[docs] added the script and the complete output

docs-gb/SUMMARY.md

@@ -51,3 +51,102 @@
   * [Deploying a Custom Tensorflow Model with MLServer and Seldon Core](examples/cassava/README.md)
 * [Changelog](changelog.md)
 * [Release Notes](https://github.com/SeldonIO/MLServer/releases)
+
+## Reference
+
+* [API Reference](api/index.md)
+  * [mlserver](api/mlserver.md)
+  * [mlserver.batching](api/mlserver/batching.md)
+  * [mlserver.batching.adaptive](api/mlserver/batching/adaptive.md)
+  * [mlserver.batching.hooks](api/mlserver/batching/hooks.md)
+  * [mlserver.batching.requests](api/mlserver/batching/requests.md)
+  * [mlserver.batching.shape](api/mlserver/batching/shape.md)
+  * [mlserver.cache](api/mlserver/cache.md)
+  * [mlserver.cache.cache](api/mlserver/cache/cache.md)
+  * [mlserver.cache.local](api/mlserver/cache/local.md)
+  * [mlserver.cache.local.local](api/mlserver/cache/local/local.md)
+  * [mlserver.cloudevents](api/mlserver/cloudevents.md)
+  * [mlserver.codecs](api/mlserver/codecs.md)
+  * [mlserver.codecs.base](api/mlserver/codecs/base.md)
+  * [mlserver.codecs.base64](api/mlserver/codecs/base64.md)
+  * [mlserver.codecs.datetime](api/mlserver/codecs/datetime.md)
+  * [mlserver.codecs.decorator](api/mlserver/codecs/decorator.md)
+  * [mlserver.codecs.errors](api/mlserver/codecs/errors.md)
+  * [mlserver.codecs.json](api/mlserver/codecs/json.md)
+  * [mlserver.codecs.lists](api/mlserver/codecs/lists.md)
+  * [mlserver.codecs.numpy](api/mlserver/codecs/numpy.md)
+  * [mlserver.codecs.pandas](api/mlserver/codecs/pandas.md)
+  * [mlserver.codecs.string](api/mlserver/codecs/string.md)
+  * [mlserver.codecs.utils](api/mlserver/codecs/utils.md)
+  * [mlserver.context](api/mlserver/context.md)
+  * [mlserver.env](api/mlserver/env.md)
+  * [mlserver.errors](api/mlserver/errors.md)
+  * [mlserver.grpc](api/mlserver/grpc.md)
+  * [mlserver.grpc.converters](api/mlserver/grpc/converters.md)
+  * [mlserver.grpc.dataplane_pb2](api/mlserver/grpc/dataplane_pb2.md)
+  * [mlserver.grpc.dataplane_pb2_grpc](api/mlserver/grpc/dataplane_pb2_grpc.md)
+  * [mlserver.grpc.interceptors](api/mlserver/grpc/interceptors.md)
+  * [mlserver.grpc.logging](api/mlserver/grpc/logging.md)
+  * [mlserver.grpc.model_repository](api/mlserver/grpc/model_repository.md)
+  * [mlserver.grpc.model_repository_pb2](api/mlserver/grpc/model_repository_pb2.md)
+  * [mlserver.grpc.model_repository_pb2_grpc](api/mlserver/grpc/model_repository_pb2_grpc.md)
+  * [mlserver.grpc.server](api/mlserver/grpc/server.md)
+  * [mlserver.grpc.servicers](api/mlserver/grpc/servicers.md)
+  * [mlserver.grpc.utils](api/mlserver/grpc/utils.md)
+  * [mlserver.handlers](api/mlserver/handlers.md)
+  * [mlserver.handlers.custom](api/mlserver/handlers/custom.md)
+  * [mlserver.handlers.dataplane](api/mlserver/handlers/dataplane.md)
+  * [mlserver.handlers.model_repository](api/mlserver/handlers/model_repository.md)
+  * [mlserver.kafka](api/mlserver/kafka.md)
+  * [mlserver.kafka.errors](api/mlserver/kafka/errors.md)
