# Seldon Core 2 ## latest - [Production-ready ML Serving Framework](https://docs.seldon.ai/seldon-core-2/about/readme.md): Discover Seldon Core 2, a Kubernetes-native MLOps framework for deploying ML and LLM systems at scale. Features flexible architecture, standardized workflows, and enhanced observability. - [Seldon Core Features](https://docs.seldon.ai/seldon-core-2/about/core-features.md): Explore the enterprise MLOps capabilities of Core 2 for production ML deployment, featuring model serving, pipeline orchestration, and intelligent resource management for scalable ML systems. - [Concepts](https://docs.seldon.ai/seldon-core-2/about/concepts.md): Learn how Seldon Core is different from a centralized orchestrator to a data flow architecture, enabling more efficient ML model deployment through stream processing and improved data handling. - [Architecture](https://docs.seldon.ai/seldon-core-2/about/architecture.md): Learn about the Seldon Core 2 microservice architecture, control plane and data plane components, and how these services work to provide a scalable, fault-tolerant ML model serving and management. - [Installation Overview](https://docs.seldon.ai/seldon-core-2/installation/installation.md): Learn how to install Seldon Core 2 in various environments - from local development with Docker Compose to production-grade Kubernetes clusters. - [Learning Environment](https://docs.seldon.ai/seldon-core-2/installation/learning-environment.md): Install Seldon Core 2 in a local learning environment. - [Self-hosted Kafka](https://docs.seldon.ai/seldon-core-2/installation/learning-environment/self-hosted-kafka.md): Learn how to set up a self-hosted Kafka cluster for Seldon Core in development and learning environments. - [Production Environment](https://docs.seldon.ai/seldon-core-2/installation/production-environment.md): Install Core 2 in a production Kubernetes environment. - [Kafka Integration](https://docs.seldon.ai/seldon-core-2/installation/production-environment/kafka.md): Learn how to set up and configure Kafka for Seldon Core in production environments, including cluster setup and security configuration. - [Managed Kafka](https://docs.seldon.ai/seldon-core-2/installation/production-environment/managed-kafka.md): Guide to integrating managed Kafka services (Confluent Cloud, Amazon MSK, Azure Event Hub) with Seldon Core 2, including security configurations and authentication setup. - [Ingress Controller](https://docs.seldon.ai/seldon-core-2/installation/production-environment/istio.md): Learn how to configure Istio as an ingress controller for Seldon Core, including traffic management and security policies. - [Test the Installation](https://docs.seldon.ai/seldon-core-2/installation/test-installation.md): Learn how to verify your Seldon Core installation by running tests and checking component functionality. - [Advanced Configurations](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations.md): Advanced Configurations in Seldon Core 2. - [Helm Configuration](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/helm.md): Learn how to install and configure Seldon Core using Helm charts, including component setup and customization options. - [Server Config](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/serverconfig.md): Server Config in Seldon Core 2. - [Server Runtime](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/seldonruntime.md): Learn about SeldonRuntime, a Kubernetes resource for creating and managing Seldon Core instances in specific namespaces with configurable settings. - [Seldon Config](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/seldonconfig.md): Learn how to configure Seldon Core installation components using SeldonConfig resource, including component specifications, Kafka settings, and tracing configuration. - [Pipeline Config](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/pipeline.md): Learn how to create and manage ML pipelines in Seldon Core using Kubernetes custom resources, including model chaining and tensor mapping. - [Managing Kafka Topics](https://docs.seldon.ai/seldon-core-2/installation/advanced-configurations/managing-kafka-topics.md): Learn how to manage Kafka topics in Seldon Core 2, including topic creation, configuration, and monitoring for model inference and event streaming. - [Upgrading](https://docs.seldon.ai/seldon-core-2/installation/upgrading.md): Learn about upgrading to the latest versions of Seldon Core 2. - [Quickstart](https://docs.seldon.ai/seldon-core-2/user-guide/quickstart.md): Learn how to deploy an AI application with Seldon Core 2. - [Kubernetes Resources](https://docs.seldon.ai/seldon-core-2/user-guide/resources.md): Learn about the Kubernetes Resources offered by Seldon Core 2. - [Servers](https://docs.seldon.ai/seldon-core-2/user-guide/servers.md): Learn how to configure and manage inference servers in Seldon Core 2, including MLServer and Triton server farms, model scheduling, and capability management. - [Resource allocation](https://docs.seldon.ai/seldon-core-2/user-guide/servers/resource-allocation.md): Learn more about using taints and tolerations with node affinity or node selector to allocate resources in a Kubernetes cluster. - [Example: Serving models on dedicated GPU nodes](https://docs.seldon.ai/seldon-core-2/user-guide/servers/resource-allocation/example-serving-models-on-dedicated-gpu-nodes.md): This example illustrates how to use taints, tolerations with nodeAffinity or nodeSelector to assign GPU nodes to specific models. - [Models](https://docs.seldon.ai/seldon-core-2/user-guide/models.md): Models in Seldon Core 2. - [Multi-Model Serving](https://docs.seldon.ai/seldon-core-2/user-guide/models/mms.md): Learn how to configure multi-model serving in Seldon Core, including resource optimization and model co-location. - [Inference Artifacts](https://docs.seldon.ai/seldon-core-2/user-guide/models/inference-artifacts.md): Learn how to manage model artifacts in Seldon Core, including storage, versioning, and deployment workflows. - [Scheduling](https://docs.seldon.ai/seldon-core-2/user-guide/models/scheduling.md): Learn how to configure model scheduling in Seldon Core, including resource allocation, scaling policies, and deployment strategies. - [rClone](https://docs.seldon.ai/seldon-core-2/user-guide/models/rclone.md): Learn how to configure and use Rclone for model artifact storage in Seldon Core, including cloud storage integration and authentication. - [Parameterized Models](https://docs.seldon.ai/seldon-core-2/user-guide/models/parameterized-models.md): Parameterized Models in Seldon Core 2. - [Pandas Query](https://docs.seldon.ai/seldon-core-2/user-guide/models/pandasquery.md): Learn how to use PandasQuery for data transformation in Seldon Core, including query configuration and parameter handling. - [Storage Secrets](https://docs.seldon.ai/seldon-core-2/user-guide/models/storage-secrets.md): Learn how to configure storage secrets in Seldon Core 2 for secure model artifact access using Rclone, including AWS S3, GCS, and MinIO integration. - [Inference](https://docs.seldon.ai/seldon-core-2/user-guide/inference.md): Inference in Seldon Core 2. - [Inference Server](https://docs.seldon.ai/seldon-core-2/user-guide/inference/inference.md): Learn how to perform model inference in Seldon Core using REST and gRPC protocols, including request/response formats and client examples. - [Run Inference](https://docs.seldon.ai/seldon-core-2/user-guide/inference/inference-1.md) - [Batch](https://docs.seldon.ai/seldon-core-2/user-guide/inference/batch-examples-k8s.md) - [Open Inference Protocol](https://docs.seldon.ai/seldon-core-2/user-guide/v2.md): Open Inference Protocol in Seldon Core 2. - [REST](https://docs.seldon.ai/seldon-core-2/user-guide/v2/rest.md): REST in Seldon Core 2. - [Health](https://docs.seldon.ai/seldon-core-2/user-guide/v2/rest/health.md) - [Inference](https://docs.seldon.ai/seldon-core-2/user-guide/v2/rest/inference.md) - [Metadata](https://docs.seldon.ai/seldon-core-2/user-guide/v2/rest/metadata.md) - [Models](https://docs.seldon.ai/seldon-core-2/user-guide/v2/rest/models.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/user-guide/pipelines.md): Learn how to create and manage ML inference pipelines in Seldon Core, including model chaining, tensor mapping, and conditional logic. - [Autoscaling](https://docs.seldon.ai/seldon-core-2/user-guide/scaling.md) - [Seldon Core Autoscaling](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/core-autoscaling.md): Autoscaling with Seldon Core 2. - [Autoscaling Models](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/core-autoscaling/core-autoscaling-models.md): Learn how to leverage Core 2's native autoscaling functionality for Models - [Autoscaling Servers](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/core-autoscaling/core-autoscaling-servers.md): Learn how to leverage Core 2's native autoscaling functionality for Servers - [Using HPA for Autoscaling](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/hpa-overview.md): Overview of Horizontal Pod Autoscaler (HPA) scaling options in Seldon Core 2 - [Exposing Metrics for HPA](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/hpa-overview/hpa-setup.md): Learn how to implement request-per-second (RPS) based autoscaling in Seldon Core 2 using Kubernetes HPA and Prometheus metrics. - [Model Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/hpa-overview/model-hpa-autoscaling.md): Configuring HPA manifests in Seldon Core 2. - [Model and Server Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/hpa-overview/single-model-serving-hpa.md): Learn how to implement HPA-based autoscaling for both Models and Servers in single-model serving deployments - [Scaling Seldon Services](https://docs.seldon.ai/seldon-core-2/user-guide/scaling/scaling-core-services.md): This