# Vespa > The Vespa documentation ([provides all the information required to use all Vespa features and deploy them in any supported environment. ## Pages - [About this documentation](about-documentationhtml.md): The Vespa documentation ([provides all the information required to u... - [Access Logging](access-logginghtml.md): The Vespa access log format allows the logs to be processed by a number of available tools handling JSON based (log) ... - [Administrative Procedures](admin-procedureshtml.md): Refer to the [multinode-HA](https://github.com/vespa-engine/sample-apps/tree/master/examples/operations/multinode-HA)... - [services.xml - 'admin'](adminhtml.md): Reference documentation for``in [services.xml](services.html). Find a working example of this configuration ... - [Vespa API and interfaces](apihtml.md): - [Deploy API](deploy-v2.html): Deploy [application packages](../../basics/applications.html) to configure a Vespa ap... - [Application package reference](application-packageshtml.md): This is the [application package](../../basics/applications.html) reference. An application package is the deployment... - [/application/v2/tenant API reference](application-v2html.md): This is the /application/v2/tenant API reference with examples for the HTTP REST API to list, [creat... - [Vespa applications](applicationshtml.md): You use Vespa by deploying an _application_ to it. Why applications? Because Vespa handles both data and the computat... - [Approximate nearest neighbor search using HNSW index](approximate-nn-hnswhtml.md): This document describes how to speed up searches for nearest neighbors in vector spaces by adding[HNSW index](../refe... - [Architecture](architecturehtml.md): The Vespa Operator is an implementation of the [Operator Pattern](https://kubernetes.io/docs/concepts/extend-kubernet... - [AWS Archive guide](archive-guide-awshtml.md): Vespa Cloud exports log data, heap dumps, and Java Flight Recorder sessions to buckets in AWS S3. This guide explains... - [GCP Archive guide](archive-guide-gcphtml.md): Vespa Cloud exports log data, heap dumps, and Java Flight Recorder sessions to buckets in Google Cloud Storage. This ... - [Archive guide](archive-guidehtml.md): Vespa Cloud exports log data, heap dumps, and Java Flight Recorder sessions to storage buckets. The bucket system use... - [Log archive in Vespa Cloud Enclave](archivehtml.md): **Warning:** The structure of log archive buckets may change without notice - [Attributes](attributeshtml.md): An _attribute_ is a [schema](../reference/schemas/schemas.html#attribute) keyword, specifying the indexing for a field: - [Automated Deployments](automated-deploymentshtml.md): Vespa Cloud provides: - [Autoscaling](autoscalinghtml.md): Autoscaling lets you adjust the hardware resources allocated to application clusters automatically depending on actua... - [Vespa Cloud Enclave AWS Architecture](aws-architecturehtml.md): Each Vespa Cloud Enclave in the tenant AWS account corresponds to a Vespa Cloud[zone](../zones.html). Inside the tena... - [Getting started with Vespa Cloud Enclave in AWS](aws-getting-startedhtml.md): Setting up Vespa Cloud Enclave requires: - [Architecture for Vespa Cloud Enclave in Azure](azure-architecturehtml.md): With Vespa Cloud Enclave, all Azure resources associated with your Vespa Cloud applications are in your enclave Azure... - [Getting started with Vespa Cloud Enclave in Azure](azure-getting-startedhtml.md): Setting up Vespa Cloud Enclave requires: - [Batch delete](batch-deletehtml.md): Options for batch deleting documents: - [Benchmarking](benchmarking-cloudhtml.md): This is a step-by-step guide to get started with benchmarking on Vespa Cloud, based on the [Vespa benchmarking guide]... - [Vespa Benchmarking](benchmarkinghtml.md): Benchmarking a Vespa application is essential to get an idea of how well the test configuration performs. Thus, bench... - [Binarizing Vectors](binarizing-vectorshtml.md): Binarization in this context is mapping numbers in a vector (embedding) to bits (reducing the value range), and repre... - [The BM25 rank feature](bm25html.md): The[bm25 rank feature](../reference/ranking/rank-features.html#bm25)implements the[Okapi BM25](https://en.wikipedia.o... - [Buckets](bucketshtml.md): The content layer splits the document space into chunks called _buckets_, and algorithmically maps documents to bucke... - [Build / install Vespa](build-installhtml.md): To develop with Vespa, follow the [guide](https://github.com/vespa-engine/vespa#building) to set up a development env... - [Bundles](bundleshtml.md): The Container uses [OSGi](https://osgi.org) to provide a modular platform for developing applications that can be com... - [Caches](caches-in-vespahtml.md): The summary cache caches summary requests and is enabled by [proton tuning configuration](../reference/applications/s... - [Chained Components](chaininghtml.md): It is useful to read the [federation guide](../querying/federation.html) before this document. - [Chunking Reference](chunkinghtml.md): Reference configuration for _chunkers_: Components that splits text into pieces in[chunk indexing expressions](../wri... - [Cloning applications and data](cloninghtml.md): This is a guide on how to replicate a Vespa application in different environments, with or without data. Use cases fo... - [Using Cloudflare Workers with Vespa Cloud](cloudflare-workershtml.md): This guide describes how you can access mutual TLS protected Vespa Cloud endpoints using[Cloudflare Workers](https://... - [/cluster/v2 API reference](cluster-v2html.md): The cluster controller has a /cluster/v2 API for viewing and modifying a content cluster state. To find the URL to ac... - [ClusterController Metrics](clustercontrollerhtml.md): | Name | Unit | Description | - [Component reference](componentshtml.md): A component is any Java class whose lifetime is controlled by the container, see the [Developer Guide](../../applicat... - [Concrete documents](concrete-documentshtml.md): In [document processing](../applications/document-processors.html),`setFieldValue()`and`getFieldValue()`is used to ... - [Custom Configuration File Reference](config-fileshtml.md): This is the