+  * [mlserver.kafka.handlers](api/mlserver/kafka/handlers.md)
+  * [mlserver.kafka.logging](api/mlserver/kafka/logging.md)
+  * [mlserver.kafka.message](api/mlserver/kafka/message.md)
+  * [mlserver.kafka.server](api/mlserver/kafka/server.md)
+  * [mlserver.logging](api/mlserver/logging.md)
+  * [mlserver.metrics](api/mlserver/metrics.md)
+  * [mlserver.metrics.context](api/mlserver/metrics/context.md)
+  * [mlserver.metrics.errors](api/mlserver/metrics/errors.md)
+  * [mlserver.metrics.logging](api/mlserver/metrics/logging.md)
+  * [mlserver.metrics.prometheus](api/mlserver/metrics/prometheus.md)
+  * [mlserver.metrics.registry](api/mlserver/metrics/registry.md)
+  * [mlserver.metrics.server](api/mlserver/metrics/server.md)
+  * [mlserver.middleware](api/mlserver/middleware.md)
+  * [mlserver.model](api/mlserver/model.md)
+  * [mlserver.parallel](api/mlserver/parallel.md)
+  * [mlserver.parallel.dispatcher](api/mlserver/parallel/dispatcher.md)
+  * [mlserver.parallel.errors](api/mlserver/parallel/errors.md)
+  * [mlserver.parallel.logging](api/mlserver/parallel/logging.md)
+  * [mlserver.parallel.messages](api/mlserver/parallel/messages.md)
+  * [mlserver.parallel.model](api/mlserver/parallel/model.md)
+  * [mlserver.parallel.pool](api/mlserver/parallel/pool.md)
+  * [mlserver.parallel.registry](api/mlserver/parallel/registry.md)
+  * [mlserver.parallel.utils](api/mlserver/parallel/utils.md)
+  * [mlserver.parallel.worker](api/mlserver/parallel/worker.md)
+  * [mlserver.raw](api/mlserver/raw.md)
+  * [mlserver.registry](api/mlserver/registry.md)
+  * [mlserver.repository](api/mlserver/repository.md)
+  * [mlserver.repository.factory](api/mlserver/repository/factory.md)
+  * [mlserver.repository.load](api/mlserver/repository/load.md)
+  * [mlserver.repository.repository](api/mlserver/repository/repository.md)
+  * [mlserver.rest](api/mlserver/rest.md)
+  * [mlserver.rest.app](api/mlserver/rest/app.md)
+  * [mlserver.rest.endpoints](api/mlserver/rest/endpoints.md)
+  * [mlserver.rest.errors](api/mlserver/rest/errors.md)
+  * [mlserver.rest.logging](api/mlserver/rest/logging.md)
+  * [mlserver.rest.openapi](api/mlserver/rest/openapi.md)
+  * [mlserver.rest.openapi.schema](api/mlserver/rest/openapi/schema.md)
+  * [mlserver.rest.requests](api/mlserver/rest/requests.md)
+  * [mlserver.rest.responses](api/mlserver/rest/responses.md)
+  * [mlserver.rest.server](api/mlserver/rest/server.md)
+  * [mlserver.rest.utils](api/mlserver/rest/utils.md)
+  * [mlserver.server](api/mlserver/server.md)
+  * [mlserver.settings](api/mlserver/settings.md)
+  * [mlserver.tracing](api/mlserver/tracing.md)
+  * [mlserver.types](api/mlserver/types.md)
+  * [mlserver.types.base](api/mlserver/types/base.md)
+  * [mlserver.types.dataplane](api/mlserver/types/dataplane.md)
+  * [mlserver.types.model_repository](api/mlserver/types/model_repository.md)
+  * [mlserver.utils](api/mlserver/utils.md)
+  * [mlserver.version](api/mlserver/version.md)
+

