⚡️(asgi) use uvicorn to serve backend

This is a naive first switch from sync to async.
This enables the backend to still answer to incomming requests
while streaming LLM results to the user.

For sure there is room for code cleaning and improvements, but
this provides a nice improvement out of the box.

Dockerfile

@@ -151,7 +151,7 @@ RUN rm -rf /var/cache/apk/*
 
 ARG IMPRESS_STATIC_ROOT=/data/static
 
-# Gunicorn
+# Gunicorn - not used by default but configuration file is provided
 RUN mkdir -p /usr/local/etc/gunicorn
 COPY docker/files/usr/local/etc/gunicorn/impress.py /usr/local/etc/gunicorn/impress.py
 
@@ -165,5 +165,18 @@ COPY --from=link-collector ${IMPRESS_STATIC_ROOT} ${IMPRESS_STATIC_ROOT}
 # Copy impress mails
 COPY --from=mail-builder /mail/backend/core/templates/mail /app/core/templates/mail
 
-# The default command runs gunicorn WSGI server in impress's main module
+# The default command runs uvicorn ASGI server in dics's main module
-CMD ["gunicorn", "-c", "/usr/local/etc/gunicorn/impress.py", "impress.wsgi:application"]
+# WEB_CONCURRENCY: number of workers to run <=> --workers=4
+ENV WEB_CONCURRENCY=4
+CMD [\
+  "uvicorn",\
+  "--app-dir=/app",\
+  "--host=0.0.0.0",\
+  "--timeout-graceful-shutdown=300",\
+  "--limit-max-requests=20000",\
+  "--lifespan=off",\
+  "impress.asgi:application"\
+  ]
+
+# To run using gunicorn WSGI server use this instead:
+#CMD ["gunicorn", "-c", "/usr/local/etc/gunicorn/conversations.py", "impress.wsgi:application"]

src/backend/impress/asgi.py

@@ -0,0 +1,18 @@
+"""
+ASGI config for impress project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/dev/howto/deployment/asgi/
+"""
+
+import os
+
+from configurations.asgi import get_asgi_application
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "impress.settings")
+os.environ.setdefault("DJANGO_CONFIGURATION", "Development")
+os.environ.setdefault("PYTHON_SERVER_MODE", "async")
+
+application = get_asgi_application()

src/backend/impress/wsgi.py

@@ -13,5 +13,6 @@ from configurations.wsgi import get_wsgi_application
 
 os.environ.setdefault("DJANGO_SETTINGS_MODULE", "impress.settings")
 os.environ.setdefault("DJANGO_CONFIGURATION", "Development")
+os.environ.setdefault("PYTHON_SERVER_MODE", "sync")
 
 application = get_wsgi_application()

src/backend/pyproject.toml

@@ -61,6 +61,7 @@ dependencies = [
     "redis<6.0.0",
     "requests==2.32.5",
     "sentry-sdk==2.48.0",
+    "uvicorn==0.40.0",
     "whitenoise==6.11.0",
 ]
 

src/helm/env.d/dev/configuration/theme/demo.json

@@ -135,9 +135,15 @@
     }
   },
   "header": {
+    "logo": {},
     "icon": {
       "src": "/assets/icon-docs.svg",
-      "width": "32px"
+      "style": {
+        "width": "32px",
+        "height": "auto"
+      },
+      "alt": "",
+      "withTitle": true
     }
   },
   "waffle": {
@@ -164,5 +170,26 @@
       ]
     },
     "showMoreLimit": 9
+  },
+  "home": {
+    "with-proconnect": false,
+    "icon-banner": {
+      "src": "/assets/icon-docs.svg",
+      "style": {
+        "width": "64px",
+        "height": "auto"
+      },
+      "alt": ""
+    }
+  },
+  "favicon": {
+    "light": {
+      "href": "/assets/favicon-light.png",
+      "type": "image/png"
+    },
+    "dark": {
+      "href": "/assets/favicon-dark.png",
+      "type": "image/png"
+    }
   }
 }

src/helm/env.d/dev/values.impress.yaml.gotmpl

@@ -91,11 +91,14 @@ backend:
     restartPolicy: Never
 
   command:
-    - "gunicorn"
+    - uvicorn
-    - "-c"
+    - --app-dir=/app
-    - "/usr/local/etc/gunicorn/impress.py"
+    - --host=0.0.0.0
-    - "impress.wsgi:application"
+    - --timeout-graceful-shutdown=300
-    - "--reload"
+    - --limit-max-requests=20000
+    - --lifespan=off
+    - --reload
+    - "impress.asgi:application"
 
   createsuperuser:
     command:
@@ -145,6 +148,9 @@ frontend:
     pullPolicy: Always
     tag: "latest"
 
+  securityContext:
+    runAsNonRoot: false
+
 yProvider:
   replicas: 1