page provides guidance about scaling Seldon Core 2 services - [Data Science Monitoring](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring.md): Data Science Monitoring in Seldon Core 2. - [Dataflow with Kafka](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/dataflow.md): Explore how Seldon Core 2 uses data flow paradigm and Kafka-based streaming to improve ML model deployment with better scalability, fault tolerance, and data observability. - [Model Performance Metrics](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/performance-tests.md): Learn how to run performance tests for Seldon Core 2 deployments, including load testing, benchmarking, and analyzing inference latency and throughput metrics. - [Drift Detection](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/drift.md): Learn how to implement drift detection in Seldon Core 2 using Alibi-Detect integration for model monitoring and batch processing. - [Outlier Detection](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/outlier.md): Learn how to implement outlier detection in Seldon Core using Alibi-Detect integration for model monitoring and anomaly detection. - [Explainability](https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/explainers.md): Learn how to implement model explainability in Seldon Core using Alibi-Explain integration for black box model explanations and pipeline insights. - [Operational Monitoring](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring.md): Operational Monitoring in Seldon Core 2. - [Operational Metrics](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring/operational.md): Learn how to monitor operational metrics in Seldon Core, including model performance, pipeline health, and system resource usage. - [Observability](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring/observability.md): Installing kube-prometheus-stack in the same Kubernetes cluster that hosts the Seldon Core 2. - [Usage Metrics](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring/usage.md): Learn how to monitor Seldon Core usage metrics, including request rates, latency, and resource utilization for models and pipelines. - [Local Metrics](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring/local-metrics-test.md): Learn how to test and validate metrics collection in Seldon Core locally, including Prometheus setup and Grafana dashboards. - [Tracing](https://docs.seldon.ai/seldon-core-2/user-guide/operational-monitoring/tracing.md): This guide walks you through setting up Jaeger Tracing for Seldon Core v2 on Kubernetes. By the end of this guide, you will be able to visualize inference traces through your Core 2 components. - [Performance Tuning](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning.md): Introduction in Seldon Core 2. - [Models](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/models.md): Model Performance Tuning in Seldon Core 2. - [Load Testing](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/models/load-testing.md): Load testing Seldon Core 2. - [Inference](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/models/inference.md): Inference in Seldon Core 2. - [Infrastructure Setup](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/models/infrastructure-setup.md): Infrastructure Setup for Seldon Core 2 usage. - [Pipelines](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/pipelines.md): Pipeline Performance Tuning in Seldon Core 2. - [Testing Pipelines](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/pipelines/testing-pipelines.md): Pipelines in Seldon Core 2. - [Core 2 Configuration](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/pipelines/core-2-configuration.md): Reducing Data Processing Overheads when using Seldon Core 2. - [Scalability of Pipelines](https://docs.seldon.ai/seldon-core-2/user-guide/performance-tuning/pipelines/scalability-pipelines.md): Pipeline Scalability Guide in Seldon Core 2. - [Experiments](https://docs.seldon.ai/seldon-core-2/user-guide/experiment.md): Experiments in Seldon Core 2. - [Examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples.md): Examples in Seldon Core 2. - [Local examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/local-examples.md): Examples of Seldon Core 2 used in a local environment. - [Kubernetes examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/k8s-examples.md) - [Huggingface models](https://docs.seldon.ai/seldon-core-2/user-guide/examples/huggingface.md) - [Model zoo](https://docs.seldon.ai/seldon-core-2/user-guide/examples/model-zoo.md) - [Artifact versions](https://docs.seldon.ai/seldon-core-2/user-guide/examples/multi-version.md) - [Pipeline examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/pipeline-examples.md): Pipeline examples in Seldon Core 2. - [Pipeline to pipeline examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/pipeline-to-pipeline.md): Pipeline to pipeline examples in Seldon Core 2. - [Cyclic Pipeline](https://docs.seldon.ai/seldon-core-2/user-guide/examples/pipeline-cyclic.md): Cyclic Inference Pipeline in Seldon Core 2. - [Explainer examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/explainer-examples.md): Learn how to implement model explainability in Seldon Core using Anchor explainers for both tabular and text data - [Custom Servers](https://docs.seldon.ai/seldon-core-2/user-guide/examples/custom-servers.md) - [Local experiments](https://docs.seldon.ai/seldon-core-2/user-guide/examples/local-experiments.md) - [Experiment version examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/experiment-versions.md) - [Tritonclient examples](https://docs.seldon.ai/seldon-core-2/user-guide/examples/tritonclient-examples.md) - [Batch Inference examples (local)](https://docs.seldon.ai/seldon-core-2/user-guide/examples/batch-examples-local.md): Batch Inference examples (local) in Seldon Core 2. - [Checking Pipeline readiness](https://docs.seldon.ai/seldon-core-2/user-guide/examples/pipeline-ready-and-metadata.md) - [Multi-Namespace Kubernetes](https://docs.seldon.ai/seldon-core-2/user-guide/examples/k8s-clusterwide.md) - [Huggingface speech to sentiment with explanations pipeline](https://docs.seldon.ai/seldon-core-2/user-guide/examples/speech-to-sentiment.md): Huggingface speech to sentiment with explanations pipeline in Seldon Core 2. - [Production image classifier with drift and outlier monitoring](https://docs.seldon.ai/seldon-core-2/user-guide/examples/cifar10.md): Tutorial of deploying an image classifier with drift and outlier monitoring in Seldon Core 2. - [Production income classifier with drift, outlier and explanations](https://docs.seldon.ai/seldon-core-2/user-guide/examples/income.md) - [Conditional pipeline with pandas query model](https://docs.seldon.ai/seldon-core-2/user-guide/examples/pandasquery.md): Conditional pipeline with pandas query model in Seldon Core 2. - [Kubernetes Server with PVC](https://docs.seldon.ai/seldon-core-2/user-guide/examples/k8s-pvc.md) - [Service Meshes](https://docs.seldon.ai/seldon-core-2/integrations/service-meshes.md): Using Service Meshes with Seldon Core 2. - [Ambassador](https://docs.seldon.ai/seldon-core-2/integrations/service-meshes/ambassador.md): Learn how to integrate Seldon Core 2 with Ambassador for service mesh and ingress management, including REST and gRPC endpoint configuration. - [Istio](https://docs.seldon.ai/seldon-core-2/integrations/service-meshes/istio.md): Learn how to integrate Seldon Core 2 with Istio service mesh for traffic management and ML model deployment, including gateway configuration and virtual service setup. - [Traefik](https://docs.seldon.ai/seldon-core-2/integrations/service-meshes/traefik.md): Learn how to integrate Seldon Core 2 with Traefik for service mesh and ingress management, including service configuration and middleware implementation. - [Secure Model Endpoints](https://docs.seldon.ai/seldon-core-2/integrations/service-meshes/securing-endpoints.md): Learn how to secure model endpoints in Seldon Core, including authentication, authorization, and TLS configuration. - [Confluent](https://docs.seldon.ai/seldon-core-2/integrations/confluent.md): Leveraging Confluent Kafka with Seldon Core 2. - [Schema Registry](https://docs.seldon.ai/seldon-core-2/integrations/confluent/schema-registry.md): Learn how to integrate Seldon Core 2 with Schema Registry on both Confluent Cloud and Confluent Platform for having a centralized repository for schema management - [Security](https://docs.seldon.ai/seldon-core-2/resources/security.md): Security in Seldon Core 2. - [APIs](https://docs.seldon.ai/seldon-core-2/resources/apis.md): APIs in Seldon Core 2. - [Internal](https://docs.seldon.ai/seldon-core-2/resources/apis/internal.md): Internal APIs in Seldon Core 2. - [Chainer](https://docs.seldon.ai/seldon-core-2/resources/apis/internal/chainer.md): Learn about the internal Chainer API in Seldon Core, including model chaining, tensor mapping, and pipeline configuration. - [Agent](https://docs.seldon.ai/seldon-core-2/resources/apis/internal/agent.md): Learn about the Seldon Agent API that enables communication between the Seldon Scheduler and Agent components for model management and request handling in Core 2. - [Inference](https://docs.seldon.ai/seldon-core-2/resources/apis/inference.md): A comprehensive guide to Seldon's Open Inference Protocol API specification for standardized inference server implementations. - [Scheduler](https://docs.seldon.ai/seldon-core-2/resources/apis/scheduler.md): Learn about the Scheduler API in Seldon Core, including gRPC service definitions, pipeline management, and model deployment. - [Seldon CLI](https://docs.seldon.ai/seldon-core-2/resources/apis/cli.md): Learn how to install and use the Seldon CLI tool for managing Seldon Core 2 resources in non-Kubernetes