docs-gb/api/SUMMARY.md

@@ -0,0 +1,97 @@
+# Summary
+* [Home](README.md)
+* [API Reference](api/index.md)
+  * [mlserver](api/mlserver.md)
+  * [mlserver.batching](api/mlserver/batching.md)
+  * [mlserver.batching.adaptive](api/mlserver/batching/adaptive.md)
+  * [mlserver.batching.hooks](api/mlserver/batching/hooks.md)
+  * [mlserver.batching.requests](api/mlserver/batching/requests.md)
+  * [mlserver.batching.shape](api/mlserver/batching/shape.md)
+  * [mlserver.cache](api/mlserver/cache.md)
+  * [mlserver.cache.cache](api/mlserver/cache/cache.md)
+  * [mlserver.cache.local](api/mlserver/cache/local.md)
+  * [mlserver.cache.local.local](api/mlserver/cache/local/local.md)
+  * [mlserver.cloudevents](api/mlserver/cloudevents.md)
+  * [mlserver.codecs](api/mlserver/codecs.md)
+  * [mlserver.codecs.base](api/mlserver/codecs/base.md)
+  * [mlserver.codecs.base64](api/mlserver/codecs/base64.md)
+  * [mlserver.codecs.datetime](api/mlserver/codecs/datetime.md)
+  * [mlserver.codecs.decorator](api/mlserver/codecs/decorator.md)
+  * [mlserver.codecs.errors](api/mlserver/codecs/errors.md)
+  * [mlserver.codecs.json](api/mlserver/codecs/json.md)
+  * [mlserver.codecs.lists](api/mlserver/codecs/lists.md)
+  * [mlserver.codecs.numpy](api/mlserver/codecs/numpy.md)
+  * [mlserver.codecs.pandas](api/mlserver/codecs/pandas.md)
+  * [mlserver.codecs.string](api/mlserver/codecs/string.md)
+  * [mlserver.codecs.utils](api/mlserver/codecs/utils.md)
+  * [mlserver.context](api/mlserver/context.md)
+  * [mlserver.env](api/mlserver/env.md)
+  * [mlserver.errors](api/mlserver/errors.md)
+  * [mlserver.grpc](api/mlserver/grpc.md)
+  * [mlserver.grpc.converters](api/mlserver/grpc/converters.md)
+  * [mlserver.grpc.dataplane_pb2](api/mlserver/grpc/dataplane_pb2.md)
+  * [mlserver.grpc.dataplane_pb2_grpc](api/mlserver/grpc/dataplane_pb2_grpc.md)
+  * [mlserver.grpc.interceptors](api/mlserver/grpc/interceptors.md)
+  * [mlserver.grpc.logging](api/mlserver/grpc/logging.md)
+  * [mlserver.grpc.model_repository](api/mlserver/grpc/model_repository.md)
+  * [mlserver.grpc.model_repository_pb2](api/mlserver/grpc/model_repository_pb2.md)
+  * [mlserver.grpc.model_repository_pb2_grpc](api/mlserver/grpc/model_repository_pb2_grpc.md)
+  * [mlserver.grpc.server](api/mlserver/grpc/server.md)
+  * [mlserver.grpc.servicers](api/mlserver/grpc/servicers.md)
+  * [mlserver.grpc.utils](api/mlserver/grpc/utils.md)
+  * [mlserver.handlers](api/mlserver/handlers.md)
+  * [mlserver.handlers.custom](api/mlserver/handlers/custom.md)
+  * [mlserver.handlers.dataplane](api/mlserver/handlers/dataplane.md)
+  * [mlserver.handlers.model_repository](api/mlserver/handlers/model_repository.md)
+  * [mlserver.kafka](api/mlserver/kafka.md)
+  * [mlserver.kafka.errors](api/mlserver/kafka/errors.md)
+  * [mlserver.kafka.handlers](api/mlserver/kafka/handlers.md)
