{"timing":{"querytime":0.002,"summaryfetchtime":0.004,"searchtime":0.007},"root":{"id":"toplevel","relevance":1.0,"fields":{"totalCount":553},"coverage":{"coverage":100,"documents":553,"full":true,"nodes":2,"results":1,"resultsFull":1},"children":[{"id":"id:open:doc::open/en/reference/query-profile-reference.html","relevance":1.0,"source":"documentation","fields":{"sddocname":"doc","content":" This is a reference to the full format of Query Profile and Query Profile Type configuration files. For an introduction to query profiles, please see query profiles. Query Profiles A query profile defines a named set of search request parameters with values - structure: <query-profile id=\"[id]\" [optional attributes]> <description></description> ? <dimensions></dimensions> ? <field name=\"[name]\" [optional attributes]>[value]</field> * <query-profile for=\"[dimension values] [optional attributes]> <field name=\"[name]\">[value]</field> * </query-profile> * </query-profile> where ? means optional","documentid":"id:open:doc::open/en/reference/query-profile-reference.html","path":"/en/reference/query-profile-reference.html","title":"Query Profile Reference","headers":["Query Profiles","id","Optional query-profile attributes","Description","Query profile field","field name","Optional field attributes","field value","Dimensions","Query profile (nested)","Query profile (nested) for attribute","Query Profile Types","Optional query-profile-type attributes","match","strict","Query profile type field","field type","Optional field definition attributes","Identifiers"],"namespace":"open","outlinks":["/en/query-profiles.html","/en/reference/tensor.html","/en/reference/query-api-reference.html"],"inlinks":{"/en/query-profiles.html":1},"term_count":1367,"last_updated":1711608089,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/operations/tools.html","relevance":1.0,"source":"documentation","fields":{"sddocname":"doc","content":"This is the command-line tools reference for various Vespa use cases. vespa-analyze-onnx-model Loads an ONNX-model to analyze memory usage and infer/probe output types based on input types. Synopsis: vespa-analyze-onnx-model <onnx-model> [options...] Example (refer to ONNX for more examples): $ vespa-analyze-onnx-model Network.onnx Option Description --probe-types Use onnx model to infer/probe output types based on input types vespa-fbench vespa-fbench is used for benchmarking the capacity of a Vespa system. Refer to vespa-benchmarking for usage and","documentid":"id:open:doc::open/en/operations/tools.html","path":"/en/operations/tools.html","title":"Tools","headers":["vespa-analyze-onnx-model","vespa-fbench","vespa-makefsa","vespa-query-profile-dump-tool"],"namespace":"open","outlinks":["/en/onnx.html","/en/query-rewriting.html","/en/performance/vespa-benchmarking.html"],"inlinks":{"/en/query-profiles.html":1},"term_count":1280,"last_updated":1711608090,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/application-packages.html","relevance":1.0,"source":"documentation","fields":{"sddocname":"doc","content":" An application package is a set of files in a specific structure that defines a deployable application. It contains all the configuration, components and machine-learned models that is necessary to deploy and run the application: No configuration is ever done locally on Vespa nodes or over remote APIs. The application package is a directory, containing at minimum services.xml. Additionally, services.xml might consume other files or directories from the application package - see the reference for a full list. A change to code and configuration is atomically deployed to running instances. To ensure code and config consistency, config definition","documentid":"id:open:doc::open/en/application-packages.html","path":"/en/application-packages.html","title":"Application Packages","headers":["Deploy","Convergence","File distribution","Deploying remote models","services.xml","Component configuration","Node configuration","Configuration assembly","Configuration delivery","Configuration definitions","Component view","Delivery mechanism","Bootstrapping","System upgrades","Notes","Further reads"],"namespace":"open","outlinks":["/en/reference/application-v2-tenant.html","/en/operations/tools.html","/en/reference/services.html","/en/operations-selfhosted/config-proxy.html","/en/onnx.html","/en/operations-selfhosted/vespa-cmdline-tools.html","/en/vespa-cli.html","/en/reference/validation-overrides.html","/en/operations-selfhosted/config-sentinel.html","/en/reference/application-packages-reference.html","/en/components/bundles.html","/en/reference/schema-reference.html","/en/jdisc/index.html","/en/contributing/configapi-dev.html","/en/lightgbm.html","/en/contributing/configapi-dev-cpp.html","/en/contributing/configapi-dev-java.html","/en/configuring-components.html","/en/operations-selfhosted/configuration-server.html","/en/operations-selfhosted/files-processes-and-ports.html","/en/tensorflow.html","/en/xgboost.html","/en/reference/config-files.html"],"inlinks":{"/en/query-profiles.html":1,"/en/jdisc/http-server-and-filters.html":1,"/en/reference/services.html":1,"/en/cross-encoders.html":1,"/en/components/bundles.html":1,"/en/document-processing.html":1},"term_count":2382,"last_updated":1711608088,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/jdisc/http-server-and-filters.html":1.0,"/en/reference/services.html":1.0,"/en/cross-encoders.html":1.0,"/en/components/bundles.html":1.0,"/en/document-processing.