Preparing for release. (#2540)

* Preparing for release.

* Upgrade version in docs.

docs/openapi.json.rej

@@ -0,0 +1,10 @@
+diff a/docs/openapi.json b/docs/openapi.json	(rejected hunks)
+@@ -10,7 +10,7 @@
+       "name": "Apache 2.0",
+       "url": "https://www.apache.org/licenses/LICENSE-2.0"
+     },
+-    "version": "2.2.1-dev0"
++    "version": "2.3.1-dev0"
+   },
+   "paths": {
+     "/": {

docs/source/installation_amd.md

@@ -11,7 +11,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm -it --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
     --device=/dev/kfd --device=/dev/dri --group-add video \
     --ipc=host --shm-size 256g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.2.0-rocm \
+    ghcr.io/huggingface/text-generation-inference:2.3.0-rocm \
     --model-id $model
 ```
 

docs/source/installation_intel.md

@@ -12,7 +12,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm --privileged --cap-add=sys_nice \
     --device=/dev/dri \
     --ipc=host --shm-size 1g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.2.0-intel-xpu \
+    ghcr.io/huggingface/text-generation-inference:2.3.0-intel-xpu \
     --model-id $model --cuda-graphs 0
 ```
 
@@ -29,7 +29,7 @@ volume=$PWD/data # share a volume with the Docker container to avoid downloading
 docker run --rm --privileged --cap-add=sys_nice \
     --device=/dev/dri \
     --ipc=host --shm-size 1g --net host -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.2.0-intel-cpu \
+    ghcr.io/huggingface/text-generation-inference:2.3.0-intel-cpu \
     --model-id $model --cuda-graphs 0
 ```
 

docs/source/installation_nvidia.md

@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 64g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.2.0 \
+    ghcr.io/huggingface/text-generation-inference:2.3.0 \
     --model-id $model
 ```
 

docs/source/quicktour.md

@@ -11,7 +11,7 @@ model=teknium/OpenHermes-2.5-Mistral-7B
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data \
-    ghcr.io/huggingface/text-generation-inference:2.2.0 \
+    ghcr.io/huggingface/text-generation-inference:2.3.0 \
     --model-id $model
 ```
 

nix/client.nix

@@ -0,0 +1,21 @@
+{
+  buildPythonPackage,
+  poetry-core,
+  huggingface-hub,
+  pydantic,
+}:
+
+buildPythonPackage {
+  name = "text-generation";
+
+  src = ../clients/python;
+
+  pyproject = true;
+
+  build-system = [ poetry-core ];
+
+  dependencies = [
+    huggingface-hub
+    pydantic
+  ];
+}