reference for config file definitions. It is useful for developing applications that has[configurable com... - [Configuration proxy](config-proxyhtml.md): Read [application packages](../../basics/applications.html) for an overview of the cloud config system. The _config p... - [Config sentinel](config-sentinelhtml.md): The config sentinel starts and stops services - and restart failed services unless they are manually stopped. All nod... - [The Config System](config-systemhtml.md): The config system in Vespa is responsible for turning the application package into live configuration of all the node... - [Config API](config-v2html.md): Vespa provides a REST API for listing and retrieving config - alternatives are the [programmatic Java API](../../appl... - [Cloud Config API](configapi-devhtml.md): This document describes how to use the C++ and Java versions of the Cloud config API (the 'config API'). This API is ... - [ConfigServer Metrics](configserverhtml.md): | Name | Unit | Description | - [Configuration Servers](configuration-serverhtml.md): Vespa Configuration Servers host the endpoint where application packages are deployed - and serves generated configur... - [Configuring Java components](configuring-componentshtml.md): Any Java component might require some sort of configuration, be it simple strings or integers, or more complex struct... - [Vespa Consistency Model](consistencyhtml.md): Vespa offers configurable data redundancy with eventual consistency across replicas. It's designed for high efficienc... - [Constant Tensor JSON Format](constant-tensor-json-formathtml.md): This document describes with examples the JSON formats accepted when reading tensor constants from a file. For conven... - [HTTP Performance Testing of the Container using Gatling](container-httphtml.md): For container testing, more flexibility and more detailed checking than straightforward saturating an interface with ... - [Container Tuning](container-tuninghtml.md): A collection of configuration parameters to tune the Container as used in Vespa. Some configuration parameters have n... - [Container](containerhtml.md): This is the Container service operational guide. - [Container clusters](containershtml.md): Vespa's Java container - JDisc, hosts all application components as well as the stateless logic of Vespa itself. Whic... - [Content node recovery](content-node-recoveryhtml.md): In exceptional cases, one or more content nodes may end up with corrupted data causing it to fail to restart. Possibl... - [Content nodes, states and metrics](content-nodeshtml.md): Content cluster processes are _distributor_, _proton_ and _cluster controller_. - [services.xml - 'content'](contenthtml.md): The root element of a Content cluster definition. Creates a content cluster. A content cluster stores and/or indexes ... - [Contributing to Vespa](contributinghtml.md): Contributions to [Vespa](http://github.com/vespa-engine/vespa)and the [Vespa documentation](http://github.com/vespa-e... - [CPU Support](cpu-supporthtml.md): For maximum performance, the current version of Vespa for x86\_64 is compiled only for [Haswell (2013)](https://en.wi... - [Ranking With Transformer Cross-Encoder Models](cross-encodershtml.md): [Cross-Encoder Transformer](https://blog.vespa.ai/pretrained-transformer-language-models-for-search-part-4/) based te... - [Provide Custom Overrides](custom-overrides-podtemplatehtml.md): While services.xml defines the Vespa application specification, it abstracts away the underlying Kubernetes infrastru... - [Data management and backup](data-managementhtml.md): This guide documents how to export data from a Vespa cloud application and how to do mass updates or removals. See [c... - [Default Metric Set](default-metric-sethtml.md): This document provides reference documentation for the Default metric set, including suffixes present per metric. If ... - [Default JSON Result Format](default-result-formathtml.md): The default Vespa query response format is used when [presentation.format](../api/query.html#presentation.format) is ... - [Deleting Applications](deleting-applicationshtml.md): **Warning:** Following these steps will remove production instances or regions and all data within them. Data will be... - [Dependency injection](dependency-injectionhtml.md): The Container (a.k.a. JDisc container) implements a dependency injection framework that allows components to declare ... - [Deploy an application having Java components](deploy-an-application-javahtml.md): Follow these steps to deploy a Vespa application which includes Java components to the [dev zone](../operations/envir... - [Deploy an application having Java components locally](deploy-an-application-local-javahtml.md): Follow these steps to deploy a Vespa application having Java components on your own machine. - [Deploy an application locally](deploy-an-application-localhtml.md): Follow these steps to deploy a Vespa application on your own machine. - [Deploy an application without Vespa CLI](deploy-an-application-shellhtml.md): This lets you deploy an application to the [dev zone](../operations/environments.html#dev)on Vespa Cloud (for free). - [Deploy an application](deploy-an-applicationhtml.md): Follow these steps to deploy a Vespa application to the [dev zone](../operations/environments.html#dev)on Vespa Cloud... - [Deploy API](deploy-v2html.md): This is the API specification and some examples for the HTTP Deploy API that can be used to deploy an application: - [Deployment patterns](deployment-patternshtml.md): Vespa Cloud's [automated deployments](automated-deployments.html)lets you design CD pipelines for staged rollouts and... - [Instance, region, cloud and environment variants](deployment-variantshtml.md): Sometimes it is useful to create configuration that varies depending on properties of the deployment, for example to ... - [deployment.xml reference](deploymenthtml.md): _deployment.xml_ controls how an application is deployed. - [Developer Guide](developer-guidehtml.md): This document explains how to develop applications, including basic terminology, tips on using the Vespa Cloud Consol... - [Distributor Metrics](distributorhtml.md): | Name | Unit | Description | - [Docker containers](docker-containershtml.md): This document describes tuning and adaptions for running Vespa Docker containers, for developer use on laptop, and in... - [services.xml - document-processing](docprochtml.md): This is the [document-processing](../../../applications/document-processors.html)reference in [services.xml](services... - [Document API](document-api-guidehtml.md): This is an introduction to how to build and compile Vespa clients using the Document API. It can be used for feeding,... - [Document enrichment with LLMs](document-enrichmenthtml.md): Document enrichment enables automatic generation of document field values using large language models (LLMs) or custo... - [Document field path reference](document-field-pathhtml.md): The field path syntax is used several places in Vespa to traverse documents through arrays, structs, maps and sets an... - [Document JSON format reference](document-json-formathtml.md): This document describes the JSON format used for sending document operations to Vespa. Field types are defined in the... - [Document processors](document-processorshtml.md): This document describes how to develop and deploy _Document Processors_, often called _docproc_ in this documentation... - [Routing](document-routinghtml.md): _Routing_ is used to configure the paths that documents and updates written to Vespa take through the system. Vespa w... - [Document selector language reference](document-selector-languagehtml.md): This document describes the _document selector language_, used to select a subset of documents when feeding, dumping ... - [Document Summaries](document-summarieshtml.md): A _document summary_ is the information that is shown for each document in a query result. What information to includ... - [/document/v1 API guide](document-v1-api-guidehtml.md): Use the _/document/v1/_ API to read, write, update and delete documents. - [/document/v1 API reference](document-v1html.md): This is the /document/v1 API reference documentation. Use this API for synchronous [Document](../../schemas/documents... - [Documents](documentshtml.md): Vespa models data as _documents_. A document has a string identifier, set by the application, unique across all docum... - [Use Case - shopping](e-commercehtml.md): The [e-commerce, or shopping, use case](https://github.com/vespa-engine/sample-apps/tree/master/use-case-shopping)is ... - [Content cluster elasticity](elasticityhtml.md): Vespa clusters can be grown and shrunk while serving queries and writes. Documents in content clusters are automatica... - [Embedding Reference](embeddinghtml.md): Reference configuration for [embedders](../../rag/embedding.html). - [Vespa Cloud Enclave](enclavehtml.md): Vespa Cloud Enclave allows Vespa Cloud applications to run inside the tenant's own cloud accounts while everything is... - [Routing and endpoints](endpoint-routinghtml.md): Vespa Cloud supports multiple methods of routing requests to an application. This guide describes how these routing m... - [Environments](environmentshtml.md): Vespa Cloud has two kinds of environments: - [Exposing schema information](exposing-schema-informationhtml.md): Some applications need to expose information about schemas to data plane clients. This document explains how to add a... - [External LLMs in Vespa](external-llmshtml.md): Please refer to [Large Language Models in Vespa](llms-in-vespa.html) for an introduction to using LLMs in Vespa. - [FAQ - frequently asked questions](faqhtml.md): Refer to [Vespa Support](https://vespa.ai/support/) for more support options. - [Vespa Serving Tuning](feature-tuninghtml.md): This document describes how to tune certain features of an application for high query serving performance, where the ... - [Features](featureshtml.md): Vespa is a platform for applications which need low-latency computation over large data sets. It allows you to write ... - [Federation](federationhtml.md): The Vespa Container allows multiple sources of data to be _federated_ to a common search service. The sources of data... - [Feed block](feed-blockhtml.md): A content cluster blocks external write operations when at least one content node has reached the [resource limit](..... - [Files, Processes, Ports, Environment](files-processes-and-portshtml.md): This is a reference of directories used in a Vespa installation, processes that run on the Vespa nodes and ports / en... - [Architecture for Vespa Cloud Enclave in GCP](gcp-architecturehtml.md): Each Vespa Cloud Enclave in the tenant GCP project corresponds to a Vespa Cloud[zone](../zones.html). Inside the tena... - [Getting started with Vespa Cloud Enclave in GCP](gcp-getting-startedhtml.md): Setting up Vespa Cloud Enclave requires: - [Geo Search](geo-searchhtml.md): To model a geographical position in documents, use a field where the type is [position](../reference/schemas/schemas.... - [Glossary](glossaryhtml.md): This is a glossary of both Vespa-specific terminology, and general terms useful in this context. - [Graceful Query Coverage Degradation](graceful-degradationhtml.md): Ideally you want to query all data indexed in a Vespa cluster within the specified timeout, but that might not always... - [Grouping Reference](grouping-languagehtml.md): Read the [Vespa grouping guide](/en/querying/grouping.html) first, for examples and an introduction to grouping - thi... - [Grouping and aggregation](groupinghtml.md): Try running requests on the [grouping example data](https://github.com/vespa-engine/sample-apps/blob/master/examples/... - [Security Guide](guidehtml.md): Vespa Cloud has several security mechanisms it is important for developers to understand. Vespa Cloud has two differe... - [Health checks reference](health-checkshtml.md): This is the reference for loadbalancer healthchecks to [containers](../../applications/containers.html). - [hosts.xml](hostshtml.md): _hosts.xml_ is a configuration file in an [application package](application-packages.html). Elements: - [Building an HTTP API using request handlers and processors](http-apihtml.md): This tutorial builds a simple application consisting of these pieces: - [HTTP Best Practices](http-best-practiceshtml.md): As