AI GitHub
AnythingLLM for document workspaces
Set up separate chat workspaces around document collections and chosen model providers.
Key Takeaways
- The workspace is the unit of document organization and retrieval.
- A deployment needs a generation provider, an embedding provider and a document collection.
- Create two workspaces with deliberately different source files.
- Switching embedding models can require rebuilding the index.
How it works
The workspace is the unit of document organization and retrieval. A deployment can select an embedding backend and model endpoint, which makes those settings part of where document data travels.
What you need
A deployment needs a generation provider, an embedding provider and a document collection. Keep the workspace identifier with application-side settings if a custom client addresses several workspaces.
What to try first
Create two workspaces with deliberately different source files. Ask the same question in both, verify the source passages, and record which processes receive the text during indexing and chat.
Delete a test file from one workspace and repeat the query. Observe the behavior of both previously stored conversation history and new retrieval results.
Where to look for failures
Switching embedding models can require rebuilding the index. Treat workspace sharing, model provider configuration and the vector store as separate decisions when deploying for a team.
Related Franklin pages
Use the same two or three documents in each workspace. Comparing source passages, index updates and data flow reveals differences that a fluent chat answer can hide.
- Collect research sources into notebooks and turn selected material into notes or audio. Open Notebook for source-based research
- Put a browser chat interface in front of Ollama or an OpenAI-compatible API. Open WebUI for self-hosted model chat
For more on how model size affects deployment decisions, read Franklin’s guide. Small language models
Project documentation
Try it for your workflow
Explore the project’s documentation for setup and usage, or save this page to a collection for later.
Read the project documentation ↗