+  * [mlserver.kafka.logging](api/mlserver/kafka/logging.md)
+  * [mlserver.kafka.message](api/mlserver/kafka/message.md)
+  * [mlserver.kafka.server](api/mlserver/kafka/server.md)
+  * [mlserver.logging](api/mlserver/logging.md)
+  * [mlserver.metrics](api/mlserver/metrics.md)
+  * [mlserver.metrics.context](api/mlserver/metrics/context.md)
+  * [mlserver.metrics.errors](api/mlserver/metrics/errors.md)
+  * [mlserver.metrics.logging](api/mlserver/metrics/logging.md)
+  * [mlserver.metrics.prometheus](api/mlserver/metrics/prometheus.md)
+  * [mlserver.metrics.registry](api/mlserver/metrics/registry.md)
+  * [mlserver.metrics.server](api/mlserver/metrics/server.md)
+  * [mlserver.middleware](api/mlserver/middleware.md)
+  * [mlserver.model](api/mlserver/model.md)
+  * [mlserver.parallel](api/mlserver/parallel.md)
+  * [mlserver.parallel.dispatcher](api/mlserver/parallel/dispatcher.md)
+  * [mlserver.parallel.errors](api/mlserver/parallel/errors.md)
+  * [mlserver.parallel.logging](api/mlserver/parallel/logging.md)
+  * [mlserver.parallel.messages](api/mlserver/parallel/messages.md)
+  * [mlserver.parallel.model](api/mlserver/parallel/model.md)
+  * [mlserver.parallel.pool](api/mlserver/parallel/pool.md)
+  * [mlserver.parallel.registry](api/mlserver/parallel/registry.md)
+  * [mlserver.parallel.utils](api/mlserver/parallel/utils.md)
+  * [mlserver.parallel.worker](api/mlserver/parallel/worker.md)
+  * [mlserver.raw](api/mlserver/raw.md)
+  * [mlserver.registry](api/mlserver/registry.md)
+  * [mlserver.repository](api/mlserver/repository.md)
+  * [mlserver.repository.factory](api/mlserver/repository/factory.md)
+  * [mlserver.repository.load](api/mlserver/repository/load.md)
+  * [mlserver.repository.repository](api/mlserver/repository/repository.md)
+  * [mlserver.rest](api/mlserver/rest.md)
+  * [mlserver.rest.app](api/mlserver/rest/app.md)
+  * [mlserver.rest.endpoints](api/mlserver/rest/endpoints.md)
+  * [mlserver.rest.errors](api/mlserver/rest/errors.md)
+  * [mlserver.rest.logging](api/mlserver/rest/logging.md)
+  * [mlserver.rest.openapi](api/mlserver/rest/openapi.md)
+  * [mlserver.rest.openapi.schema](api/mlserver/rest/openapi/schema.md)
+  * [mlserver.rest.requests](api/mlserver/rest/requests.md)
+  * [mlserver.rest.responses](api/mlserver/rest/responses.md)
+  * [mlserver.rest.server](api/mlserver/rest/server.md)
+  * [mlserver.rest.utils](api/mlserver/rest/utils.md)
+  * [mlserver.server](api/mlserver/server.md)
+  * [mlserver.settings](api/mlserver/settings.md)
+  * [mlserver.tracing](api/mlserver/tracing.md)
+  * [mlserver.types](api/mlserver/types.md)
+  * [mlserver.types.base](api/mlserver/types/base.md)
+  * [mlserver.types.dataplane](api/mlserver/types/dataplane.md)
+  * [mlserver.types.model_repository](api/mlserver/types/model_repository.md)
+  * [mlserver.utils](api/mlserver/utils.md)
+  * [mlserver.version](api/mlserver/version.md)

