“ydy0615”
30 lines
836 B
Bash
30 lines
836 B
Bash
# LLM provider (OpenAI-compatible endpoint)
|
|
LLM_BASE_URL=http://localhost:11434/v1/
|
|
# For Ollama, API key is not required but a placeholder is needed.
|
|
LLM_API_KEY=ollama
|
|
|
|
# Default model for inline completions (e.g., gpt-oss:20b, qwen3:8b)
|
|
LLM_MODEL=gpt-oss:20b
|
|
|
|
# Pro-tier model (defaults to LLM_MODEL if unset)
|
|
PRO_LLM_MODEL=gpt-oss:20b
|
|
|
|
# Vision model for OCR (e.g., qwen3-vl:30b, llava)
|
|
VLM_MODEL=qwen3-vl:30b
|
|
|
|
# API key for the FastAPI app (change in production)
|
|
API_KEY=your-secret-key-here
|
|
|
|
# PRO completion timeout (seconds)
|
|
PRO_COMPLETION_TIMEOUT=1200
|
|
|
|
# Concurrency limits
|
|
STANDARD_CONCURRENCY_LIMIT=5
|
|
PRO_CONCURRENCY_LIMIT=20
|
|
|
|
# Legacy fallback: if LLM_BASE_URL is not set, OLLAMA_HOST will be auto-converted to /v1/ path
|
|
#OLLAMA_HOST=http://localhost:11434
|
|
|
|
# TTS/ASR settings (see README for full list)
|
|
TTS_ASR_DEVICE=auto
|