environments. - [CLI](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/cli.md): Learn more about using Seldon CLI commands - [Seldon](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon.md): seldon commands in Seldon Core 2. - [Config](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config.md) - [Config Activate](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config_activate.md): Learn how to activate Seldon Core configurations using the seldon config activate CLI command. This command enables you to set and manage active configurations for your Seldon Core deployment. - [Config Deactivate](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config_deactivate.md): Learn how to deactivate Seldon Core configurations using the seldon config deactivate CLI command. This command allows you to disable and remove active configurations from your Seldon Core deployment. - [Config Add](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config_add.md): Learn how to add new configurations to Seldon Core using the seldon config add CLI command. This command allows you to create and store new configuration profiles for your Seldon Core deployment. - [Config List](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config_list.md): Learn how to view and list all Seldon Core configurations using the seldon config list CLI command. This command displays all available configuration profiles in your Seldon Core deployment. - [Config Remove](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon/seldon_config_remove.md) - [Experiment](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_experiment.md) - [Experiment Start](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_experiment/seldon_experiment_start.md) - [Experiment Status](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_experiment/seldon_experiment_status.md) - [Experiment List](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_experiment/seldon_experiment_list.md) - [Experiment Stop](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_experiment/seldon_experiment_stop.md) - [Model](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model.md) - [Model Status](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_status.md) - [Model Load](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_load.md) - [Model List](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_list.md) - [Model Infer](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_infer.md) - [Model Metadata](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_metadata.md) - [Model Unload](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_model/seldon_model_unload.md) - [Pipeline](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline.md) - [Pipeline Load](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_load.md) - [Pipeline Status](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_status.md) - [Pipeline List](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_list.md) - [Pipeline Inspect](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_inspect.md) - [Pipeline Infer](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_infer.md) - [Pipeline Unload](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_pipeline/seldon_pipeline_unload.md) - [Server](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_server.md) - [Server List](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_server/seldon_server_list.md) - [Server Status](https://docs.seldon.ai/seldon-core-2/resources/apis/cli/seldon_server/seldon_server_status.md) - [FAQs](https://docs.seldon.ai/seldon-core-2/resources/faqs.md): Find answers to common questions about Seldon Core, including installation, configuration, model deployment, and troubleshooting. - [Development](https://docs.seldon.ai/seldon-core-2/resources/development.md): Development in Seldon Core 2. - [License](https://docs.seldon.ai/seldon-core-2/resources/development/licenses.md): 3rd party license generation in Seldon Core 2. - [Release](https://docs.seldon.ai/seldon-core-2/resources/development/release.md): Release process in Seldon Core 2. ## v2.9 - [Production-ready ML Serving Framework](https://docs.seldon.ai/seldon-core-2/v2.9/about/readme.md): Discover Seldon Core 2, a Kubernetes-native MLOps framework for deploying ML and LLM systems at scale. Features flexible architecture, standardized workflows, and enhanced observability. - [Seldon Core Features](https://docs.seldon.ai/seldon-core-2/v2.9/about/core-features.md): Explore the enterprise MLOps capabilities of Core 2 for production ML deployment, featuring model serving, pipeline orchestration, and intelligent resource management for scalable ML systems. - [Concepts](https://docs.seldon.ai/seldon-core-2/v2.9/about/concepts.md): Learn how Seldon Core is different from a centralized orchestrator to a data flow architecture, enabling more efficient ML model deployment through stream processing and improved data handling. - [Architecture](https://docs.seldon.ai/seldon-core-2/v2.9/about/architecture.md): Learn about the Seldon Core 2 microservice architecture, control plane and data plane components, and how these services work to provide a scalable, fault-tolerant ML model serving and management. - [Installation Overview](https://docs.seldon.ai/seldon-core-2/v2.9/installation/installation.md): Learn how to install Seldon Core 2 in various environments - from local development with Docker Compose to production-grade Kubernetes clusters. - [Learning Environment](https://docs.seldon.ai/seldon-core-2/v2.9/installation/learning-environment.md): Install Seldon Core 2 in a local learning environment. - [Self-hosted Kafka](https://docs.seldon.ai/seldon-core-2/v2.9/installation/learning-environment/self-hosted-kafka.md): Learn how to set up a self-hosted Kafka cluster for Seldon Core in development and learning environments. - [Production Environment](https://docs.seldon.ai/seldon-core-2/v2.9/installation/production-environment.md): Install Core 2 in a production Kubernetes environment. - [Kafka Integration](https://docs.seldon.ai/seldon-core-2/v2.9/installation/production-environment/kafka.md): Learn how to set up and configure Kafka for Seldon Core in production environments, including cluster setup and security configuration. - [Managed Kafka](https://docs.seldon.ai/seldon-core-2/v2.9/installation/production-environment/managed-kafka.md): Guide to integrating managed Kafka services (Confluent Cloud, Amazon MSK, Azure Event Hub) with Seldon Core 2, including security configurations and authentication setup. - [Ingress Controller](https://docs.seldon.ai/seldon-core-2/v2.9/installation/production-environment/istio.md): Learn how to configure Istio as an ingress controller for Seldon Core, including traffic management and security policies. - [Test the Installation](https://docs.seldon.ai/seldon-core-2/v2.9/installation/test-installation.md): Learn how to verify your Seldon Core installation by running tests and checking component functionality. - [Advanced Configurations](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations.md) - [Helm Configuration](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/helm.md): Learn how to install and configure Seldon Core using Helm charts, including component setup and customization options. - [Server Config](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/serverconfig.md) - [Server Runtime](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/seldonruntime.md): Learn about SeldonRuntime, a Kubernetes resource for creating and managing Seldon Core instances in specific namespaces with configurable settings. - [Seldon Config](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/seldonconfig.md): Learn how to configure Seldon Core installation components using SeldonConfig resource, including component specifications, Kafka settings, and tracing configuration. - [Pipeline Config](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/pipeline.md): Learn how to create and manage ML pipelines in Seldon Core using Kubernetes custom resources, including model chaining and tensor mapping. - [Managing Kafka Topics](https://docs.seldon.ai/seldon-core-2/v2.9/installation/advanced-configurations/managing-kafka-topics.md): Learn how to manage Kafka topics in Seldon Core 2, including topic creation, configuration, and monitoring for model inference and event streaming. - [Upgrading](https://docs.seldon.ai/seldon-core-2/v2.9/installation/upgrading.md) - [Quickstart](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/quickstart.md) - [Kubernetes Resources](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/resources.md) - [Servers](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/servers.md): Learn how to configure and manage inference servers in Seldon Core 2, including MLServer and Triton server farms, model scheduling, and capability management. - [Resource allocation](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/servers/resource-allocation.md): Learn more about using taints and tolerations with node affinity or node selector to allocate resources in a Kubernetes cluster. - [Example: Serving models on dedicated GPU nodes](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/servers/resource-allocation/example-serving-models-on-dedicated-gpu-nodes.md): This example illustrates how to use taints, tolerations with nodeAffinity or nodeSelector to assign GPU nodes to specific models. - [Models](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models.md) - [Multi-Model Serving](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/mms.md): Learn how to configure multi-model serving in Seldon Core, including resource optimization and model co-location. - [Inference Artifacts](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/inference-artifacts.md): Learn