Skip to main content

Settings: Documents

Documents let Row-Bot search files you add to its local document library. This is different from attaching a file to one chat: indexed documents become reusable context for future questions. Mixedbread Embed Large v1 is the recommended local embedding model; it is separate from the chat model and normal use loads it only from Row-Bot's private cache.

Settings: Documents in Row-Bot.
The Documents tab controls uploads, embedding models, indexed document state, and vector rebuild actions.

Where To Find It

Open Settings, then choose Documents from the left tab list.

Controls

  • Upload documents adds files to Row-Bot-managed storage for indexing.
  • Embedding provider and model controls choose how document chunks become searchable vectors.
  • Download model installs the selected local model, Retry local load retries a cached model, and Repair local model deliberately replaces a broken cache entry.
  • Dimension override is for advanced embedding models that need a specific vector size.
  • Batch size controls how much indexing work happens at once.
  • Auto-unload local embedding resources releases local model memory after heavy document work.
  • Indexed Documents lists what Row-Bot has processed and whether each item is ready.
  • Rebuild document vectors repeats indexing when you change embedding settings.
  • Rebuild memory vectors refreshes memory search with the current embedding settings.

Common Workflow

  1. Keep the checked first-launch download, or choose Local runtime model and use Download model before adding a large document library.
  2. Upload a small test document and wait until it is indexed.
  3. Ask Chat a question that should require the document.
  4. Rebuild vectors only when you change embedding model settings or suspect stale search results.

What Is Saved

Uploaded files, extracted text, vectors, and local embedding model caches are stored under the active Row-Bot data directory. In Docker, the named /data volume preserves the cache. The active chat only sees relevant results when document search is enabled. A cloud embedding provider is opt-in and sends indexed text to that provider; the recommended local model does not.

Privacy And Safety

Review credential, account, channel, provider, or tool settings before enabling features that can contact outside services. Local-only features stay on your machine until you ask Row-Bot to use a provider, account, channel, MCP server, plugin, or tool that sends data elsewhere.

Control-Level Reference

The generated Settings Controls reference lists the visible controls found in the current application source, including defaults, allowed values when they are declared inline, dependencies, restart notes, security notes, and source locations.

Troubleshooting

  • If search misses obvious content, rebuild vectors and check the embedding provider.
  • If the local model is missing, use Download model. Use Retry local load for a cached model or Repair local model for a damaged download.
  • If local indexing is slow, lower batch size or enable auto-unload.
  • If a document contains private material, remove it from the document library before sharing screenshots or logs.