docs-gb/api/index.md

@@ -0,0 +1,2 @@
+# API Reference
+

docs-gb/api/mlserver.md

@@ -0,0 +1,2 @@
+# Module `mlserver`
+

docs-gb/api/mlserver/batching.md

@@ -0,0 +1,2 @@
+# Module `mlserver.batching`
+

docs-gb/api/mlserver/batching/adaptive.md

@@ -0,0 +1,17 @@
+# Module `mlserver.batching.adaptive`
+
+
+## Class `AdaptiveBatcher`
+
+
+**Description:**
+*No docstring available.*
+
+### Method `predict`
+
+
+**Signature:** `predict(self, req: 'InferenceRequest') -> 'InferenceResponse'`
+
+
+**Description:**
+*No docstring available.*

docs-gb/api/mlserver/batching/hooks.md

@@ -0,0 +1,37 @@
+# Module `mlserver.batching.hooks`
+
+
+## Class `InvalidBatchingMethod`
+
+
+**Description:**
+Common base class for all non-exit exceptions.
+
+## Function `adaptive_batching`
+
+
+**Signature:** `adaptive_batching(f: Callable[[mlserver.types.dataplane.InferenceRequest], Awaitable[mlserver.types.dataplane.InferenceResponse]])`
+
+
+**Description:**
+Decorator for the `predict()` method which will ensure it uses the
+underlying adaptive batcher instance.
+
+## Function `load_batching`
+
+
+**Signature:** `load_batching(model: mlserver.model.MLModel) -> mlserver.model.MLModel`
+
+
+**Description:**
+*No docstring available.*
+
+## Function `not_implemented_warning`
+
+
+**Signature:** `not_implemented_warning(f: Callable[[AsyncIterator[mlserver.types.dataplane.InferenceRequest]], AsyncIterator[mlserver.types.dataplane.InferenceResponse]])`
+
+
+**Description:**
+Decorator to lets users know that adaptive batching is not required on
+method `f`.

docs-gb/api/mlserver/batching/requests.md

@@ -0,0 +1,17 @@
+# Module `mlserver.batching.requests`
+
+
+## Class `BatchedRequests`
+
+
+**Description:**
+*No docstring available.*
+
+### Method `split_response`
+
+
+**Signature:** `split_response(self, batched_response: mlserver.types.dataplane.InferenceResponse) -> Dict[str, mlserver.types.dataplane.InferenceResponse]`
+
+
+**Description:**
+*No docstring available.*

docs-gb/api/mlserver/batching/shape.md

@@ -0,0 +1,26 @@
+# Module `mlserver.batching.shape`
+
+
+## Class `Shape`
+
+
+**Description:**
+Helper class to manipulate shapes.
+
+### Method `copy`
+
+
+**Signature:** `copy(self) -> 'Shape'`
+
+
+**Description:**
+*No docstring available.*
+
+### Method `to_list`
+
+
+**Signature:** `to_list(self) -> List[int]`
+
+
+**Description:**
+*No docstring available.*

docs-gb/api/mlserver/cache.md

@@ -0,0 +1,2 @@
+# Module `mlserver.cache`
+

docs-gb/api/mlserver/cache/cache.md

@@ -0,0 +1,38 @@
+# Module `mlserver.cache.cache`
+
+
+## Class `ResponseCache`
+
+
+**Description:**
+*No docstring available.*
+
+### Method `insert`
+
+
+**Signature:** `insert(self, key: str, value: str)`
+
+
+**Description:**
+Method responsible for inserting value to cache.
+**This method should be overriden to implement your custom cache logic.**
+
+### Method `lookup`
+
+
+**Signature:** `lookup(self, key: str) -> str`
+
+
+**Description:**
+Method responsible for returning key value in the cache.
+**This method should be overriden to implement your custom cache logic.**
+
+### Method `size`
+
+
+**Signature:** `size(self) -> int`
+
+
+**Description:**
+Method responsible for returning the size of the cache.
+**This method should be overriden to implement your custom cache logic.**

docs-gb/api/mlserver/cache/local.md

@@ -0,0 +1,2 @@
+# Module `mlserver.cache.local`
+

docs-gb/api/mlserver/cache/local/local.md

@@ -0,0 +1,38 @@
+# Module `mlserver.cache.local.local`
+
+
+## Class `LocalCache`
+
+
+**Description:**
+*No docstring available.*
+
+### Method `insert`
+
+
+**Signature:** `insert(self, key: str, value: str)`
+
+
+**Description:**
+Method responsible for inserting value to cache.
+**This method should be overriden to implement your custom cache logic.**
+
+### Method `lookup`
+
+
+**Signature:** `lookup(self, key: str) -> str`
+
+
+**Description:**
+Method responsible for returning key value in the cache.
+**This method should be overriden to implement your custom cache logic.**
+
+### Method `size`
+
+
+**Signature:** `size(self) -> int`
+
+
+**Description:**
+Method responsible for returning the size of the cache.
+**This method should be overriden to implement your custom cache logic.**