Vault QA (Basic)

Vault QA lets you ask questions in plain language and get answers from all your notes in Obsidian. It uses RAG (Retrieval-Augmented Generation), which combines searching your notes with AI responses, making it powerful for finding accurate and relevant information quickly.

Easy Guide to Use Vault QA

0. Make sure you have a working embedding model and chat model in your Copilot settings!

1. Activate Vault QA Mode: In the Copilot interface, choose "Vault QA (Basic)" to activate this mode. Note that it may trigger indexing of your vault, which may take a while for large vaults. Indexing uses your embedding model, so it may generate costs if you're using a paid embedding provider. Use "Count total tokens" Copilot command to estimate the cost first if you have a large vault.

2. Ask Specific Questions: Once indexing completed successfully and you are in Vault QA mode, simply type your questions or queries into the chat input about a specific topic. Copilot will do a local search through your vault and passes relevant parts to the chat model to generate answers.

3. Receive Cited Responses: The AI will respond with relevant information and include Sources citations to the specific notes where the information was found. This allows you to easily track the sources within your vault.

Tips for Effective Use of Vault QA

• Vault QA is best for specific questions. Beware of its limitations since it's relies on retrieval. Questions like "give me an overview of my vault" won't retrieve anything because there's nothing in the query to retrieve. Instead, ask questions like "what did I learn about x?" or "what are some ideas I jotted down about y?"
• Regularly refresh your index, especially after adding new notes or making significant changes to your vault. You can click on the 3-dot icon above your chat box and select Refresh Vault Index or Force Reindex Vault.
• Sources citations are provided at the end of the AI response to verify your original notes.
• Experiment with different chat and embedding models to balance speed and accuracy. OpenAI's gpt-4o and text-embedding-3-small are good default options.
• Technical and Cost Considerations:
  • Indexing large vaults can take time and may incur costs if using paid embedding services.
  • Embedding costs are generally low, but always check pricing for your chosen model.
  • Local embedding models (e.g., Ollama) offer privacy and cost benefits but may be slower or less accurate than cloud-based services.

Advanced Options

• Check out Copilot Plus to enhance your Vault QA experience. It features a more advanced RAG system and agentic custom tools that handle complex queries, support multimodal context understanding, and provide more accurate answers.