connections to a JDisc container cluster are terminated at the individual container nodes, the cost of connection ... - [Http servers and filters](http-servers-and-filtershtml.md): This document explains how to set up http servers and filters in the Container. Before proceeding, familiarize with t... - [services.xml - http](httphtml.md): This is the reference for the`http`subelement of[container](container.html) in [services.xml](services.html). The h... - [HTTP/2](http2html.md): This document contains HTTP/2 performance considerations on the container—see [Container tuning](container-tuning.htm... - [Hybrid Text Search Tutorial](hybrid-searchhtml.md): Hybrid search combines different retrieval methods to improve search quality. This tutorial distinguishes between two... - [IDE support](ide-supporthtml.md): Vespa provides plugins for working with schemas and rank profiles in IDE's: - [Distribution Algorithm](idealstatehtml.md): The distribution algorithm decides what nodes should be responsible for a given bucket. This is used directly in the ... - [Tutorials and use cases](indexhtml.md): - [Tutorial: Text Search](text-search). A text search tutorial and introduction to text ranking with Vespa using trad... - [Indexing language reference](indexing-languagehtml.md): This reference documents the full Vespa _indexing language_. If more complex processing of input data is required, im... - [Indexing paged vectors](indexing-paged-vectorshtml.md): Most of the data of a vector (tensor) index is the vectors themselves. The vector data must be accessed to calculate ... - [Indexing](indexinghtml.md): Refer to the [overview](../learn/overview.html). The primary index configuration is the [schema](../basics/schemas.ht... - [Configure External Access Layer](ingresshtml.md): The Vespa Operator automatically provisions Kubernetes`Service`resources to enable external access for feeding and ... - [Inheritance in schemas](inheritance-in-schemashtml.md): Both document types and full schemas can be inherited to make it easy to design a structured application package with... - [Initial batch feed](initial-batch-feedhtml.md): One of the first things you do when creating a Vespa application is deploying it to Vespa Cloud and batch feeding all... - [Inspecting structured data in a Searcher](inspecting-structured-datahtml.md): The [Data Access API](https://javadoc.io/doc/com.yahoo.vespa/vespajlib/latest/com/yahoo/data/access/package-summary.h... - [Install Vespa on Kubernetes](installationhtml.md): The Vespa Operator should be installed using the official Helm chart. - [Vespaドキュメンテーションの紹介](introduction-to-documentationhtml.md): このドキュメンテーションはVespaの利用者、あるいは潜在的な利用者（アプリケーションの所有者 / PM、エンジニアまたは運用者）のためのものです。 このドキュメンテーションはプロダクトの概念上の概要をカバーしており、それには背景的な... - [Select Query Reference](json-query-languagehtml.md): This document describes what the`select`parameter is and gives a few examples on how to use it. Refer to the [Query... - [Ranking with LightGBM Models](lightgbmhtml.md): [LightGBM](https://github.com/microsoft/LightGBM) is a gradient boosting framework, similar to [XGBoost](xgboost). Am... - [Custom Linguistics](linguistics-customhtml.md): A linguistics component is an implementation of[com.yahoo.language.Linguistics](https://github.com/vespa-engine/vespa... - [OpenNLP Linguistics](linguistics-opennlphtml.md): The default Vespa linguistics implementation uses [OpenNLP](https://opennlp.apache.org/). The Apache OpenNLP language... - [Linguistics in Vespa](linguisticshtml.md): Vespa uses a _linguistics_ module to process text in queries and documents during indexing and searching. The goal of... - [Live-upgrading Vespa](live-upgradehtml.md): This document describes how to live upgrade a Vespa instance. Use this procedure to upgrade without disruption to rea... - [Getting help from LLMs](llm-helphtml.md): This page describes some of the ways that you can get help from large language models (LLMs) when developing a Vespa ... - [Large Language Models in Vespa](llms-in-vespahtml.md): Large Language Models (LLMs) are AI systems that generate human-like text, supporting a variety of applications like ... - [Running LLMs inside your Vespa application](local-llmshtml.md): Please refer to [Large Language Models in Vespa](llms-in-vespa.html) for an introduction to using LLMs in Vespa. - [Log file reference](log-fileshtml.md): All Vespa components use a common log module for logging. These log messages are added to a local log file in _$VESPA... - [Logd Metrics](logdhtml.md): | Name | Unit | Description | - [Configure Log Collection](logginghtml.md): Use the Fluent Bit Operator to collect logs and forward them to Grafana Cloud Loki. - [Lucene Linguistics](lucene-linguisticshtml.md): Lucene Linguistics is a custom [linguistics](linguistics.html) implementation of the [Apache Lucene](https://lucene.a... - [Memory Visualizer](memory-visualizerhtml.md): The [schema](../basics/schemas.html) defines fields, types of fields and settings per field, e.g. - [Metric Units Reference](metric-unitshtml.md): | Unit | Description | - [/metrics/v1 API reference](metrics-v1html.md): The _node metrics API_ is available on each _node_ at the metrics proxy port, default _http://host:19092/metrics/v1/v... - [/metrics/v2 API reference](metrics-v2html.md): The _application metrics API_ is available on each _node_ at the metrics proxy port, default _http://host:19092/metri... - [Metrics Reference](metricshtml.md): Each metric have one of the types documented [here](metric-units.html). - [Migrating from Elasticsearch](migrating-from-elastic-searchhtml.md): This is a guide for how to move data from Elasticsearch to Vespa. By the end of this guide you will have exported doc... - [Migrating to Vespa Cloud](migrating-to-cloudhtml.md): Migrating a Vespa application to Vespa Cloud is straightforward, as applications on Vespa Cloud supports all the same... - [Stateless model reference](model-fileshtml.md): _.model_ files are used in[stateless model evaluation](../../ranking/stateless-model-evaluation.html). These are file... - [Using machine-learned models from Vespa Cloud](model-hubhtml.md): Vespa Cloud provides a set of