“ydy0615”
17d211bf93
- Introduced a new web search block plugin to handle web search queries and results. - Updated copilot, doc block, and pro block plugins to include web search context in AI completions. - Implemented utility functions for parsing and building web search markdown. - Enhanced API to support web search requests and responses. - Added configuration for web search URL and timeout settings. - Updated size limit checks to account for web search content.
129 lines
3.6 KiB
Bash
129 lines
3.6 KiB
Bash
# OpenAI-compatible endpoint
|
|
# In Docker, use host.docker.internal instead of localhost for a model service on the host.
|
|
LLM_BASE_URL=https://api.openai.com/v1/
|
|
LLM_API_KEY=sk-your-key
|
|
|
|
# Default model for inline completions
|
|
LLM_MODEL=gpt-4.1-mini
|
|
|
|
# Pro-tier model (defaults to LLM_MODEL if unset)
|
|
PRO_LLM_MODEL=gpt-4.1
|
|
|
|
# Vision model for OCR
|
|
VLM_MODEL=gpt-4.1-mini
|
|
|
|
# API key for the FastAPI app (change in production)
|
|
API_KEY=your-secret-key-here
|
|
|
|
# Browser origins allowed to send anonymous session cookies
|
|
CORS_ALLOW_ORIGINS=https://imageteach.tech,https://www.imageteach.tech,http://localhost:5173,http://127.0.0.1:5173
|
|
|
|
# Anonymous session cookie
|
|
SESSION_COOKIE_NAME=llm_anonymous_session
|
|
SESSION_COOKIE_SECURE=true
|
|
SESSION_COOKIE_SAMESITE=none
|
|
SESSION_COOKIE_DOMAIN=
|
|
SESSION_COOKIE_PATH=/
|
|
SESSION_COOKIE_MAX_AGE_SECONDS=2592000
|
|
SESSION_ROTATION_SECONDS=86400
|
|
|
|
# Job backend
|
|
JOB_BACKEND=redis
|
|
REDIS_URL=redis://localhost:6379/0
|
|
DATABASE_URL=postgresql://llm_in_text:llm_in_text_change_me@localhost:5432/llm_in_text
|
|
DOCS_BACKEND=postgres
|
|
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_WEB_SEARCH_CONCURRENCY=1
|
|
JOB_WEB_SEARCH_MAX_QUEUE=4
|
|
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
|
|
|
|
# Risk control
|
|
RISK_API_WINDOW_SECONDS=60
|
|
RISK_API_SOFT_LIMIT=90
|
|
RISK_API_HARD_LIMIT=180
|
|
RISK_LLM_WINDOW_SECONDS=600
|
|
RISK_LLM_SOFT_LIMIT=8
|
|
RISK_LLM_HARD_LIMIT=16
|
|
RISK_SESSION_CONCURRENCY_LIMIT=2
|
|
RISK_GLOBAL_CONCURRENCY_LIMIT=12
|
|
RISK_DAILY_BUDGET_GLOBAL_USD=20
|
|
RISK_DAILY_BUDGET_SESSION_USD=2
|
|
RISK_DAILY_BUDGET_IP_USD=5
|
|
RISK_SINGLE_REQUEST_MAX_COST_USD=0.8
|
|
RISK_DELAY_STEP_MS=2500
|
|
RISK_DELAY_CAP_MS=30000
|
|
RISK_MODEL_CIRCUIT_FAILURES=8
|
|
RISK_MODEL_CIRCUIT_TTL_SECONDS=300
|
|
RISK_ENFORCE_REDIS_FAIL_CLOSED=false
|
|
|
|
# Backend-controlled model policy
|
|
RISK_COMPLETION_MODEL=gpt-4.1-mini
|
|
RISK_PRO_MODEL=gpt-4.1
|
|
RISK_VISION_MODEL=gpt-4.1-mini
|
|
RISK_WEB_SEARCH_MODEL=gpt-4.1-mini
|
|
RISK_COMPLETION_MAX_INPUT_CHARS=24000
|
|
RISK_COMPLETION_MAX_OUTPUT_TOKENS=768
|
|
RISK_COMPLETION_TEMPERATURE=0.4
|
|
RISK_PRO_MAX_INPUT_CHARS=48000
|
|
RISK_PRO_MAX_OUTPUT_TOKENS=2048
|
|
RISK_PRO_TEMPERATURE=0.6
|
|
RISK_WEB_SEARCH_MAX_INPUT_CHARS=128000
|
|
RISK_WEB_SEARCH_MAX_OUTPUT_TOKENS=4096
|
|
RISK_WEB_SEARCH_TEMPERATURE=0.4
|
|
RISK_COMPRESS_MAX_INPUT_CHARS=128000
|
|
RISK_COMPRESS_MAX_OUTPUT_TOKENS=1536
|
|
RISK_OCR_MAX_INPUT_BYTES=10485760
|
|
|
|
# Web search providers
|
|
SEARXNG_BASE_URL=http://searxng:8080
|
|
SEARXNG_RESULT_LIMIT=10
|
|
FIRECRAWL_BASE_URL=http://firecrawl:3002
|
|
FIRECRAWL_API_KEY=change-me
|
|
WEB_SEARCH_QUERY_COUNT=4
|
|
WEB_SEARCH_SELECTED_URL_LIMIT=10
|
|
|
|
# Estimated pricing for budget control
|
|
RISK_COMPLETION_INPUT_COST_PER_1K=0.0004
|
|
RISK_COMPLETION_OUTPUT_COST_PER_1K=0.0016
|
|
RISK_PRO_INPUT_COST_PER_1K=0.003
|
|
RISK_PRO_OUTPUT_COST_PER_1K=0.012
|
|
RISK_VISION_INPUT_COST_PER_1K=0.0008
|
|
RISK_VISION_OUTPUT_COST_PER_1K=0.0024
|
|
|
|
# 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
|