FernandoJVideiraandClaude Opus 5.5
7ae1fa5747
/tldr [since] summarizes the messages in the channel it is run in that the caller has not been summarized yet, using a small local model on Ollama, and replies ephemerally. The answer streams into the reply as it is written. - Per-user, per-channel cursor (tldr_cursors) so each run picks up where the last left off; `since:` (e.g. 6h, 2d, max 7d) peeks without moving it. First use covers the last 24h, and a stale cursor never reaches back more than 7 days. - Only summarizes channels both the caller and the bot can read. - The transcript drops bots, system messages, reactions and filler, turns links, GIFs, images and files into short tags ([link: site], [image], [file: name], preview titles), marks replies, and writes a date marker where the chat paused for 3h or more so the model can keep topics apart. - The prompt asks for one bullet per conversation, oldest first, with a worked example; it was tuned against a synthetic chat and a real export with qwen3:4b-instruct-2507 (the default model). - One model call at a time across the bot, one /tldr per user. - docker-compose: Ollama service (CPU only, 8g memory cap: 6g killed the runner mid-request), model pull on startup. Needs the tldr_cursors migration (velox-dashboard-api 000016). Co-Authored-By: Claude Opus 5.5 <[email protected]>
79 lines
2.4 KiB
YAML
79 lines
2.4 KiB
YAML
services:
|
|
db:
|
|
image: postgres:16
|
|
container_name: velox-postgres
|
|
restart: unless-stopped
|
|
environment:
|
|
POSTGRES_USER: velox
|
|
POSTGRES_PASSWORD: velox_pwd
|
|
POSTGRES_DB: velox
|
|
ports:
|
|
- "5432:5432"
|
|
volumes:
|
|
- velox_pgdata:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U velox -d velox"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
bot:
|
|
build: .
|
|
container_name: velox-bot
|
|
restart: unless-stopped
|
|
env_file: .env
|
|
environment:
|
|
DB_HOST: ${DB_HOST:-postgres://velox:velox_pwd@db:5432/velox?sslmode=disable}
|
|
LAVALINK_HOST: ${LAVALINK_HOST:-ws://lavalink:2333}
|
|
LAVALINK_PASSWORD: ${LAVALINK_PASSWORD:-youshallnotpass}
|
|
OLLAMA_HOST: ${OLLAMA_HOST:-http://ollama:11434}
|
|
TLDR_MODEL: ${TLDR_MODEL:-qwen3:4b-instruct-2507-q4_K_M}
|
|
TLDR_THREADS: ${TLDR_THREADS:-6}
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
networks:
|
|
- default
|
|
|
|
# Local LLM behind /tldr. CPU only, so it's kept polite: low CPU priority
|
|
# (cpu_shares), a memory cap, and a thread cap the bot sends per request
|
|
# (TLDR_THREADS). Do NOT add a `cpus:` quota: Ollama would still start one
|
|
# busy-waiting thread per core, the quota throttles them, and inference
|
|
# drops to a fraction of a token per second.
|
|
ollama:
|
|
image: ollama/ollama:latest
|
|
container_name: velox-ollama
|
|
restart: unless-stopped
|
|
environment:
|
|
OLLAMA_KEEP_ALIVE: 5m # unload the model when idle to give the RAM back
|
|
OLLAMA_NUM_PARALLEL: "1"
|
|
OLLAMA_MAX_LOADED_MODELS: "1"
|
|
OLLAMA_CONTEXT_LENGTH: "8192"
|
|
volumes:
|
|
- ollama_models:/root/.ollama
|
|
# qwen3:4b measured 5.9 GB in use (model, 8k context cache, buffers and the
|
|
# file cache of the model), so 6g killed the runner mid-request. Leave room.
|
|
mem_limit: 8g
|
|
cpu_shares: 512
|
|
healthcheck:
|
|
test: ["CMD", "ollama", "list"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
# One-shot: downloads the model into the volume, then exits.
|
|
ollama-init:
|
|
image: ollama/ollama:latest
|
|
container_name: velox-ollama-init
|
|
restart: "no"
|
|
depends_on:
|
|
ollama:
|
|
condition: service_healthy
|
|
environment:
|
|
OLLAMA_HOST: http://ollama:11434
|
|
entrypoint: ["/bin/sh", "-c", "ollama pull ${TLDR_MODEL:-qwen3:4b-instruct-2507-q4_K_M}"]
|
|
|
|
volumes:
|
|
velox_pgdata:
|
|
ollama_models:
|