omniference 0.3.2

A multi-protocol inference engine with provider adapters
Documentation
## Omniference examples configuration
# Copy this file to `.env` and fill in values as needed.

# Logging
RUST_LOG=info

# Ollama provider
OLLAMA_BASE_URL=http://localhost:11434

# OpenAI-compatible provider (e.g., OpenAI)
OPENAI_BASE_URL=https://api.openai.com
OPENAI_API_KEY=

# Discord example
DISCORD_TOKEN=

# Example servers
# Standalone server
SERVER_ADDR=0.0.0.0:8080
# Embedded Axum example
EMBEDDED_SERVER_ADDR=0.0.0.0:3000