how to manage model artifacts in Seldon Core, including storage, versioning, and deployment workflows. - [Scheduling](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/scheduling.md): Learn how to configure model scheduling in Seldon Core, including resource allocation, scaling policies, and deployment strategies. - [rClone](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/rclone.md): Learn how to configure and use Rclone for model artifact storage in Seldon Core, including cloud storage integration and authentication. - [Parameterized Models](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/parameterized-models.md) - [Pandas Query](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/pandasquery.md): Learn how to use PandasQuery for data transformation in Seldon Core, including query configuration and parameter handling. - [Storage Secrets](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/models/storage-secrets.md): Learn how to configure storage secrets in Seldon Core 2 for secure model artifact access using Rclone, including AWS S3, GCS, and MinIO integration. - [Inference](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/inference.md) - [Inference Server](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/inference/inference.md): Learn how to perform model inference in Seldon Core using REST and gRPC protocols, including request/response formats and client examples. - [Run Inference](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/inference/inference-1.md) - [OIP](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/inference/v2.md) - [Batch](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/inference/batch-examples-k8s.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/pipelines.md): Learn how to create and manage ML inference pipelines in Seldon Core, including model chaining, tensor mapping, and conditional logic. - [Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling.md) - [Seldon Core Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/core-autoscaling.md) - [Autoscaling Models](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/core-autoscaling/core-autoscaling-models.md): Learn how to leverage Core 2's native autoscaling functionality for Models - [Autoscaling Servers](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/core-autoscaling/core-autoscaling-servers.md): Learn how to leverage Core 2's native autoscaling functionality for Servers - [Using HPA for Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/hpa-overview.md): Overview of Horizontal Pod Autoscaler (HPA) scaling options in Seldon Core 2 - [Exposing Metrics for HPA](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/hpa-overview/hpa-setup.md): Learn how to implement request-per-second (RPS) based autoscaling in Seldon Core 2 using Kubernetes HPA and Prometheus metrics. - [Model Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/hpa-overview/model-hpa-autoscaling.md) - [Model and Server Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/hpa-overview/single-model-serving-hpa.md): Learn how to implement HPA-based autoscaling for both Models and Servers in single-model serving deployments - [Scaling Seldon Services](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/scaling/scaling-core-services.md): This page provides guidance about scaling Seldon Core 2 services - [Data Science Monitoring](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring.md) - [Dataflow with Kafka](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring/dataflow.md): Explore how Seldon Core 2 uses data flow paradigm and Kafka-based streaming to improve ML model deployment with better scalability, fault tolerance, and data observability. - [Model Performance Metrics](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring/performance-tests.md): Learn how to run performance tests for Seldon Core 2 deployments, including load testing, benchmarking, and analyzing inference latency and throughput metrics. - [Drift Detection](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring/drift.md): Learn how to implement drift detection in Seldon Core 2 using Alibi-Detect integration for model monitoring and batch processing. - [Outlier Detection](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring/outlier.md): Learn how to implement outlier detection in Seldon Core using Alibi-Detect integration for model monitoring and anomaly detection. - [Explainability](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/data-science-monitoring/explainers.md): Learn how to implement model explainability in Seldon Core using Alibi-Explain integration for black box model explanations and pipeline insights. - [Operational Monitoring](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring.md) - [Operational Metrics](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring/operational.md): Learn how to monitor operational metrics in Seldon Core, including model performance, pipeline health, and system resource usage. - [Observability](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring/observability.md) - [Usage Metrics](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring/usage.md): Learn how to monitor Seldon Core usage metrics, including request rates, latency, and resource utilization for models and pipelines. - [Local Metrics](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring/local-metrics-test.md): Learn how to test and validate metrics collection in Seldon Core locally, including Prometheus setup and Grafana dashboards. - [Tracing](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/operational-monitoring/tracing.md): Learn how to implement distributed tracing in Seldon Core 2 using OpenTelemetry and Jaeger for monitoring and debugging ML model serving pipelines. - [Performance Tuning](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning.md) - [Models](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/models.md) - [Load Testing](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/models/load-testing.md) - [Inference](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/models/inference.md) - [Infrastructure Setup](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/models/infrastructure-setup.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/pipelines.md) - [Testing Pipelines](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/pipelines/testing-pipelines.md) - [Core 2 Configuration](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/performance-tuning/pipelines/core-2-configuration.md) - [Experiments](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/experiment.md) - [Examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples.md) - [Local examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/local-examples.md) - [Kubernetes examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/k8s-examples.md) - [Huggingface models](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/huggingface.md) - [Model zoo](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/model-zoo.md) - [Artifact versions](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/multi-version.md) - [Pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/pipeline-examples.md) - [Pipeline to pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/pipeline-to-pipeline.md) - [Cyclic Pipeline](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/pipeline-cyclic.md) - [Explainer examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/explainer-examples.md): Learn how to implement model explainability in Seldon Core using Anchor explainers for both tabular and text data - [Custom Servers](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/custom-servers.md) - [Local experiments](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/local-experiments.md) - [Experiment version examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/experiment-versions.md) - [Tritonclient examples](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/tritonclient-examples.md) - [Batch Inference examples (local)](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/batch-examples-local.md) - [Checking Pipeline readiness](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/pipeline-ready-and-metadata.md) - [Multi-Namespace Kubernetes](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/k8s-clusterwide.md) - [Huggingface speech to sentiment with explanations pipeline](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/speech-to-sentiment.md) - [Production image classifier with drift and outlier monitoring](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/cifar10.md) - [Production income classifier with drift, outlier and explanations](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/income.md) - [Conditional pipeline with pandas query model](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/pandasquery.md) - [Kubernetes Server with PVC](https://docs.seldon.ai/seldon-core-2/v2.9/user-guide/examples/k8s-pvc.md) - [Service Meshes](https://docs.seldon.ai/seldon-core-2/v2.9/integrations/service-meshes.md) - [Ambassador](https://docs.seldon.ai/seldon-core-2/v2.9/integrations/service-meshes/ambassador.md): Learn how to integrate Seldon Core 2 with Ambassador for service mesh and ingress management, including REST and gRPC endpoint configuration. - [Istio](https://docs.seldon.ai/seldon-core-2/v2.9/integrations/service-meshes/istio.md): Learn how to integrate Seldon Core 2 with Istio service mesh for traffic management and ML model deployment, including gateway configuration and virtual service setup. - [Traefik](https://docs.seldon.ai/seldon-core-2/v2.9/integrations/service-meshes/traefik.md): Learn how to integrate Seldon Core 2 with Traefik for service mesh and ingress management, including service configuration