llm-in-text/backend/.env.example

# 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