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/searcher-development.html","relevance":1.0,"source":"documentation","fields":{"sddocname":"doc","content":" The Container is the home for all global processing of user actions (represented as queries) and their results. It provides a development and hosting environment for processing components, and a model for composing such components developed by multiple development teams into a functional whole. This document describes how to develop and deploy Searcher components. To get started with development, see the Developer Guide. For reference, see the Container javadoc, and the services.xml reference. Best practise for queries is submitting the","documentid":"id:open:doc::open/en/searcher-development.html","path":"/en/searcher-development.html","title":"Searcher Development","headers":["Searchers","Queries and Results","Search Chains","Writing a Searcher","Testing a Searcher","Deploying a Searcher","Testing a Searcher with an Application","Passing information between Searchers","Query Context","Parametrizing Searchers","Execution model","Keeping state in Searchers","Multiphase searching","Error handling","Timeouts","WordItem"],"namespace":"open","outlinks":["/en/reference/services-processing.html","/en/faq.html","/en/components/chained-components.html","/en/jdisc/container-components.html","/en/query-profiles.html","/en/query-api.html","/en/federation.html","/en/developer-guide.html","/en/reference/services-search.html","/en/reference/inspecting-structured-data.html"],"inlinks":{"/en/query-profiles.html":1,"/en/ranking.html":1,"/en/developer-guide.html":1,"/en/jdisc/container-components.html":1,"/en/document-summaries.html":1,"/en/query-api.html":1,"/en/federation.html":1,"/en/using-wand-with-vespa.html":1,"/en/multivalue-query-operators.html":1,"/en/document-processing.html":1,"/en/reads-and-writes.html":1,"/en/reference/schema-reference.html":1},"term_count":3490,"last_updated":1711608090,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/ranking.html":1.0,"/en/developer-guide.html":1.0,"/en/jdisc/container-components.html":1.0,"/en/document-summaries.html":1.0,"/en/query-api.html":1.0,"/en/federation.html":1.0,"/en/using-wand-with-vespa.html":1.0,"/en/multivalue-query-operators.html":1.0,"/en/document-processing.html":1.0,"/en/reads-and-writes.html":1.0,"/en/reference/schema-reference.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/testing.html","relevance":1.0,"source":"documentation","fields":{"sddocname":"doc","content":" A system tests suite is an invaluable tool both when developing and maintaining a complex Vespa application. These are functional tests which are run against a deployment of the application package to verify, and use its HTTP APIs to execute feed and query operations which are compared to expected outcomes. Vespa provides two formalizations of this: Basic HTTP tests, expressing requests and expected responses as JSON, and run with the Vespa CLI. Java JUnit tests, for more advanced tests, run as regular Java","documentid":"id:open:doc::open/en/testing.html","path":"/en/testing.html","title":"Vespa testing","headers":["System tests","Running system tests","Staging tests","Running staging tests","Feature switches and bucket tests"],"namespace":"open","outlinks":["/en/reference/services.html","/en/reference/testing.html","/en/reference/schema-reference.html","/en/components/chained-components.html","/en/query-profiles.html","/en/reference/testing-java.html","/en/vespa-cli.html","/en/reference/validation-overrides.html"],"inlinks":{"/en/query-profiles.html":1},"term_count":1385,"last_updated":1711608090,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/reference/indexing-language-reference.html","relevance":0.0,"source":"documentation","fields":{"sddocname":"doc","content":" This reference documents the full Vespa indexing language. If more complex processing of input data is required, implement a document processor. The indexing language is analogous to UNIX pipes, in that statements consists of expressions separated by the pipe symbol where the output of each expression is the input of the next. Statements are terminated by semicolon and are independent of each other (except when using variables). Find examples in the indexing guide. Indexing script An indexing script is a sequence of indexing statements separated by a semicolon (;). A script is","documentid":"id:open:doc::open/en/reference/indexing-language-reference.html","path":"/en/reference/indexing-language-reference.html","title":"Indexing Language Reference","headers":["Indexing script","Indexing statement","Indexing expression","Primitives","Outputs","Arithmetics","Converters","Other expressions"],"namespace":"open","outlinks":["/en/embedding.html","/en/reference/schema-reference.html","/en/linguistics.html","/en/schemas.html","/en/operations/reindexing.html","/en/indexing.html","/en/reference/services-content.html","/en/document-processing.html"],"term_count":2083,"last_updated":1711608088,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/reference/application-packages-reference.html","relevance":0.0,"source":"documentation","fields":{"sddocname":"doc","content":" This is the application package reference. An application package is the deployment unit in Vespa. To deploy an application, create an application package and vespa deploy or use the deploy API. The application package is a directory of files and