and middleware implementation. - [Secure Model Endpoints](https://docs.seldon.ai/seldon-core-2/v2.9/integrations/service-meshes/securing-endpoints.md): Learn how to secure model endpoints in Seldon Core, including authentication, authorization, and TLS configuration. - [Security](https://docs.seldon.ai/seldon-core-2/v2.9/resources/security.md) - [APIs](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis.md) - [Internal](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/internal.md) - [Chainer](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/internal/chainer.md): Learn about the internal Chainer API in Seldon Core, including model chaining, tensor mapping, and pipeline configuration. - [Agent](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/internal/agent.md): Learn about the Seldon Agent API that enables communication between the Seldon Scheduler and Agent components for model management and request handling in Core 2. - [Inference](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/inference.md): A comprehensive guide to Seldon's Open Inference Protocol API specification for standardized inference server implementations. - [Scheduler](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/scheduler.md): Learn about the Scheduler API in Seldon Core, including gRPC service definitions, pipeline management, and model deployment. - [Seldon CLI](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli.md): Learn how to install and use the Seldon CLI tool for managing Seldon Core 2 resources in non-Kubernetes environments. - [CLI](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/cli.md): Learn more about using Seldon CLI commands - [Seldon](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon.md) - [Config](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config.md) - [Config Activate](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config_activate.md): Learn how to activate Seldon Core configurations using the seldon config activate CLI command. This command enables you to set and manage active configurations for your Seldon Core deployment. - [Config Deactivate](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config_deactivate.md): Learn how to deactivate Seldon Core configurations using the seldon config deactivate CLI command. This command allows you to disable and remove active configurations from your Seldon Core deployment. - [Config Add](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config_add.md): Learn how to add new configurations to Seldon Core using the seldon config add CLI command. This command allows you to create and store new configuration profiles for your Seldon Core deployment. - [Config List](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config_list.md): Learn how to view and list all Seldon Core configurations using the seldon config list CLI command. This command displays all available configuration profiles in your Seldon Core deployment. - [Config Remove](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon/seldon_config_remove.md) - [Experiment](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_experiment.md) - [Experiment Start](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_experiment/seldon_experiment_start.md) - [Experiment Status](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_experiment/seldon_experiment_status.md) - [Experiment List](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_experiment/seldon_experiment_list.md) - [Experiment Stop](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_experiment/seldon_experiment_stop.md) - [Model](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model.md) - [Model Status](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_status.md) - [Model Load](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_load.md) - [Model List](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_list.md) - [Model Infer](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_infer.md) - [Model Metadata](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_metadata.md) - [Model Unload](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_model/seldon_model_unload.md) - [Pipeline](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline.md) - [Pipeline Load](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_load.md) - [Pipeline Status](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_status.md) - [Pipeline List](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_list.md) - [Pipeline Inspect](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_inspect.md) - [Pipeline Infer](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_infer.md) - [Pipeline Unload](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_pipeline/seldon_pipeline_unload.md) - [Server](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_server.md) - [Server List](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_server/seldon_server_list.md) - [Server Status](https://docs.seldon.ai/seldon-core-2/v2.9/resources/apis/cli/seldon_server/seldon_server_status.md) - [FAQs](https://docs.seldon.ai/seldon-core-2/v2.9/resources/faqs.md): Find answers to common questions about Seldon Core, including installation, configuration, model deployment, and troubleshooting. - [Development](https://docs.seldon.ai/seldon-core-2/v2.9/resources/development.md) - [License](https://docs.seldon.ai/seldon-core-2/v2.9/resources/development/licenses.md) - [Release](https://docs.seldon.ai/seldon-core-2/v2.9/resources/development/release.md) ## v2.8 - [Home](https://docs.seldon.ai/seldon-core-2/v2.8/readme.md) - [Getting Started](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started.md) - [Docker Installation](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/docker-installation.md) - [Kubernetes Installation](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation.md) - [Ansible](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/ansible.md) - [Helm](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/helm.md) - [Security](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security.md) - [AWS MSK mTLS](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/aws-msk-mtls.md) - [AWS MSK SASL](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/aws-msk-sasl.md) - [Azure Event Hub SASL Example](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/azure-event-hub-sasl.md) - [Confluent Cloud Oauth 2.0 Example](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/confluent-oauth.md) - [Confluent Cloud SASL Example](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/confluent-sasl.md) - [Strimzi mTLS Example](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/strimzi-mtls.md) - [Strimzi SASL Example](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/strimzi-sasl.md) - [Reference](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/kubernetes-installation/security/reference.md) - [Configuration](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/configuration.md) - [Seldon CLI](https://docs.seldon.ai/seldon-core-2/v2.8/getting-started/cli.md): Learn about installing Seldon command line tool that you can use to manage Seldon Core 2 resources. - [APIs](https://docs.seldon.ai/seldon-core-2/v2.8/apis.md) - [Internal](https://docs.seldon.ai/seldon-core-2/v2.8/apis/internal.md) - [Chainer](https://docs.seldon.ai/seldon-core-2/v2.8/apis/internal/chainer.md) - [Agent](https://docs.seldon.ai/seldon-core-2/v2.8/apis/internal/agent.md) - [Inference](https://docs.seldon.ai/seldon-core-2/v2.8/apis/inference.md) - [Open Inference Protocol](https://docs.seldon.ai/seldon-core-2/v2.8/apis/inference/v2.md) - [Scheduler](https://docs.seldon.ai/seldon-core-2/v2.8/apis/scheduler.md) - [Architecture](https://docs.seldon.ai/seldon-core-2/v2.8/architecture.md) - [DataFlow](https://docs.seldon.ai/seldon-core-2/v2.8/architecture/dataflow.md) - [Examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples.md) - [Local examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/local-examples.md) - [Kubernetes examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/k8s-examples.md) - [Huggingface models](https://docs.seldon.ai/seldon-core-2/v2.8/examples/huggingface.md) - [Model zoo](https://docs.seldon.ai/seldon-core-2/v2.8/examples/model-zoo.md) - [Artifact versions](https://docs.seldon.ai/seldon-core-2/v2.8/examples/multi-version.md) - [Pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/pipeline-examples.md) - [Pipeline to pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/pipeline-to-pipeline.md) - [Explainer examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/explainer-examples.md) - [Custom Servers](https://docs.seldon.ai/seldon-core-2/v2.8/examples/custom-servers.md) - [Local experiments](https://docs.seldon.ai/seldon-core-2/v2.8/examples/local-experiments.md) - [Experiment version examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/experiment-versions.md) - [Inference examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/inference.md) - [Tritonclient examples](https://docs.seldon.ai/seldon-core-2/v2.8/examples/tritonclient-examples.md) - [Batch Inference examples (kubernetes)](https://docs.seldon.ai/seldon-core-2/v2.8/examples/batch-examples-k8s.md) - [Batch Inference examples (local)](https://docs.seldon.ai/seldon-core-2/v2.8/examples/batch-examples-local.md) - [Checking Pipeline readiness](https://docs.seldon.ai/seldon-core-2/v2.8/examples/pipeline-ready-and-metadata.md) - [Multi-Namespace Kubernetes](https://docs.seldon.ai/seldon-core-2/v2.8/examples/k8s-clusterwide.md) - [Huggingface speech to sentiment with explanations pipeline](https://docs.seldon.ai/seldon-core-2/v2.8/examples/speech-to-sentiment.md) - [Production image classifier with drift and outlier monitoring](https://docs.seldon.ai/seldon-core-2/v2.8/examples/cifar10.md) - [Production