machine-learned models that you can use in your applications. These models will always ... - [Monitoring](monitoringhtml.md): Vespa provides metrics integration with CloudWatch, Datadog and Prometheus / Grafana, as well as a JSON HTTP API. - [Mutually authenticated TLS (mTLS) reference](mtlshtml.md): **Note:** See [Securing a self-hosted Vespa application with mutually authenticated TLS (mTLS)](../../security/mtls) ... - [Multi-Currency Pricing](multi-currency-filteringhtml.md): Vespa for e-commerce includes multi-currency pricing support for e-commerce applications with global product catalogs... - [Multinode systems](multinode-systemshtml.md): A Vespa _system_ consists of one or more stateless and stateful clusters configured by an application package. A Vesp... - [Multivalue Query Operators](multivalue-query-operatorshtml.md): This article is a followup to the [ranking introduction](ranking-intro). Some use cases in this guide are better solv... - [nativeRank Reference](nativerankhtml.md): The _nativeRank_ feature produces a reasonable text ranking score which is computed at an acceptable performance, and... - [Vespa nearest neighbor search - a practical guide](nearest-neighbor-search-guidehtml.md): This guide is a practical introduction to using Vespa nearest neighbor search query operator and how to combine neare... - [Nearest Neighbor Search](nearest-neighbor-searchhtml.md): Nearest neighbor search, or vector search, is a technique used to find the closest data points to a given query point... - [News search and recommendation tutorial - getting started on Docker](news-1-deploy-an-applicationhtml.md): Our goal with this series is to set up a Vespa application for personalized news recommendations. We will do this in ... - [News search and recommendation tutorial - applications, feeding and querying](news-2-basic-feeding-and-queryhtml.md): This is the second part of the tutorial series for setting up a Vespa application for personalized news recommendatio... - [News search and recommendation tutorial - searching](news-3-searchinghtml.md): This is the third part of the tutorial series for setting up a Vespa application for personalized news recommendation... - [News search and recommendation tutorial - embeddings](news-4-embeddingshtml.md): This is the fourth part of the tutorial series for setting up a Vespa application for personalized news recommendatio... - [News search and recommendation tutorial - recommendations](news-5-recommendationhtml.md): This is the fifth part of the tutorial series for setting up a Vespa application for personalized news recommendation... - [News search and recommendation tutorial - Searchers](news-6-recommendation-with-searchershtml.md): This is the sixth part of the tutorial series for setting up a Vespa application for personalized news recommendation... - [News Recommendation Tutorial - parent child and tensor ranking](news-7-recommendation-with-parent-childhtml.md): This is the seventh part of the tutorial series for setting up a Vespa application for personalized news recommendati... - [Node Resources](node-resourceshtml.md): This guide goes through the following aspects of node resource configuration: - [Node and network setup](node-setuphtml.md): Vespa is composed of services that communicate and interact with each other. These services can be partitioned onto a... - [NodeAdmin Metrics](nodeadminhtml.md): | Name | Unit | Description | - [Notifications](notificationshtml.md): Vespa Cloud supports two different categories of notifications. Notifications can be sent by email if this has been c... - [Ranking With ONNX Models](onnxhtml.md): Vespa supports advanced ranking models through its tensor API. If your model is in the [ONNX format](https://onnx.ai/... - [Lifecycle Operations for Vespa on Kubernetes](operationshtml.md): The ConfigServer and Vespa Application Pods have built-in resilience and recovery capabilities; they are automaticall... - [Vespaの概要](overviewhtml.md): Vespaはスケーラブルで低レイテンシな、ステートフルあるいはステートレスなバックエンドサービスを簡単に開発して稼働させることができるプラットフォームです。 このドキュメントではプラットフォームの機能と主なコンポーネントの概要を説明します。 - [The 'page' result format](page-result-formathtml.md): This document describes the`page`result format returned by Vespa. This result format is used when [presentation.for... - [Page templates reference](page-templateshtml.md): This document is a reference to the elements of the Page Template XML format. Refer to the [Introduction to Page Temp... - [Parent/Child](parent-childhtml.md): Using [document references](../reference/schemas/schemas.html#reference), documents can have parent/child relationshi... - [Partial Updates](partial-updateshtml.md): A partial update is an update to one or more fields in a document. It also includes updating all index structures so ... - [Phased Ranking](phased-rankinghtml.md): Vespa allows expressing multiphased retrieval and ranking of documents. The retrieval phase is done close to the data... - [Using pluggable frameworks](pluggable-frameworkshtml.md): Many libraries provide pluggable architectures via Service Provider Interfaces (SPI). Using such libraries usually re... - [Vespa query performance - a practical guide](practical-search-performance-guidehtml.md): This is a practical Vespa query performance guide. It uses the[Last.fm](http://millionsongdataset.com/lastfm/) tracks... - [Predicate Fields](predicate-fieldshtml.md): _[Predicate](../reference/schemas/schemas.html#predicate) fields_provides a way to match queries to a set of _boolean... - [Private endpoints](private-endpointshtml.md): Vespa Cloud lets you set up private endpoint services on your application clusters, for exclusive access from your ow... - [Procedure: Change from attribute to index](procedure-change-attribute-indexhtml.md): Changing between`index`and`attribute`is a common field change operation to optimize performance. Use the [reindex... - [services.xml - processing](processinghtml.md): This document explains the syntax and semantics of the`processing`subelement of the [`container`](container.html) p... - [Production Deployment](production-deploymenthtml.md): Production zones enable serving from various locations, with a [CI/CD