build(docker): granite is the standalone stack's default embedding model

settings.EMBEDDINGS_NAME still defaults to mpnet so an upgraded deployment
keeps its index; new installs only get granite because setup.sh writes it to
.env. The standalone compose always starts on fresh volumes, so it defaults
EMBEDDINGS_NAME to granite (overridable from .env or the shell), and the
Docker guide's hand-written .env examples name the model too.

deployment/docker-compose-standalone.yaml

@@ -17,6 +17,9 @@
 #                          develop follows the main branch
 #   DOCSGPT_IMAGE_VARIANT  empty (slim, default) or -docling: docling parser
 #                          engine, its models, and tesseract baked in (OCR-ready)
+#   EMBEDDINGS_NAME        defaults to granite here (this stack always starts on
+#                          fresh volumes, so there is no older index to keep
+#                          compatible); the code default stays mpnet for upgrades.
 name: docsgpt
 
 services:
@@ -47,6 +50,7 @@ services:
       - CELERY_RESULT_BACKEND=redis://redis:6379/1
       - CACHE_REDIS_URL=redis://redis:6379/2
       - POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
+      - EMBEDDINGS_NAME=${EMBEDDINGS_NAME:-ibm-granite/granite-embedding-311m-multilingual-r2}
     ports:
       - "7091:7091"
     volumes:
@@ -75,6 +79,7 @@ services:
       - CACHE_REDIS_URL=redis://redis:6379/2
       - POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
       - API_URL=http://backend:7091
+      - EMBEDDINGS_NAME=${EMBEDDINGS_NAME:-ibm-granite/granite-embedding-311m-multilingual-r2}
     volumes:
       - indexes:/app/indexes
       - inputs:/app/inputs

docs/content/Deploying/Docker-Deploying.mdx

@@ -42,7 +42,9 @@ first use. You do not need the source tree to run them:
 
     `INTERNAL_KEY` is the secret the worker uses to hand finished indexes to
     the API; without it every upload fails with a 401. `setup.sh` generates
-    one for you, a hand-written `.env` has to include it.
+    one for you, a hand-written `.env` has to include it. This stack runs the
+    granite embedding model unless `.env` sets `EMBEDDINGS_NAME`; both granite
+    and mpnet are baked into the image.
 
 3.  **Start it:**
 
@@ -91,9 +93,13 @@ extra packages: `EXTRAS=docling` in `.env`).
     LLM_PROVIDER=docsgpt
     VITE_API_STREAMING=true
     INTERNAL_KEY=<any random string, e.g. openssl rand -hex 16>
+    EMBEDDINGS_NAME=ibm-granite/granite-embedding-311m-multilingual-r2
     ```
 
-    This minimal configuration tells DocsGPT to use the public API. For more advanced settings and other LLM options, refer to the [DocsGPT Settings Guide](/Deploying/DocsGPT-Settings).
+    This minimal configuration tells DocsGPT to use the public API. The
+    `EMBEDDINGS_NAME` line is what `setup.sh` writes for a new install; without
+    it the code falls back to mpnet, the model earlier releases indexed with,
+    so that an upgraded deployment keeps its existing index working. For more advanced settings and other LLM options, refer to the [DocsGPT Settings Guide](/Deploying/DocsGPT-Settings).
 
 4.  **Launch DocsGPT with Docker Compose:**