bvandeusen
590682a5d2
Research pipeline (research_topic tool): - New service: services/research.py — sub-query generation, SearXNG search, URL fetch, deduplication, and LLM synthesis into a note - 5 sub-queries × 3 pages = up to 15 sources, capped at 12 for synthesis - Synthesis uses num_ctx=16384 + max_tokens=8192 for long-form output - Prompt demands 2500+ words, 6+ topic-appropriate sections, detailed prose - 429 retry with backoff; 1s inter-query sleep; raw_decode JSON parsing search_web tool (new): - Lightweight single-query SearXNG search, results returned inline in chat - LLM answers conversationally in round 1; no note created - web_search result type with external links in ToolCallCard Infrastructure: - llm.py: generate_completion accepts num_ctx override - config.py: SEARXNG_URL + Config.searxng_enabled() - docker-compose: OLLAMA_NUM_PARALLEL=2, commented SEARXNG_URL example - intent.py: search_web and research_topic routing rules Settings UI: - 2-column grid layout (small sections pair up, complex span full width) - Search Test section: live SearXNG query with result preview - GET /api/settings/search?q= proxy endpoint - Research button (magnifier) in ChatView input toolbar → popover modal Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
59 lines
1.6 KiB
YAML
59 lines
1.6 KiB
YAML
services:
|
|
app:
|
|
build: .
|
|
ports:
|
|
- "5000:5000"
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
ollama:
|
|
condition: service_started
|
|
environment:
|
|
DATABASE_URL: "postgresql+asyncpg://${POSTGRES_USER:-fabled}:${POSTGRES_PASSWORD:-fabled}@db:5432/${POSTGRES_DB:-fabledassistant}"
|
|
OLLAMA_URL: "http://ollama:11434"
|
|
OLLAMA_MODEL: "${OLLAMA_MODEL:-llama3.1}"
|
|
SECRET_KEY: "${SECRET_KEY:-dev-secret-change-me}"
|
|
# Uncomment and set to enable web research via SearXNG:
|
|
# SEARXNG_URL: "http://searxng:8080"
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/api/health')"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 30s
|
|
|
|
db:
|
|
image: postgres:16-alpine
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-fabled}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-fabled}
|
|
POSTGRES_DB: ${POSTGRES_DB:-fabledassistant}
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-fabled}"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
ollama:
|
|
image: ollama/ollama
|
|
volumes:
|
|
- ollama_models:/root/.ollama
|
|
environment:
|
|
OLLAMA_MAX_LOADED_MODELS: "2"
|
|
OLLAMA_NUM_PARALLEL: "2"
|
|
OLLAMA_KEEP_ALIVE: "30m"
|
|
OLLAMA_FLASH_ATTENTION: "1"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
|
|
volumes:
|
|
pgdata:
|
|
ollama_models:
|