income classifier with drift, outlier and explanations](https://docs.seldon.ai/seldon-core-2/v2.8/examples/income.md) - [Conditional pipeline with pandas query model](https://docs.seldon.ai/seldon-core-2/v2.8/examples/pandasquery.md) - [Kubernetes Server with PVC](https://docs.seldon.ai/seldon-core-2/v2.8/examples/k8s-pvc.md) - [Kubernetes](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes.md) - [Scaling](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/scaling.md) - [Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/autoscaling.md) - [HPA Autoscaling in single-model serving](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/hpa-rps-autoscaling.md) - [Tracing](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/tracing.md) - [Storage Secrets](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/storage-secrets.md) - [Kafka](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/kafka.md) - [Metrics](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/metrics.md) - [Resources](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources.md) - [Model](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/model.md) - [Experiment](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/experiment.md) - [Pipeline](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/pipeline.md) - [Server](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/server.md) - [Server Config](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/serverconfig.md) - [Server Runtime](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/seldonruntime.md) - [Seldon Config](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/resources/seldonconfig.md) - [Service Meshes](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/service-meshes.md) - [Ambassador](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/service-meshes/ambassador.md) - [Istio](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/service-meshes/istio.md) - [Traefik](https://docs.seldon.ai/seldon-core-2/v2.8/kubernetes/service-meshes/traefik.md) - [Resource allocation](https://docs.seldon.ai/seldon-core-2/v2.8/resource-allocation.md): Learn more about using taints and tolerations with node affinity or node selector to allocate resources in a Kubernetes cluster. - [Example: Serving models on dedicated GPU nodes](https://docs.seldon.ai/seldon-core-2/v2.8/resource-allocation/example-serving-models-on-dedicated-gpu-nodes.md): This example illustrates how to use taints, tolerations with nodeAffinity or nodeSelector to assign GPU nodes to specific models. - [Models](https://docs.seldon.ai/seldon-core-2/v2.8/models.md) - [Multi-Model Serving](https://docs.seldon.ai/seldon-core-2/v2.8/models/mms.md) - [Inference Artifacts](https://docs.seldon.ai/seldon-core-2/v2.8/models/inference-artifacts.md) - [rClone](https://docs.seldon.ai/seldon-core-2/v2.8/models/rclone.md) - [Parameterized Models](https://docs.seldon.ai/seldon-core-2/v2.8/models/parameterized-models.md) - [Pandas Query](https://docs.seldon.ai/seldon-core-2/v2.8/models/pandasquery.md) - [Metrics](https://docs.seldon.ai/seldon-core-2/v2.8/metrics.md) - [Usage](https://docs.seldon.ai/seldon-core-2/v2.8/metrics/usage.md) - [Operational](https://docs.seldon.ai/seldon-core-2/v2.8/metrics/operational.md) - [Local Metrics](https://docs.seldon.ai/seldon-core-2/v2.8/metrics/local-metrics-test.md) - [Development](https://docs.seldon.ai/seldon-core-2/v2.8/development.md) - [License](https://docs.seldon.ai/seldon-core-2/v2.8/development/licenses.md) - [Release](https://docs.seldon.ai/seldon-core-2/v2.8/development/release.md) - [CLI](https://docs.seldon.ai/seldon-core-2/v2.8/cli.md): Learn more about using Seldon CLI commands - [Seldon](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon.md) - [Config](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config.md) - [Config Activate](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config/seldon_config_activate.md) - [Config Deactivate](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config/seldon_config_deactivate.md) - [Config Add](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config/seldon_config_add.md) - [Config List](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config/seldon_config_list.md) - [Config Remove](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_config/seldon_config_remove.md) - [Experiment](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_experiment.md) - [Experiment Start](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_experiment/seldon_experiment_start.md) - [Experiment Status](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_experiment/seldon_experiment_status.md) - [Experiment List](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_experiment/seldon_experiment_list.md) - [Experiment Stop](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_experiment/seldon_experiment_stop.md) - [Model](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model.md) - [Model Status](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_status.md) - [Model Load](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_load.md) - [Model List](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_list.md) - [Model Infer](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_infer.md) - [Model Metadata](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_metadata.md) - [Model Unload](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_model/seldon_model_unload.md) - [Pipeline](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline.md) - [Pipeline Load](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_load.md) - [Pipeline Status](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_status.md) - [Pipeline List](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_list.md) - [Pipeline Inspect](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_inspect.md) - [Pipeline Infer](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_infer.md) - [Pipeline Unload](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_pipeline/seldon_pipeline_unload.md) - [Server](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_server.md) - [Server List](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_server/seldon_server_list.md) - [Server Status](https://docs.seldon.ai/seldon-core-2/v2.8/cli/seldon_server/seldon_server_status.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/v2.8/pipelines.md) - [Experiments](https://docs.seldon.ai/seldon-core-2/v2.8/experiments.md) - [Servers](https://docs.seldon.ai/seldon-core-2/v2.8/servers.md) - [Inference](https://docs.seldon.ai/seldon-core-2/v2.8/inference.md) - [Outlier Detection](https://docs.seldon.ai/seldon-core-2/v2.8/outlier.md) - [Drift Detection](https://docs.seldon.ai/seldon-core-2/v2.8/drift.md) - [Explainers](https://docs.seldon.ai/seldon-core-2/v2.8/explainers.md) - [Performance Tests](https://docs.seldon.ai/seldon-core-2/v2.8/performance-tests.md) - [Upgrading](https://docs.seldon.ai/seldon-core-2/v2.8/upgrading.md) - [FAQ](https://docs.seldon.ai/seldon-core-2/v2.8/faqs.md) ## v2.10 - [Production-ready ML Serving Framework](https://docs.seldon.ai/seldon-core-2/v2.10/about/readme.md): Discover Seldon Core 2, a Kubernetes-native MLOps framework for deploying ML and LLM systems at scale. Features flexible architecture, standardized workflows, and enhanced observability. - [Seldon Core Features](https://docs.seldon.ai/seldon-core-2/v2.10/about/core-features.md): Explore the enterprise MLOps capabilities of Core 2 for production ML deployment, featuring model serving, pipeline orchestration, and intelligent resource management for scalable ML systems. - [Concepts](https://docs.seldon.ai/seldon-core-2/v2.10/about/concepts.md): Learn how Seldon Core is different from a centralized orchestrator to a data flow architecture, enabling more efficient ML model deployment through stream processing and improved data handling. - [Architecture](https://docs.seldon.ai/seldon-core-2/v2.10/about/architecture.md): Learn about the Seldon Core 2 microservice architecture, control plane and data plane components, and how these services work to provide a scalable, fault-tolerant ML model serving and management. - [Installation Overview](https://docs.seldon.ai/seldon-core-2/v2.10/installation/installation.md): Learn how to install Seldon Core 2 in various environments - from local development with Docker Compose to production-grade Kubernetes clusters. - [Learning Environment](https://docs.seldon.ai/seldon-core-2/v2.10/installation/learning-environment.md): Install Seldon Core 2 in a local learning environment. - [Self-hosted Kafka](https://docs.seldon.ai/seldon-core-2/v2.10/installation/learning-environment/self-hosted-kafka.md): Learn how to set up a self-hosted Kafka cluster for Seldon Core in development and learning environments. - [Production Environment](https://docs.seldon.ai/seldon-core-2/v2.10/installation/production-environment.md): Install Core 2 in a production Kubernetes environment. - [Kafka Integration](https://docs.seldon.ai/seldon-core-2/v2.10/installation/production-environment/kafka.md): Learn how to set up and configure Kafka for Seldon Core in production environments, including cluster setup and security configuration. - [Managed Kafka](https://docs.seldon.ai/seldon-core-2/v2.10/installation/production-environment/managed-kafka.md): Guide to integrating managed Kafka services (Confluent Cloud, Amazon MSK, Azure Event Hub) with Seldon Core 2, including security configurations and authentication setup. - [Ingress Controller](https://docs.seldon.ai/seldon-core-2/v2.10/installation/production-environment/istio.md): Learn how to configure Istio as an ingress controller for Seldon Core, including traffic management and security policies. - [Test the