. Private repositories go through your GitHub connection.
New wiki	An editable Markdown wiki that agents can read and rewrite. See Wiki sources.
Connect your data	Content synced from a connected service, such as Google Drive, SharePoint, Confluence or Amazon S3. See Connectors. This tile shows only when the instance has a connector that syncs.

Name the source and add it

Every source needs a Name. It is how the source appears on the Knowledge page and in the knowledge pickers. For an upload, the name starts as the first file’s name.

Advanced settings (not shown for a wiki) holds the chunking and retrieval options for this source. The defaults suit most content; see Per-source configuration for what each option does.

Click Add to Knowledge (Create for a wiki). The dialog closes, and a panel in the corner shows the upload, parsing and embedding progress. The source appears on the Knowledge page when indexing finishes. If indexing fails, the source’s menu offers Reingest.

Upload files

Upload File accepts one or more files. Files you pick together become one source.

The upload dialog accepts these types:

Documents: .pdf, .docx, .doc, .docm, .odt, .rtf, .txt, .md, .rst, .html, .xhtml, .epub, .json
Spreadsheets: .xlsx, .xls, .xlsm, .xlsb, .ods, .csv
Presentations: .pptx, .ppt, .pptm, .pps, .ppsx, .ppsm, .pot, .odp
Images: .png, .jpg, .jpeg. Their text is read with OCR when OCR is enabled (OCR_ENABLED, off by default). PARSE_IMAGE_REMOTE instead uploads each image to the hosted https://llm.arc53.com/doc2md service, so if images must stay on your servers, use OCR_ENABLED. With both off, an image adds no text. See Document parsing and OCR.
Audio: .wav, .mp3, .m4a, .ogg, .webm. Audio is transcribed with speech-to-text, and the transcript is indexed.
Archives: .zip

ℹ️

The upload dialog takes files up to 25 MB each. It lists larger files, and files of other types, as not added. Uploads through the API are capped by the server instead: UPLOAD_MAX_FILE_BYTES (100 MB per file by default), UPLOAD_MAX_REQUEST_BYTES (256 MB per request) and, for audio, STT_MAX_FILE_SIZE_MB (50 MB).

Zip archives are extracted on the server, and every supported file inside is indexed, including archives nested up to three levels deep. Files of other types are skipped. This is also how to upload .mdx files, which the dialog doesn’t list. The server rejects an upload whose archives expand past UPLOAD_MAX_ARCHIVE_BYTES (250 MB), hold more than UPLOAD_MAX_ARCHIVE_FILES (10,000) files, or nest deeper than UPLOAD_MAX_ARCHIVE_DEPTH (3). The size and file-count limits apply to all the archives in one upload combined. Office and e-book files (.docx, .xlsx, .pptx, .odt, .epub and similar) are zip containers internally, but DocsGPT parses them as documents and does not unpack them.

Scanned PDFs and images need OCR, which is off by default (OCR_ENABLED). See Document parsing and OCR for the parser engines and OCR settings. All size and parsing settings are listed in the settings reference.

Add a web page or a website

Link reads the one page at the URL.
Crawler starts at the URL and follows links on the same host until it has tried 10 pages. Pages that fail to load count toward the 10.

Both fetch pages from the DocsGPT server, not from your browser. Pages behind a sign-in can’t be read, and URLs that resolve to private or internal addresses are refused.

Add a GitHub repository

Paste a public repository URL, such as https://github.com/arc53/DocsGPT. An operator can set GITHUB_ACCESS_TOKEN to raise GitHub’s rate limit for these public reads. That token is never used for private repositories.

For a private repository, use Connect GitHub in the form, or Pick a repository if you are already connected. These buttons appear when the GitHub connector is set up on the instance. They hand over to the GitHub connection, which lists your account’s repositories. See GitHub.

Sync content from connected services

Connect your data lists the services on this instance that can sync into Knowledge. Pick one, sign in, then choose which files or folders to sync and how often. You can also start from Connect a service on an empty Knowledge page, or from Settings > Connectors. Operators must configure each connector first; see Connectors.

Manage your knowledge

Each source on the Knowledge page has a menu. Which items appear depends on the source type and on your access to it:

View opens the source’s files and chunks. If you can edit the source, you can edit, add and delete chunks.
Sync: Never / Daily / Weekly / Monthly and Sync now appear for sources that can be fetched again: links, crawls, GitHub repositories and connector content. A sync replaces the content, so it can overwrite chunk edits.
Source settings changes chunking and retrieval. Retrieval changes apply on the next question. Chunking changes apply only after the source is re-ingested. See Per-source configuration.
Test retrieval runs a question against the source and shows which chunks come back.
Convert to wiki turns the source into editable wiki pages. This can’t be undone.
Share with team shares the source with a team. See Access control.
Delete removes the source and its index.

To build a knowledge graph over a source, see GraphRAG.

Use knowledge in chats and agents

In a chat without an agent, click Knowledge in the composer and select one or more sources. Answers draw on the chunks retrieved from them and cite them. The menu’s footer has Go to Knowledge, Connect more (the connectors that sync into Knowledge) and Upload new.
In an agent, pick sources in the agent builder’s Knowledge field (Select knowledge). Knowledge is optional: without it, the agent answers from the model and its tools. When you chat with an agent, the composer hides the Knowledge button because the agent uses its own. See Agents.

Attach in the composer is different. It adds a file to the current conversation only. To reuse a file across chats and agents, add it to Knowledge instead.