Settings

Configure your LLM provider, search method, tuning parameters, and chunk settings to optimize search quality and AI response behavior.

Who can access this?

analyst manager superadmin

Overview

Settings are persisted in a dedicated SQLite database (settings.db). Environment variables serve as initial defaults only — once you change a setting via the UI, the stored value takes priority.

Settings page
Screenshot: Settings page with search method radios, sliders, toggles, and model info card

All Configurable Settings

SettingTypeDefaultRangeDescription
Model Provider Select bedrock bedrock / gemini Which LLM provider to use for generating AI responses
Search Method Radio hybrid hybrid / vector / bm25 Which search algorithm to use (see How Search Works)
Temperature Slider 0.7 0.0 – 1.0 Controls LLM creativity. Lower = more factual, Higher = more creative
Relevance Threshold Slider 0.25 0.0 – 1.0 Minimum score for search results to be included. Higher = stricter filtering
Top K Number 5 1 – 50 Maximum number of search results sent to the LLM as context
Chunk Size Slider 500 100 – 10,000 Number of characters per document chunk (affects new uploads only)
Chunk Overlap Slider 50 0 – 5,000 Characters shared between consecutive chunks
Use LLM Toggle On On / Off When off, queries return raw search results without AI-generated answers
Streaming Toggle On On / Off When on, responses are streamed word-by-word via SSE

LLM Provider

BABEH supports two LLM providers. You can switch between them at any time.

AWS Bedrock

PropertyValue
Default modelamazon.nova-lite-v1:0
Also supportsAnthropic Claude models via Bedrock
FeaturesSync + streaming responses
AuthAWS credentials (Access Key, Secret Key, Region)

Google Gemini

PropertyValue
Default modelgemini-2.0-flash-exp
Also supportsAny Gemini model (configurable via env var)
FeaturesSync + streaming responses
AuthGemini API key
Provider Credentials

LLM provider credentials (AWS keys, Gemini API key) are configured as environment variables on the server — they cannot be changed from the Settings UI. Contact your system administrator to update credentials.

Temperature Guide

Temperature controls the randomness/creativity of the AI's responses:

ValueBehaviorBest For
0.0 – 0.3 Very factual, deterministic Pricing queries, spec lookups, factual Q&A
0.3 – 0.7 Balanced (default: 0.7) General queries, explanations
0.7 – 1.0 More creative, varied Content generation, brainstorming

Tuning Tips

Best Practices
  • Low relevance threshold (0.1–0.2) — More results, but may include less relevant ones. Good for broad queries.
  • High relevance threshold (0.4–0.6) — Fewer, more precise results. Good when you need accuracy.
  • Higher Top-K (10–20) — Gives the LLM more context, useful for comparison queries.
  • Smaller chunks (200–400) — Better for precise, specific questions.
  • Larger chunks (800–1500) — Better for context-heavy, explanatory questions.

Save & Reset

Public API Access

Current settings can be read via the public API at GET /api/settings (requires API key). The widget and other integrations use this to auto-configure themselves.