From 03274418c7c27c8c25f232b45d1ab039c5f1c2c5 Mon Sep 17 00:00:00 2001 From: paulb-seldon <141156400+paulb-seldon@users.noreply.github.com> Date: Thu, 8 Feb 2024 10:10:52 +0000 Subject: [PATCH 1/4] Update v2-protocol.md --- doc/source/reference/apis/v2-protocol.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/doc/source/reference/apis/v2-protocol.md b/doc/source/reference/apis/v2-protocol.md index 3ae11aeeb5..4b17a2f163 100644 --- a/doc/source/reference/apis/v2-protocol.md +++ b/doc/source/reference/apis/v2-protocol.md @@ -1,18 +1,18 @@ -# V2 Inference Protocol +# Open Inference Protocol -The V2 Inference Protocol is an industry-wide effort to provide an standardised +The Open Inference Protocol is an industry-wide effort to provide a standardized protocol to communicate with different inference servers (e.g. MLServer, Triton, etc.) and orchestrating frameworks (e.g. Seldon Core, KServe, etc.). -The spec of the V2 Inference Protocol defines both the endpoints and payload +The spec of the Open Inference Protocol defines both the endpoints and payload schemas for REST and gRPC interfaces. -As part of the V2 Protocol definition, you can find dedicated endpoints for: +As part of the Open Inference Protocol definition, you can find dedicated endpoints to: -- Health endpoints, to assess liveness and readiness of your model. -- Inference endpoints, to interact with your model. -- Metadata endpoints, to query your model metadata (e.g. expected inputs, expected +- Assess liveness and readiness of your model. +- Interact with your model. +- Query your model metadata (e.g. expected inputs, expected outputs, etc.). -- Model repository endpoints, to load and unload models dynamically. +- Load and unload models dynamically. ## REST From 8a594bb63e020287b4ac0f4ed24e030c4ab56320 Mon Sep 17 00:00:00 2001 From: paulb-seldon <141156400+paulb-seldon@users.noreply.github.com> Date: Thu, 8 Feb 2024 11:05:34 +0000 Subject: [PATCH 2/4] Add back endpoint categories for clarity --- doc/source/reference/apis/v2-protocol.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/doc/source/reference/apis/v2-protocol.md b/doc/source/reference/apis/v2-protocol.md index 4b17a2f163..471a6248a7 100644 --- a/doc/source/reference/apis/v2-protocol.md +++ b/doc/source/reference/apis/v2-protocol.md @@ -8,11 +8,10 @@ schemas for REST and gRPC interfaces. As part of the Open Inference Protocol definition, you can find dedicated endpoints to: -- Assess liveness and readiness of your model. -- Interact with your model. -- Query your model metadata (e.g. expected inputs, expected +- Health: Assess liveness and readiness of your model. +- Model controls: Interact with your model, load and unload models dynamically +- Metadata: Query your model metadata (e.g. expected inputs, expected outputs, etc.). -- Load and unload models dynamically. ## REST From 7984dee0c984c38c95a35c54c2ecf035dacf472b Mon Sep 17 00:00:00 2001 From: paulb-seldon <141156400+paulb-seldon@users.noreply.github.com> Date: Thu, 8 Feb 2024 11:06:06 +0000 Subject: [PATCH 3/4] Grammar --- doc/source/reference/apis/v2-protocol.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/reference/apis/v2-protocol.md b/doc/source/reference/apis/v2-protocol.md index 471a6248a7..0fdb9831b1 100644 --- a/doc/source/reference/apis/v2-protocol.md +++ b/doc/source/reference/apis/v2-protocol.md @@ -6,7 +6,7 @@ Triton, etc.) and orchestrating frameworks (e.g. Seldon Core, KServe, etc.). The spec of the Open Inference Protocol defines both the endpoints and payload schemas for REST and gRPC interfaces. -As part of the Open Inference Protocol definition, you can find dedicated endpoints to: +As part of the Open Inference Protocol definition, you can find dedicated endpoints for: - Health: Assess liveness and readiness of your model. - Model controls: Interact with your model, load and unload models dynamically From fd5c0ab80302d6dc68f3f7706b7826ce060666d4 Mon Sep 17 00:00:00 2001 From: paulb-seldon <141156400+paulb-seldon@users.noreply.github.com> Date: Thu, 8 Feb 2024 11:28:12 +0000 Subject: [PATCH 4/4] Add model inference under endpoints --- doc/source/reference/apis/v2-protocol.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/reference/apis/v2-protocol.md b/doc/source/reference/apis/v2-protocol.md index 0fdb9831b1..ca6016e8fc 100644 --- a/doc/source/reference/apis/v2-protocol.md +++ b/doc/source/reference/apis/v2-protocol.md @@ -8,8 +8,8 @@ schemas for REST and gRPC interfaces. As part of the Open Inference Protocol definition, you can find dedicated endpoints for: +- Model controls: Call model inference, interact with your model, and load and unload models dynamically - Health: Assess liveness and readiness of your model. -- Model controls: Interact with your model, load and unload models dynamically - Metadata: Query your model metadata (e.g. expected inputs, expected outputs, etc.).