Installation](https://docs.seldon.ai/seldon-core-2/v2.10/installation/test-installation.md): Learn how to verify your Seldon Core installation by running tests and checking component functionality. - [Advanced Configurations](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations.md) - [Helm Configuration](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/helm.md): Learn how to install and configure Seldon Core using Helm charts, including component setup and customization options. - [Server Config](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/serverconfig.md) - [Server Runtime](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/seldonruntime.md): Learn about SeldonRuntime, a Kubernetes resource for creating and managing Seldon Core instances in specific namespaces with configurable settings. - [Seldon Config](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/seldonconfig.md): Learn how to configure Seldon Core installation components using SeldonConfig resource, including component specifications, Kafka settings, and tracing configuration. - [Pipeline Config](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/pipeline.md): Learn how to create and manage ML pipelines in Seldon Core using Kubernetes custom resources, including model chaining and tensor mapping. - [Managing Kafka Topics](https://docs.seldon.ai/seldon-core-2/v2.10/installation/advanced-configurations/managing-kafka-topics.md): Learn how to manage Kafka topics in Seldon Core 2, including topic creation, configuration, and monitoring for model inference and event streaming. - [Upgrading](https://docs.seldon.ai/seldon-core-2/v2.10/installation/upgrading.md) - [Quickstart](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/quickstart.md) - [Kubernetes Resources](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/resources.md) - [Servers](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/servers.md): Learn how to configure and manage inference servers in Seldon Core 2, including MLServer and Triton server farms, model scheduling, and capability management. - [Resource allocation](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/servers/resource-allocation.md): Learn more about using taints and tolerations with node affinity or node selector to allocate resources in a Kubernetes cluster. - [Example: Serving models on dedicated GPU nodes](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/servers/resource-allocation/example-serving-models-on-dedicated-gpu-nodes.md): This example illustrates how to use taints, tolerations with nodeAffinity or nodeSelector to assign GPU nodes to specific models. - [Models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models.md) - [Multi-Model Serving](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/mms.md): Learn how to configure multi-model serving in Seldon Core, including resource optimization and model co-location. - [Inference Artifacts](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/inference-artifacts.md): Learn how to manage model artifacts in Seldon Core, including storage, versioning, and deployment workflows. - [Scheduling](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/scheduling.md): Learn how to configure model scheduling in Seldon Core, including resource allocation, scaling policies, and deployment strategies. - [rClone](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/rclone.md): Learn how to configure and use Rclone for model artifact storage in Seldon Core, including cloud storage integration and authentication. - [Parameterized Models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/parameterized-models.md) - [Pandas Query](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/pandasquery.md): Learn how to use PandasQuery for data transformation in Seldon Core, including query configuration and parameter handling. - [Storage Secrets](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/models/storage-secrets.md): Learn how to configure storage secrets in Seldon Core 2 for secure model artifact access using Rclone, including AWS S3, GCS, and MinIO integration. - [Inference](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/inference.md) - [Inference Server](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/inference/inference.md): Learn how to perform model inference in Seldon Core using REST and gRPC protocols, including request/response formats and client examples. - [Run Inference](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/inference/inference-1.md) - [Batch](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/inference/batch-examples-k8s.md) - [Open Inference Protocol](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2.md) - [REST](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2/rest.md) - [Health](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2/rest/health.md) - [Inference](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2/rest/inference.md) - [Metadata](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2/rest/metadata.md) - [Models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/v2/rest/models.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/pipelines.md): Learn how to create and manage ML inference pipelines in Seldon Core, including model chaining, tensor mapping, and conditional logic. - [Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling.md) - [Seldon Core Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/core-autoscaling.md) - [Autoscaling Models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/core-autoscaling/core-autoscaling-models.md): Learn how to leverage Core 2's native autoscaling functionality for Models - [Autoscaling Servers](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/core-autoscaling/core-autoscaling-servers.md): Learn how to leverage Core 2's native autoscaling functionality for Servers - [Using HPA for Autoscaling](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/hpa-overview.md): Overview of Horizontal Pod Autoscaler (HPA) scaling options in Seldon Core 2 - [Exposing Metrics for HPA](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/hpa-overview/hpa-setup.md): Learn how to implement request-per-second (RPS) based autoscaling in Seldon Core 2 using Kubernetes HPA and Prometheus metrics. - [Model Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/hpa-overview/model-hpa-autoscaling.md) - [Model and Server Autoscaling with HPA](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/hpa-overview/single-model-serving-hpa.md): Learn how to implement HPA-based autoscaling for both Models and Servers in single-model serving deployments - [Scaling Seldon Services](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/scaling/scaling-core-services.md): This page provides guidance about scaling Seldon Core 2 services - [Data Science Monitoring](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring.md) - [Dataflow with Kafka](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring/dataflow.md): Explore how Seldon Core 2 uses data flow paradigm and Kafka-based streaming to improve ML model deployment with better scalability, fault tolerance, and data observability. - [Model Performance Metrics](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring/performance-tests.md): Learn how to run performance tests for Seldon Core 2 deployments, including load testing, benchmarking, and analyzing inference latency and throughput metrics. - [Drift Detection](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring/drift.md): Learn how to implement drift detection in Seldon Core 2 using Alibi-Detect integration for model monitoring and batch processing. - [Outlier Detection](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring/outlier.md): Learn how to implement outlier detection in Seldon Core using Alibi-Detect integration for model monitoring and anomaly detection. - [Explainability](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/data-science-monitoring/explainers.md): Learn how to implement model explainability in Seldon Core using Alibi-Explain integration for black box model explanations and pipeline insights. - [Operational Monitoring](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring.md) - [Operational Metrics](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring/operational.md): Learn how to monitor operational metrics in Seldon Core, including model performance, pipeline health, and system resource usage. - [Observability](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring/observability.md): Installing kube-prometheus-stack in the same Kubernetes cluster that hosts the Seldon Core 2. - [Usage Metrics](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring/usage.md): Learn how to monitor Seldon Core usage metrics, including request rates, latency, and resource utilization for models and pipelines. - [Local Metrics](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring/local-metrics-test.md): Learn how to test and validate metrics collection in Seldon Core locally, including Prometheus setup and Grafana dashboards. - [Tracing](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/operational-monitoring/tracing.md): This guide walks you through setting up Jaeger Tracing for Seldon Core v2 on Kubernetes. By the end of this guide, you will be able to visualize inference traces through your Core 2 components. - [Performance Tuning](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning.md) - [Models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/models.md) - [Load Testing](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/models/load-testing.md) - [Inference](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/models/inference.md) - [Infrastructure