pipeline](automated-deployments.html) for safe ... - [Profiling](profilinghtml.md): Guidelines when profiling: - [/prometheus/v1 API reference](prometheus-v1html.md): The _prometheus node metrics API_ is available on each _node_ at the metrics proxy port, default _http://host:19092/p... - [Proton](protonhtml.md): Proton is Vespa's search core and runs on each content node as the _vespa-proton-bin_ process. Proton maintains disk ... - [Query API](query-apihtml.md): Use the Vespa Query API to query, rank and organize data. Example: - [Vespa Query Language - YQL](query-languagehtml.md): Vespa accepts unstructured human input and structured queries for application logic separately, then combines them in... - [Query Profile Reference](query-profileshtml.md): This is a reference to the full format of Query Profile and[Query Profile Type](#query-profile-typ... - [Query Rewriting](query-rewritinghtml.md): A search application can improve the quality by interpreting the intended meaning of the user queries. Once the meani... - [Query API Reference](queryhtml.md): Refer to the [Query API guide](../../querying/query-api.html) for API examples. - [Querying](queryinghtml.md): An introduction to querying with Vespa. - [RAG Blueprint](rag-blueprinthtml.md): Many of our users use Vespa to power large scale RAG Applications. - [Retrieval-augmented generation (RAG) in Vespa](raghtml.md): Please refer to [Large Language Models in Vespa](llms-in-vespa) for an introduction to using LLMs in Vespa. - [Rank Feature Configuration](rank-feature-configurationhtml.md): For some [rank features](rank-features.html), it is possible to set configuration variables for how the features are ... - [Rank Feature Reference](rank-featureshtml.md): This is the list of the rank features in Vespa. These features are available during document ranking for combination ... - [Rank Types](rank-typeshtml.md): This document presents the [rank-types](../schemas/schemas.html#rank-type) that are supported by nativeRank and the m... - [Ranking Expressions and Features](ranking-expressions-featureshtml.md): Read the [ranking introduction](../basics/ranking.html) first. This guide is about [ranking expressions](../reference... - [Ranking Expressions](ranking-expressionshtml.md): This is a complete reference to the _ranking expressions_ used to configure application specific ranking functions. F... - [Introduction to ranking](ranking-introhtml.md): Learn how [ranking](../basics/ranking.html) works in Vespa by using the open [query API](../querying/query-api.html) ... - [Ranking](rankinghtml.md): _Ranking_ in Vespa is the computation that is done on matching documents during query execution. These are specified ... - [Rate Limiting Search Requests](rate-limiting-searcherhtml.md): To avoid overloading a Vespa content cluster or to limit query load from e.g. certain clients, the bundled [Vespa Rat... - [Reads and writes](reads-and-writeshtml.md): This guide covers the aspects of accessing [documents](../schemas/documents.html) in Vespa. Documents are stored in _... - [Reindexing](reindexinghtml.md): When the indexing pipeline of a Vespa application changes, Vespa may automatically refeed stored data such that the i... - [Releases](releaseshtml.md): Vespa is released every Monday through Thursday. Each public release has passed all functional and performance tests,... - [Request handlers](request-handlershtml.md): This document explains how to implement and deploy a custom request handler. - [Re-ranking using a custom Searcher](reranking-in-searcherhtml.md): This guide demonstrates how to deploy a [searcher](../applications/searchers.html) implementing a last stage of [phas... - [Result Diversity](result-diversityhtml.md): In Search and Recommendation applications, the highest-ranking documents are displayed to the user. A document’s rank... - [Result renderers](result-renderershtml.md): Vespa provides a default JSON format for query results. _Renderers_ can be configured to implement custom formats, li... - [Saved search notifications](saved-searchhtml.md): Vespa for e-commerce includes a module for storing queries in Vespa ("searches") and issuing notifications when a new... - [Schema reference](schemashtml.md): This reference documents the syntax and content of schemas, document types, and fields. This is a reference, see [sch... - [services.xml - 'search'](searchhtml.md): This is the reference for the _search_ part of the container config. Related: [Chained components](../../../applicati... - [**Search results from](search-betahtml.md): **Search results from - [Searchers](searchershtml.md): The _Container_ is the home for all global processing of user actions (represented as queries) and their results. It ... - [Searching and ranking of multivalued fields](searching-multivalue-fieldshtml.md): This guide explains how to search and rank over structured multivalued fields. The examples in this guide use the [we... - [SearchNode Metrics](searchnodehtml.md): | Name | Unit | Description | - [Secret Store](secret-storehtml.md): Vespa Cloud supports secure storage and management of secrets for use in your application. A secret is a text-based v... - [Securing a Vespa Installation](securing-your-vespa-installationhtml.md): **Note:** This document is only relevant for **self-hosting Vespa** as Vespa Cloud does this for you. - [Vespa Cloud Security](securityhtml.md): - [**Security Guide**](guide) is a practical guide to using the different security features and getting started with ... - [Semantic Rule Language Reference](semantic-ruleshtml.md): This is the reference for the semantic rule language in Vespa. For a guide on using this language, see [query rewriti... - [Sentinel Metrics](sentinelhtml.md): | Name | Unit | Description | - [services.xml](serviceshtml.md): _services.xml_ specifies the clusters an application should have and their capabilities. It is placed in the root of ... - [Significance Model](significancehtml.md): _Significance_ is a measure of how rare a term is in a collection of documents. Rare terms like "neurotransmitter" ar... - [Simple Query Language Reference](simple-query-languagehtml.md): The _simple query language_ allows application