fix: do not automatically set latest

Author: OlivierDehaene

.github/workflows/build_75.yaml

@@ -108,6 +108,8 @@
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern=turing-{{version}}
              type=semver,pattern=turing-{{major}}.{{minor}}

.github/workflows/build_80.yaml

@@ -105,11 +105,11 @@
          id: meta-80
          uses: docker/metadata-action@v4.3.0
          with:
-           flavor: |
-             latest=auto
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern={{version}}
              type=semver,pattern={{major}}.{{minor}}

.github/workflows/build_86.yaml

@@ -108,6 +108,8 @@
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern=86-{{version}}
              type=semver,pattern=86-{{major}}.{{minor}}

.github/workflows/build_89.yaml

@@ -108,6 +108,8 @@
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern=89-{{version}}
              type=semver,pattern=89-{{major}}.{{minor}}

.github/workflows/build_90.yaml

@@ -108,6 +108,8 @@
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern=hopper-{{version}}
              type=semver,pattern=hopper-{{major}}.{{minor}}

.github/workflows/build_cpu.yaml

@@ -108,6 +108,8 @@
            images: |
              registry.internal.huggingface.tech/api-inference/text-embeddings-inference
              ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
            tags: |
              type=semver,pattern=cpu-{{version}}
              type=semver,pattern=cpu-{{major}}.{{minor}}

README.md

@@ -81,7 +81,7 @@ model=BAAI/bge-large-en-v1.5
 revision=refs/pr/5
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 
-docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:latest --model-id $model --revision $revision
+docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.2.2 --model-id $model --revision $revision
 ```
 
 And then you can make requests like
@@ -223,15 +223,15 @@ Options:
 
 Text Embeddings Inference ships with multiple Docker images that you can use to target a specific backend:
 
-| Architecture                        | Image                                                       |
-|-------------------------------------|-------------------------------------------------------------|
-| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-latest    |
-| Volta                               | NOT SUPPORTED                                               |
-| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-latest |
-| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:latest        |
-| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-latest     |
-| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-latest     |
-| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-latest |
+| Architecture                        | Image                                                      |
+|-------------------------------------|------------------------------------------------------------|
+| CPU                                 | ghcr.io/huggingface/text-embeddings-inference:cpu-0.2.2    |
+| Volta                               | NOT SUPPORTED                                              |
+| Turing (T4, RTX 2000 series, ...)   | ghcr.io/huggingface/text-embeddings-inference:turing-0.2.2 |
+| Ampere 80 (A100, A30)               | ghcr.io/huggingface/text-embeddings-inference:0.2.2        |
+| Ampere 86 (A10, A40, ...)           | ghcr.io/huggingface/text-embeddings-inference:86-0.2.2     |
+| Ada Lovelace (RTX 4000 series, ...) | ghcr.io/huggingface/text-embeddings-inference:89-0.2.2     |
+| Hopper (H100)                       | ghcr.io/huggingface/text-embeddings-inference:hopper-0.2.2 |
 
 ### API documentation
 
@@ -256,7 +256,7 @@ model=<your private model>
 volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
 token=<your cli READ token>
 
-docker run --gpus all -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:latest --model-id $model
+docker run --gpus all -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.2.2 --model-id $model
 ```
 
 ### Distributed Tracing