ai_ml_operations/chat_backend

Fork 0

Files

T

westfarn de84ff1b00

CI / test (pull_request) Successful in 15s

Details

Unit Tests / test (pull_request) Successful in 13s

Details

Dockerize chat_backend for server-infra deploy (closes #6 ).

Add uv packaging, env-driven Django settings, OLLAMA_BASE_URL (LAN GPU
host), DatabaseStorage for prompt/document blobs, compose/CI/deploy
workflows mirroring scha, and ASGI gunicorn+UvicornWorker for WebSockets.

2026-07-25 07:03:10 -05:00

930 B

Raw Blame History

Chat Backend

Django + Channels API for AIML Operations chat (llm_be/).

Local (uv)

cp .env.example .env
uv sync
cd llm_be
uv run python manage.py migrate
uv run python manage.py runserver 0.0.0.0:8003

Docker (dev compose = bundled Postgres)

docker compose up --build

Prod compose (docker-compose.prod.yml) expects external DATABASE_URL and WEB_PORT from server-infra secrets. See .env.prod.example.

Ollama

Set OLLAMA_BASE_URL (default http://127.0.0.1:11434 locally). Deployed envs use the GPU host: http://10.0.0.128:11434.

File storage

Prompt attachments and documents are stored in Postgres (StoredFile / DatabaseStorage), not on the container filesystem.

Deploy

Gitea Actions on master → server-infra/scripts/deploy.sh --app chat_backend --env prod.

Related: chat_backend#6

930 B Raw Blame History