GCO Inference Proxy API — API spec sheet¶
Service inference-proxy · OpenAPI 3.1.0 · API version 1.0.0 · 9 endpoints · 2 schemas
Authenticated streaming reverse proxy for managed GCO inference endpoints
- Machine-readable document:
docs/openapi/inference-proxy.json— the FastAPIapp.openapi()export (scripts/generate_openapi.py) this sheet is rendered from - Interactive console (Swagger UI): https://aws-solutions-library-samples.github.io/global-capacity-orchestrator-on-aws/swagger/inference-proxy/
- Catalogue index: README.md · interaction diagram
Endpoints¶
| Method | Path | Summary | Tags |
|---|---|---|---|
GET |
/ |
Root | Info |
GET |
/healthz |
Kubernetes Health Check | Health |
GET |
/inference/{endpoint_name} |
Proxy Inference Root | Inference |
POST |
/inference/{endpoint_name} |
Proxy Inference Root | Inference |
HEAD |
/inference/{endpoint_name} |
Proxy Inference Root | Inference |
GET |
/inference/{endpoint_name}/{upstream_path} |
Proxy Inference Path | Inference |
POST |
/inference/{endpoint_name}/{upstream_path} |
Proxy Inference Path | Inference |
HEAD |
/inference/{endpoint_name}/{upstream_path} |
Proxy Inference Path | Inference |
GET |
/readyz |
Kubernetes Readiness Check | Health |
Endpoint details¶
GET /¶
Return a small authenticated service descriptor.
- Operation ID:
root__get - Tags: Info
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: object (free-form) |
GET /healthz¶
Kubernetes and ALB liveness probe.
- Operation ID:
kubernetes_health_check_healthz_get - Tags: Health
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: object of string |
GET /inference/{endpoint_name}¶
Proxy an endpoint-root request after platform authentication.
- Operation ID:
proxy_inference_root_inference__endpoint_name__get - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
POST /inference/{endpoint_name}¶
Proxy an endpoint-root request after platform authentication.
- Operation ID:
proxy_inference_root_inference__endpoint_name__post - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
HEAD /inference/{endpoint_name}¶
Proxy an endpoint-root request after platform authentication.
- Operation ID:
proxy_inference_root_inference__endpoint_name__head - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
GET /inference/{endpoint_name}/{upstream_path}¶
Proxy an endpoint sub-path after platform authentication.
- Operation ID:
proxy_inference_path_inference__endpoint_name___upstream_path__get - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
upstream_path |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
POST /inference/{endpoint_name}/{upstream_path}¶
Proxy an endpoint sub-path after platform authentication.
- Operation ID:
proxy_inference_path_inference__endpoint_name___upstream_path__post - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
upstream_path |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
HEAD /inference/{endpoint_name}/{upstream_path}¶
Proxy an endpoint sub-path after platform authentication.
- Operation ID:
proxy_inference_path_inference__endpoint_name___upstream_path__head - Tags: Inference
Parameters
| Name | In | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|---|
endpoint_name |
path | string | yes | — | — | — |
upstream_path |
path | string | yes | — | — | — |
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: any |
422 |
Validation Error | application/json: HTTPValidationError |
GET /readyz¶
Readiness probe; external dependencies are resolved per request.
- Operation ID:
kubernetes_readiness_check_readyz_get - Tags: Health
Responses
| Status | Description | Content |
|---|---|---|
200 |
Successful Response | application/json: object of string |
Schemas¶
HTTPValidationError¶
| Property | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|
detail |
array of ValidationError |
no | — | — | — |
ValidationError¶
| Property | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|
ctx |
object | no | — | — | — |
input |
any | no | — | — | — |
loc |
array of string or integer | yes | — | — | — |
msg |
string | yes | — | — | — |
type |
string | yes | — | — | — |