Search & RAG Settings

These settings are found under Advanced Settings in the settings panel. They control Atlas’s local search and retrieval system — how it breaks your notes into searchable pieces and how it finds relevant content. These are free features that run entirely on your device.

How Indexing Works

When you point Atlas at a vault, it reads every note and builds two things: a vector index (for meaning-based search) and a keyword index (for exact-match search). These two indexes are combined at search time for the best of both worlds.

Chunk Size

Range: 100 – 2000 characters | Default: 500

When indexing a note, Atlas splits it into overlapping segments called chunks. Each chunk is what gets searched and returned as a result.

• Smaller chunks (100 – 300): More precise retrieval — you get the exact paragraph that’s relevant. Good for dense notes with lots of distinct facts.
• Larger chunks (700 – 2000): More context per result — each hit includes more surrounding text. Good for narrative notes, meeting summaries, or long-form writing.

The default of 500 characters works well for most vaults.

Chunk Overlap

Range: 0 – 500 characters | Default: 50

The number of characters shared between adjacent chunks. Overlap helps avoid splitting a sentence or idea right at a chunk boundary.

If you find that search results sometimes feel like they’re missing the beginning or end of a thought, try increasing overlap to 100–150.

Embedding Model

Two models are available:

Model	Speed	Memory	Accuracy
BGE-small	Faster	Less (~100MB)	Good
BGE-base	Slower	More (~400MB)	Better

BGE-small is the right choice for most users, especially on older hardware or laptops without dedicated GPU memory. BGE-base produces slightly more accurate semantic matches and is worth trying if you have a modern machine.

Caution

Changing the embedding model requires a full re-index of your vault. The current index will be cleared and rebuilt automatically. This can take a few minutes for large vaults.

Relevance Threshold

Range: 0.0 – 0.9 | Default: 0.3

The minimum score a result must have to be included. Results below this threshold are discarded.

• Lower values (0.1 – 0.2): More results, but some may not be very relevant
• Higher values (0.5 – 0.9): Only very strong matches get through

If search feels too noisy, raise the threshold. If useful notes aren’t showing up, lower it.

Hybrid Search

Default: On

Hybrid search combines semantic (meaning-based) and keyword (exact-match) search into a single ranked list. This almost always outperforms either approach alone.

Turn this off only if you’re debugging or have a specific reason to use pure vector search.

Search Weights

A preset dropdown controls the balance between semantic and keyword search:

Preset	Semantic	Keyword
Balanced (default)	70%	30%
Semantic-heavy	90%	10%
Keyword-heavy	30%	70%
Custom	You choose	You choose

The two weight sliders let you fine-tune the balance when using the Custom preset. Semantic search understands meaning (e.g., “happy” finds “joyful”). Keyword search finds exact matches (better for code, names, identifiers).

Note

The default split (70% semantic / 30% keyword) works well for natural-language queries. If you often search for specific proper nouns, file names, or technical terms, try shifting toward a higher keyword weight.

---

For more on how Atlas uses these search results in AI chat, see How Context Works.