Setup](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/models/infrastructure-setup.md) - [Pipelines](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/pipelines.md) - [Testing Pipelines](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/pipelines/testing-pipelines.md) - [Core 2 Configuration](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/pipelines/core-2-configuration.md) - [Scalability of Pipelines](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/performance-tuning/pipelines/scalability-pipelines.md) - [Experiments](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/experiment.md) - [Examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples.md) - [Local examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/local-examples.md) - [Kubernetes examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/k8s-examples.md) - [Huggingface models](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/huggingface.md) - [Model zoo](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/model-zoo.md) - [Artifact versions](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/multi-version.md) - [Pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/pipeline-examples.md) - [Pipeline to pipeline examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/pipeline-to-pipeline.md) - [Cyclic Pipeline](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/pipeline-cyclic.md) - [Explainer examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/explainer-examples.md): Learn how to implement model explainability in Seldon Core using Anchor explainers for both tabular and text data - [Custom Servers](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/custom-servers.md) - [Local experiments](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/local-experiments.md) - [Experiment version examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/experiment-versions.md) - [Tritonclient examples](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/tritonclient-examples.md) - [Batch Inference examples (local)](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/batch-examples-local.md) - [Checking Pipeline readiness](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/pipeline-ready-and-metadata.md) - [Multi-Namespace Kubernetes](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/k8s-clusterwide.md) - [Huggingface speech to sentiment with explanations pipeline](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/speech-to-sentiment.md) - [Production image classifier with drift and outlier monitoring](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/cifar10.md) - [Production income classifier with drift, outlier and explanations](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/income.md) - [Conditional pipeline with pandas query model](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/pandasquery.md) - [Kubernetes Server with PVC](https://docs.seldon.ai/seldon-core-2/v2.10/user-guide/examples/k8s-pvc.md) - [Service Meshes](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/service-meshes.md) - [Ambassador](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/service-meshes/ambassador.md): Learn how to integrate Seldon Core 2 with Ambassador for service mesh and ingress management, including REST and gRPC endpoint configuration. - [Istio](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/service-meshes/istio.md): Learn how to integrate Seldon Core 2 with Istio service mesh for traffic management and ML model deployment, including gateway configuration and virtual service setup. - [Traefik](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/service-meshes/traefik.md): Learn how to integrate Seldon Core 2 with Traefik for service mesh and ingress management, including service configuration and middleware implementation. - [Secure Model Endpoints](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/service-meshes/securing-endpoints.md): Learn how to secure model endpoints in Seldon Core, including authentication, authorization, and TLS configuration. - [Confluent](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/confluent.md) - [Schema Registry](https://docs.seldon.ai/seldon-core-2/v2.10/integrations/confluent/schema-registry.md): Learn how to integrate Seldon Core 2 with Schema Registry on both Confluent Cloud and Confluent Platform for having a centralized repository for schema management - [Security](https://docs.seldon.ai/seldon-core-2/v2.10/resources/security.md) - [APIs](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis.md) - [Internal](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/internal.md) - [Chainer](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/internal/chainer.md): Learn about the internal Chainer API in Seldon Core, including model chaining, tensor mapping, and pipeline configuration. - [Agent](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/internal/agent.md): Learn about the Seldon Agent API that enables communication between the Seldon Scheduler and Agent components for model management and request handling in Core 2. - [Inference](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/inference.md): A comprehensive guide to Seldon's Open Inference Protocol API specification for standardized inference server implementations. - [Scheduler](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/scheduler.md): Learn about the Scheduler API in Seldon Core, including gRPC service definitions, pipeline management, and model deployment. - [Seldon CLI](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli.md): Learn how to install and use the Seldon CLI tool for managing Seldon Core 2 resources in non-Kubernetes environments. - [CLI](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/cli.md): Learn more about using Seldon CLI commands - [Seldon](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon.md) - [Config](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config.md) - [Config Activate](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config_activate.md): Learn how to activate Seldon Core configurations using the seldon config activate CLI command. This command enables you to set and manage active configurations for your Seldon Core deployment. - [Config Deactivate](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config_deactivate.md): Learn how to deactivate Seldon Core configurations using the seldon config deactivate CLI command. This command allows you to disable and remove active configurations from your Seldon Core deployment. - [Config Add](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config_add.md): Learn how to add new configurations to Seldon Core using the seldon config add CLI command. This command allows you to create and store new configuration profiles for your Seldon Core deployment. - [Config List](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config_list.md): Learn how to view and list all Seldon Core configurations using the seldon config list CLI command. This command displays all available configuration profiles in your Seldon Core deployment. - [Config Remove](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon/seldon_config_remove.md) - [Experiment](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_experiment.md) - [Experiment Start](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_experiment/seldon_experiment_start.md) - [Experiment Status](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_experiment/seldon_experiment_status.md) - [Experiment List](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_experiment/seldon_experiment_list.md) - [Experiment Stop](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_experiment/seldon_experiment_stop.md) - [Model](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model.md) - [Model Status](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_status.md) - [Model Load](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_load.md) - [Model List](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_list.md) - [Model Infer](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_infer.md) - [Model Metadata](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_metadata.md) - [Model Unload](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_model/seldon_model_unload.md) - [Pipeline](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline.md) - [Pipeline Load](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_load.md) - [Pipeline Status](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_status.md) - [Pipeline List](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_list.md) - [Pipeline Inspect](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_inspect.md) - [Pipeline Infer](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_infer.md) - [Pipeline Unload](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_pipeline/seldon_pipeline_unload.md) - [Server](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_server.md) - [Server List](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_server/seldon_server_list.md) - [Server Status](https://docs.seldon.ai/seldon-core-2/v2.10/resources/apis/cli/seldon_server/seldon_server_status.md) - [FAQs](https://docs.seldon.ai/seldon-core-2/v2.10/resources/faqs.md): Find answers to common questions about Seldon Core, including installation, configuration, model deployment, and troubleshooting. - [Development](https://docs.seldon.ai/seldon-core-2/v2.10/resources/development.md) - [License](https://docs.seldon.ai/seldon-core-2/v2.10/resources/development/licenses.md) - [Release](https://docs.seldon.ai/seldon-core-2/v2.10/resources/development/release.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on a page URL with the `ask` query parameter: ``` GET https://docs.seldon.ai/seldon-core-2/about/readme.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.