subdirectories: Directory/file Required Description services.xml Yes Describes which services to run where, and their main configuration hosts.xml No The mapping from logical nodes to actual hosts validation-overrides.xml No Override, allowing this package to deploy even if it fails validation","documentid":"id:open:doc::open/en/reference/application-packages-reference.html","path":"/en/reference/application-packages-reference.html","title":"Application Package Reference","headers":["Deploy","Preprocess directives","Versioning application packages"],"namespace":"open","outlinks":["/en/reference/services.html","/en/reference/testing.html","/en/reference/semantic-rules.html","/en/jdisc/container-components.html","/en/application-packages.html","/en/schemas.html","/en/reference/stateless-model-reference.html","/en/tensor-user-guide.html","/en/onnx.html","/en/stateless-model-evaluation.html","/en/reference/deploy-rest-api-v2.html","/en/vespa-cli.html","/en/reference/validation-overrides.html","/en/reference/hosts.html","/en/reference/schema-reference.html","/en/lightgbm.html","/en/operations-selfhosted/configuration-server.html","/en/tensorflow.html","/en/xgboost.html","/en/reference/query-profile-reference.html","/en/ranking.html"],"inlinks":{"/en/reference/stateless-model-reference.html":1},"term_count":708,"last_updated":1711608088,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/reference/stateless-model-reference.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/annotations.html","relevance":0.0,"source":"documentation","fields":{"sddocname":"doc","content":" This document describes the Vespa Annotations API; its purpose and use cases along with some usage examples. Annotating Text Using Annotations as Simple Labels Imagine a use case where one wants to add some metadata to a chunk of text, where various parts of the text have some semantics that we want to express. This can be done by marking up the text with spans - where a span is identified by a start character index, and a length, and grouping these spans together to form a span tree: In the illustration above, we have a span tree called \"html\", with a root node that holds references to the spans we have created over the text","documentid":"id:open:doc::open/en/annotations.html","path":"/en/annotations.html","title":"Annotations API","headers":["Annotating Text","Using Annotations as Simple Labels","Annotation Trees","Annotation values","Alternate subtrees","Annotation References","Manipulating a Span Tree","Iterating over SpanNodes","Iterating over annotations","Annotation Inheritance"],"namespace":"open","outlinks":["/en/reference/schema-reference.html"],"inlinks":{"/en/document-processing.html":1},"term_count":2744,"last_updated":1711608088,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{"/en/document-processing.html":1.0}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:open:doc::open/en/reference/nativerank.html","relevance":0.0,"source":"documentation","fields":{"sddocname":"doc","content":" The nativeRank feature produces a reasonably text ranking score which is computed at an acceptable performance, and is a good candidate for first phase ranking. The nativeRank feature is a linear combination of the normalized scores computed by the features nativeFieldMatch, nativeProximity, and nativeAttributeMatch. All these features are described in detail below. See the configuration properties section for how to configure the features. nativeFieldMatch The nativeFieldMatch feature captures how well query terms match searched index fields by looking at the number of times a term","documentid":"id:open:doc::open/en/reference/nativerank.html","path":"/en/reference/nativerank.html","title":"nativeRank Reference","headers":["nativeFieldMatch","nativeProximity","nativeAttributeMatch","nativeRank","Variables","Configuration properties","Boost tables","Rank types","nativeRank limitations"],"namespace":"open","outlinks":["/en/reference/schema-reference.html","/en/reference/rank-types.html","/en/phased-ranking.html"],"term_count":2259,"last_updated":1711608089,"summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{}},"vespa.summaryFeatures.cached":0.0}}},{"id":"id:cloud:doc::cloud/en/data-management-and-backup.html","relevance":0.0,"source":"documentation","fields":{"sddocname":"doc","content":" This guide documents how to export data from a Vespa cloud application and how to do mass updates or removals. See cloning applications and data for how to copy documents from one application to another. Prerequisite: Use the latest version of the vespa command-line client. Export documents To export documents, configure the application to export from, then select zone, container cluster and schema - example: $ vespa config set application vespa-team.vespacloud-docsearch.default $ vespa visit --zone prod.aws-us-east-1c --cluster default --selection doc | head Some of the parameters above are redundant if unambiguous. Here, the application is set up using a template found in multinode","documentid":"id:cloud:doc::cloud/en/data-management-and-backup.html","path":"/en/data-management-and-backup.html","title":"Data management and backup","namespace":"cloud","summaryfeatures":{"query(links)":{"type":"tensor(links{})","cells":{"/en/query-profiles.html":1.0,"/en/page-templates.html":1.0,"/en/overview.html":1.0}},"tensorFromWeightedSet(attribute(inlinks),links)":{"type":"tensor(links{})","cells":{}},"vespa.summaryFeatures.cached":0.0}}}]}}