“ydy0615”
60 lines
1.5 KiB
Bash
60 lines
1.5 KiB
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
|
|
|
|
# Job backend
|
|
JOB_BACKEND=redis
|
|
REDIS_URL=redis://localhost:6379/0
|
|
JOB_REDIS_PREFIX=llmtext:jobs
|
|
JOB_CONSUMER_NAME=
|
|
JOB_SHARED_TEMP_DIR=/tmp/llm-in-text-jobs
|
|
JOB_STATE_TTL_SECONDS=600
|
|
JOB_EVENT_TTL_SECONDS=600
|
|
JOB_EVENT_STREAM_MAXLEN=512
|
|
JOB_CANCEL_POLL_SECONDS=0.5
|
|
JOB_BUSY_NORMAL_THRESHOLD=0.25
|
|
JOB_BUSY_HIGH_THRESHOLD=0.75
|
|
JOB_BUSY_FULL_THRESHOLD=1.0
|
|
|
|
# Per-queue concurrency and capacity
|
|
JOB_COMPLETION_CONCURRENCY=2
|
|
JOB_COMPLETION_MAX_QUEUE=16
|
|
JOB_PRO_COMPLETION_CONCURRENCY=1
|
|
JOB_PRO_COMPLETION_MAX_QUEUE=8
|
|
JOB_COMPRESS_CONCURRENCY=1
|
|
JOB_COMPRESS_MAX_QUEUE=8
|
|
JOB_OCR_CONCURRENCY=1
|
|
JOB_OCR_MAX_QUEUE=8
|
|
JOB_CONVERT_CONCURRENCY=1
|
|
JOB_CONVERT_MAX_QUEUE=8
|
|
JOB_TTS_CONCURRENCY=1
|
|
JOB_TTS_MAX_QUEUE=4
|
|
JOB_ASR_CONCURRENCY=1
|
|
JOB_ASR_MAX_QUEUE=4
|
|
|
|
# Timeouts (seconds)
|
|
LLM_COMPLETION_TIMEOUT=600
|
|
LLM_OCR_TIMEOUT=600
|
|
|
|
# Compression limit
|
|
DOC_COMPRESS_CONTEXT_LIMIT=128000
|
|
|
|
# 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
|