end users to issue more complex queries than a list of tokens. It is a... - [Table of contents](sitemaphtml.md): - [Deploy an application](/en/basics/deploy-an-application.html) - [Vespa Scaling Configuration Examples](sizing-exampleshtml.md): This guide has a set of example configurations for content clusters using flat or grouped data distribution. Data is ... - [Vespa Feed Sizing Guide](sizing-feedinghtml.md): Vespa is optimized to sustain a high feed load while serving - also during planned and unplanned changes to the insta... - [Vespa Serving Scaling Guide](sizing-searchhtml.md): _Vespa can scale in multiple scaling dimensions:_ - [Service location broker - slobrok](slobrokhtml.md): Slobrok is an acronym for _Service Location Broker_, and it is a name service used in Vespa. The service listens on a... - [Sorting Reference](sorting-languagehtml.md): A sorting specification in a query consists of one or more sorting expressions. Each sorting expression is an optiona... - [/state/v1 API reference](state-v1html.md): Every service exposes the`/state/v1`API - use [vespa-model-inspect](/en/reference/operations/self-managed/tools.htm... - [Stateless Model Evaluation](stateless-model-evaluationhtml.md): Vespa's speciality is evaluating machine-learned models quickly over large numbers of data points. However, it can al... - [Storage Metrics](storagehtml.md): | Name | Unit | Description | - [Streaming Search](streaming-searchhtml.md): Search engines make queries fast by creating indexes over the stored data. While the indexes cost extra resources to ... - [String Segment Match](string-segment-matchhtml.md): The **string segment match** algorithm computes a set of metrics - the **string segment match metrics** - intended to... - [Structs](structshtml.md): This document explains how to use structs in Vespa documents. - [Tenants, Applications and Instances](tenant-apps-instanceshtml.md): When registering for Vespa Cloud, a _tenant_ is created. Tenant is the billable unit, and most often represents an or... - [Tensor Computation Examples](tensor-exampleshtml.md): Tensors can be used to express machine-learned models such as neural nets, but they can be used for much more than th... - [Tensor Guide](tensor-user-guidehtml.md): Vespa provides a _tensor_ data model and computation engine to support advanced computations over data. This guide ex... - [Tensor Reference](tensorhtml.md): A tensor is a set of named _dimensions_ defining its _order_ and a set of values located in the space of those dimens... - [Ranking with TensorFlow Models](tensorflowhtml.md): Vespa can import TensorFlow models converted to the ONNX format. The tutorial [TensorFlow: Deploy model to Vespa thro... - [Testing with Java JUnit tests](testing-javahtml.md): This is the Vespa Testing reference for [Vespa application system tests](../../applications/testing.html) written in ... - [Basic HTTP testing](testinghtml.md): This is the Vespa Testing reference for basic HTTP tests, used to write [Vespa application system tests](../../applic... - [Text Matching](text-matchinghtml.md): This guide demonstrates tokenization, linguistic processing and matching over [string](../reference/schemas/schemas.h... - [Improving Text Search through ML](text-search-mlhtml.md): At this point, we assume you have read our [Text Search Tutorial](text-search.html) and accomplished the following st... - [Text Search Tutorial](text-searchhtml.md): This tutorial will guide you through setting up a simple text search application. At the end, you can index text docu... - [Enable TLS Encryption for Vespa on Kubernetes](tlshtml.md): TLS encryption for Vespa on Kubernetes can be configured for internal pod-to-pod communication using mutual TLS (mTLS... - [Vespa Command-line Tools](toolshtml.md): This is the reference for the Vespa command-line tools. - [Topology and Resizing](topology-and-resizinghtml.md): Vespa has features to optimize cost, query latency, and throughput, at the same time, making tradeoffs for availabili... - [Troubleshooting character encoding](troubleshooting-encodinghtml.md): This document helps recognize the most common problems related to Unicode and I18N. - [Unit testing](unit-testinghtml.md): This document describes how to test application functionality in a local Java vm. See [automated deployments](../oper... - [Using Kubernetes with Vespa](using-kubernetes-with-vespahtml.md): This article outlines how to run Vespa using Kubernetes. Find a quickstart for running Vespa in a single pod in [sing... - [Using ZooKeeper](using-zookeeperhtml.md): The Vespa container supports [ZooKeeper](https://zookeeper.apache.org/), which allows distributed synchronization acr... - [Using Valgrind with Vespa](valgrindhtml.md): Valgrind is a useful tool to investigate bugs, and to get a detailed performance profile of an application after [pro... - [validation-overrides.xml](validation-overrideshtml.md): _validation-overrides.xml_ is added to the root of an [application package](application-packages.html) (i.e. next to ... - [An intro to vector search](vector-search-introhtml.md): Vector Search is a method to search objects using a digital representation of both the query and the objects - easier... - [Vespa CLI](vespa-clihtml.md): Vespa CLI is the command-line client for Vespa. It is a single binary without any runtime dependencies and is availab... - [vespa-feed-client](vespa-feed-clienthtml.md): - Java library and command line client for feeding document operations using [Document v1](../writing/document-v1-api... - [Container GPU setup](vespa-gpu-containerhtml.md): Vespa supports using GPUs to evaluate ONNX models, as part of its [stateless model evaluation feature](../../ranking/... - [Vespa Metric Set](vespa-metric-sethtml.md): This document provides reference documentation for the Vespa metric set, including suffixes present per metric. If th... - [Vespa on Kubernetes](vespa-on-kuberneteshtml.md): Vespa applications can be deployed on Kubernetes using the Vespa Operator. The Vespa Operator provides a native Kuber... - [Dockerを使ったVespaのクイック・スタート](vespa-quick-starthtml.md): このガイドではDockerを使って1台のマシン上にVespaをインストールして起動する方法を説明します。 - [vespa](vespahtml.md): The command-line tool for Vespa.ai - [Vespa 7 Release Notes](vespa7html.md): These notes documents the changes between Vespa major versions 6 and 7. As documented in [Vespa versions](../../learn... - [Position fields - Vespa 8 migration](vespa8-geo-migration-guidehtml.md): Refer to [Vespa 8 release notes](vespa8.html) - this is a guide on how to migrate from Vespa 7 to Vespa 8 when using ... - [Vespa 8 Release Notes](vespa8html.md): This document lists the changes between Vespa major versions 7 and 8. As documented in [Vespa versions](../../learn/r... - [Vespa 9 Release Notes](vespa9html.md): This document lists the changes between Vespa major versions 8 and 9. As documented in [Vespa versions](https://vespa... - [vespa activate](vespa-activatehtml.md): Activate (deploy) a previously prepared application package - [vespa auth](vespa-authhtml.md): Manage Vespa Cloud credentials - [vespa auth api-key](vespa-auth-api-keyhtml.md): Create a new developer key for headless authentication with Vespa Cloud control plane - [vespa auth cert](vespa-auth-certhtml.md): Create a new self-signed certificate for authentication with Vespa Cloud data plane - [vespa auth cert add](vespa-auth-cert-addhtml.md): Add certificate to application package - [vespa auth login](vespa-auth-loginhtml.md): Authenticate Vespa CLI with Vespa Cloud control plane. This is preferred over api-key for interactive use - [vespa auth logout](vespa-auth-logouthtml.md): Sign out of Vespa Cloud - [vespa auth show](vespa-auth-showhtml.md): Show authenticated user - [vespa clone](vespa-clonehtml.md): Create files and directory structure from a Vespa sample application - [vespa completion](vespa-completionhtml.md): Generate the autocompletion script for the specified shell - [vespa completion bash](vespa-completion-bashhtml.md): Generate the autocompletion script for bash - [vespa completion fish](vespa-completion-fishhtml.md): Generate the autocompletion script for fish - [vespa completion powershell](vespa-completion-powershellhtml.md): Generate the autocompletion script for powershell - [vespa completion zsh](vespa-completion-zshhtml.md): Generate the autocompletion script for zsh - [vespa config](vespa-confightml.md): Manage persistent values for global flags - [vespa config get](vespa-config-gethtml.md): Show given configuration option, or all configuration options - [vespa config set](vespa-config-sethtml.md): Set a configuration option. - [vespa config unset](vespa-config-unsethtml.md): Unset a configuration option. - [vespa curl](vespa-curlhtml.md): Access Vespa directly using curl - [vespa deploy](vespa-deployhtml.md): Deploy (prepare and activate) an application package - [vespa destroy](vespa-destroyhtml.md): Remove a deployed Vespa application and its data - [vespa document](vespa-documenthtml.md): Issue a single document operation to Vespa - [vespa document get](vespa-document-gethtml.md): Gets one or more documents - [vespa document put](vespa-document-puthtml.md): Writes a document to Vespa - [vespa document remove](vespa-document-removehtml.md): Removes a document from Vespa - [vespa document update](vespa-document-updatehtml.md): Modifies some fields of an existing document - [vespa feed](vespa-feedhtml.md): Feed multiple document operations to Vespa - [vespa fetch](vespa-fetchhtml.md): Download a deployed application package - [vespa inspect](vespa-inspecthtml.md): Provides insight - [vespa inspect profile](vespa-inspect-profilehtml.md): Inspect profiling results - [vespa log](vespa-loghtml.md): Show the Vespa log - [vespa prepare](vespa-preparehtml.md): Prepare an application package for activation - [vespa prod](vespa-prodhtml.md): Deploy an application package to production in Vespa Cloud - [vespa prod deploy](vespa-prod-deployhtml.md): Deploy an application to production - [vespa prod init](vespa-prod-inithtml.md): Modify service.xml and deployment.xml for production deployment - [vespa query](vespa-queryhtml.md): Issue a query to Vespa - [vespa status](vespa-statushtml.md): Show Vespa endpoints and status - [vespa status deploy](vespa-status-deployhtml.md): Show status of the Vespa deploy service - [vespa status deployment](vespa-status-deploymenthtml.md): Show status of a Vespa deployment - [vespa status document](vespa-status-documenthtml.md): * * * - [vespa status query](vespa-status-queryhtml.md): * * * - [vespa test](vespa-testhtml.md): Run a test suite, or a single test - [vespa version](vespa-versionhtml.md): Show current CLI version and check for updates - [vespa visit](vespa-visithtml.md): Retrieve and print all documents from Vespa - [.vespaignore](vespaignorehtml.md): When deploying an [application package](../reference/applications/application-packages.html) with [Vespa CLI](/en/cli... - [Visiting](visitinghtml.md): Visiting is a feature to efficiently get or process a set of documents, identified by a [document selection expressio... - [WAND: Accelerated OR search](wandhtml.md): This document describes how to use the Weak And algorithm for accelerated OR like search. - [Developing Web Service Applications](web-serviceshtml.md): This document explains how to develop (REST) web service type applications on the container - design options, accessi... - [What's more](whats-morehtml.md): The _Vespa basics_ articles introduces the central concepts in Vespa, but can't cover everything needed to build comp... - [Vespa Cloud Security Whitepaper](whitepaperhtml.md): _Last updated: 2025-06-04_ - [Working with chunks](working-with-chunkshtml.md): A key technique in RAG applications, and vector search applications in general, is to split longer text into chunks. ... - [Writing](writinghtml.md): This is an introduction to writing data into Vespa. - [Ranking with XGBoost Models](xgboosthtml.md): Vespa supports importing Gradient Boosting Decision Tree (GBDT) models trained with XGBoost. - [YQL Query Language Reference](yqlhtml.md): Vespa accepts unstructured human input and structured queries for application logic separately, then combines them in... - [Zones](zoneshtml.md): An application is deployed to a _zone_, which is a combination of an [environment](environments.html) and a _region_,...