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.

README.md

@@ -1,40 +1,38 @@
-# Chat Bot Backend
+# Chat Backend
 
-## Setup
+Django + Channels API for AIML Operations chat (`llm_be/`).
 
-Clone the repo
-```console
-git clone http://10.0.0.160:3000/AI_ML_Operations_LLC/Chat_Bot_Backend.git
+## Local (uv)
+
+```bash
+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
 ```
 
-Go into the repo
-```console
-cd Chat_Bot_Backend
+## Docker (dev compose = bundled Postgres)
+
+```bash
+docker compose up --build
 ```
 
-Create the virtual environment
-```console
-virtualenv --python=python3.9 venv
-```
+Prod compose (`docker-compose.prod.yml`) expects external `DATABASE_URL` and
+`WEB_PORT` from server-infra secrets. See `.env.prod.example`.
 
-Activate the Virtual Environment
-```console
-. venv/bin/activate
-```
+## Ollama
 
-Install the requirments
-```console
-python -m pip install -r requirements.txt
-```
+Set `OLLAMA_BASE_URL` (default `http://127.0.0.1:11434` locally).
+Deployed envs use the GPU host: `http://10.0.0.128:11434`.
 
-Pre-populate the database with test data
+## File storage
 
-Run the dev server
-```console
-python manage.py
-```
+Prompt attachments and documents are stored in Postgres (`StoredFile` /
+`DatabaseStorage`), not on the container filesystem.
 
-## TODO
+## Deploy
 
- - [ ] Create inital database with temp data
- - [ ] Do a lot of stuff.....
+Gitea Actions on `master` → `server-infra/scripts/deploy.sh --app chat_backend --env prod`.
+
+Related: [chat_backend#6](https://git.aimloperations.com/ai_ml_operations/chat_backend/issues/6)