New Workspace
⚠ Changing the database path will restart the UI.
Ingestion Sync
Enrich on Watch
Run semantic enrichment for watch-triggered syncs too (only applies if Semantic Indexing is enabled).
Document Preview
Loading…
Ingesting…
Access Denied

Settings

Keys are stored locally on your machine, outside the project folder. They are never uploaded anywhere.

Google
OpenAI
Anthropic
Ollama
No key required — runs locally. Install from ollama.com.
LANGSMITH TRACING (OPTIONAL)
LangSmith

Enable LangSmith tracing to trace and debug agent runs. Leave blank to disable.

Semantic features add AI-powered metadata at ingest time. Disabled by default.

Enable Semantic Indexing
Runs ConceptCompiler + StructuralParser at ingest. Adds one LLM call per document.
Enable Query Expansion
Expands queries with synonyms at search time for better recall.
Semantic Model (optional override)

Use a different provider and model for concept extraction at ingest time. Leave on Default to use the same model as the agent.

ℹ Add models first via the Model Manager tab — they will appear here automatically.

RE-RANKING
Enable Re-ranking
Re-rank BM25 search results with a local cross-encoder (flashrank) for better relevance. Model downloads once (~17MB), runs fully offline. Recommended.
Fetch top-k × this many BM25 candidates before re-ranking. Higher = better quality, slower.

Add model names per provider. They will appear in the Model dropdown in the sidebar.

Add Model
Model access by role

Choose which of the models above each role may use for their own queries (see the Provider/Model selector in the sidebar). A role with nothing added here cannot query at all — superadmin always bypasses this and is never affected.

Member
Admin
Concurrency (max simultaneous LLM calls)

For Ollama, set this to whatever your own hardware actually supports (mirrors Ollama's own OLLAMA_NUM_PARALLEL) — this framework can't detect your VRAM. For cloud providers, this is a burst control on top of any RPM/TPM override below. Leave a provider unset for no cap.

Quota overrides (RPM / TPM / RPD)

Google gets auto-detected free-tier limits by default; every other provider tracks nothing until you add an override here. Set real numbers from your paid-tier account — leave a field blank to not track that dimension.

Override ingestion and search constants. Leave blank to use the compiled-in defaults. Changes take effect on the next ingest run.

Chunking
Table / CSV Chunking
PDF / DOCX Batching
OCR
Agent & Search

Manage who can access this deployment and what they can do. Real enforcement always happens server-side — this panel is a convenience over the same API the CLI uses. A key created here is always an ordinary credential — whether its holder acts as a workspace admin or member is entirely determined by the grants below, not by anything set at key-creation time. Framework-level superadmin status can only be granted via the CLI (local-search auth create-key --superadmin), never from this panel.

Grant / revoke workspace access
WorkspaceSubjectRoleGranted by
API keys
This key will not be shown again — copy it now.
SubjectDisplay nameStatusCreated
Version{{ version }}
GitHubwiss84/local-search-agent