feat: ghost text AI inline + Ollama qwen2.5-coder:1.5b
- Ollama provider ajoute dans ai.py (OpenAI-compatible API) - Service ollama dans docker-compose (auto-pull qwen2.5-coder:1.5b) - Ghost overlay dans Forge: prediction en texte pale apres le curseur - Tab pour accepter, Escape pour rejeter, taper pour annuler - Declenchement automatique apres 800ms de pause - Scroll sync entre overlay et textarea - Env vars: AI_DEFAULT_PROVIDER, OLLAMA_BASE_URL, OLLAMA_MODEL
This commit is contained in:
@@ -20,3 +20,25 @@ services:
|
||||
- OBSIGATE_AUTH_ENABLED=false
|
||||
- OBSIGATE_ADMIN_USER=admin
|
||||
- OBSIGATE_ADMIN_PASSWORD=test123
|
||||
- AI_DEFAULT_PROVIDER=deepseek
|
||||
- OLLAMA_BASE_URL=http://ollama:11434/v1
|
||||
- OLLAMA_MODEL=qwen2.5-coder:1.5b
|
||||
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
container_name: obsigate-ollama
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "11434:11434"
|
||||
volumes:
|
||||
- ollama_data:/root/.ollama
|
||||
entrypoint: ["/bin/sh", "-c"]
|
||||
command:
|
||||
- |
|
||||
ollama serve &
|
||||
sleep 5
|
||||
ollama pull qwen2.5-coder:1.5b
|
||||
wait
|
||||
|
||||
volumes:
|
||||
ollama_data:
|
||||
|
||||
Reference in New Issue
Block a user