Overview
Parsaa can search your project by meaning, not just exact text. When Code Indexing is enabled, the agent’ssemantic_search tool retrieves the most relevant code for a request — even when your wording doesn’t match the identifiers in the source.
This isn’t a separate search box you open with a shortcut. Code Indexing powers retrieval that the agent uses automatically while it works. Searching for “authentication flow” surfaces login logic, token refresh, and session management even if those exact words never appear.
How It Works
Parsaa builds a hybrid index
Your code is chunked and embedded, then stored in a local index that combines vector similarity with full-text (FTS5) search for the best of both — meaning and exact matches.
The index stays on your Mac
The vector + FTS index lives locally under Parsaa’s application support directory. It is per-project and updates as your code changes.
Setup
Embeddings are generated through Parsaa’s backend pipeline — you don’t need a separate embeddings API key. The resulting index is stored locally on your Mac.
What It’s Good For
Architecture & flow
Architecture & flow
- “authentication flow”
- “how data gets saved to Core Data”
- “navigation between screens”
- “dependency injection setup”
Specific patterns
Specific patterns
- “network error handling”
- “SwiftUI views that display user data”
- “async/await usage in the networking layer”
- “custom view modifiers”
Business logic
Business logic
- “payment processing”
- “user session management”
- “push notification handling”
Privacy
Local index
The vector + FTS index is stored on your Mac, per project. It is not uploaded to Parsaa’s servers.
You control retention
In Private Mode nothing is retained past the request. Training Mode adds a “Store Codebases” toggle you can leave off. See Privacy & Data.