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.

API Key

Project

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.

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

Add Model

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

Chunking

Min chars before chunking

Target chars per chunk

Max chars per chunk

Overlap chars between chunks

Table / CSV Chunking

Rows per chunk

PDF / DOCX Batching

PDF pages per batch

PDF split threshold (pages)

PDF fallback pages per batch

DOCX char split threshold

OCR

Tesseract fallback min chars

Agent & Search

Default top-k results

Max agent iterations

Snippet context chars

Version{{ version }}

GitHubwiss84/local-search-agent