Table of contents

Vespa basics

• Deploy an application
• Vespa applications
• Schemas
• Writing
• Querying
• Ranking
• Operations
• What's more

Learn more

• Vespa overview
• Getting help from LLMs
• Features
• Tutorials and use cases
• Frequently asked questions
• Glossary
• Releases
• Tenants, apps and instances
• Migrating to Vespa Cloud
• Migrating from ElasticSearch
• About this documentation
• Contributing to Vespa

Applications and components

• Developer guide
• IDE support
• Deployment
• .vespaignore files
• Containers
• Components
• Searchers
• Document processors
• Request handlers
• Result renderers
• Dependency injection
• Configuring components
• Chaining
• Inspecting structured data in a Searcher
• Developing web services
• Unit testing
• System testing
• The config system
• Request-response processing
• Bundles
• Using ZooKeeper
• Http servers and filters
• Using pluggable frameworks
• Java config API

Schemas and documents

• Documents
• Inheritance in schemas
• Concrete document types
• Parent-child relationships
• Structs
• Predicate fields
• Exposing schema information

Reading and writing

• Reads and writes
• /document/v1
• Indexing
• Index bootstrap
• Visiting
• Document API
• Partial updates
• Batch delete
• Feed block
• Document routing
• Indexing paged vectors

Querying

• The query api
• The YQL query language
• Grouping and aggregation
• Federation
• Query profiles
• An intro to vector search
• Nearest neighbor search
• Approximate nearest neighbor search
• Nearest neighbor search guide
• Text matching
• Searching multivalue fields
• Geo search
• Document summaries
• Result diversity
• Page templates

Ranking and inference

• Ranking introduction
• Ranking expressions and features
• Multivalue query operators
• Tensor user guide
• Tensor examples
• Phased ranking
• Using TensorFlow models
• Using ONNX models
• Using XGBoost models
• Using LightGBM models
• Wand: Accelerated OR search
• The BM25 rank feature
• The nativeRank rank feature
• Cross-encoder transformer ranking
• Searcher re-ranking
• Significance model
• Stateless model evaluation

RAG and embedding

• RAG in Vespa
• Working with chunks
• Embedding
• Binarizing vectors
• LLMs in Vespa
• Using local LLMs
• Using external LLMs
• Document enrichment with LLMs
• Model hub

Linguistics and text processing

• Linguistics
• Lucene linguistics
• Query rewriting
• Troubleshooting character encoding

Content and elasticity

• Content clusters
• Content nodes and states
• Elasticity
• Document attributes
• Consistency Model
• Distribution algorithm
• Buckets

Performance

• Performance overview
• Practical performance guide
• Serving sizing guide
• Feed sizing guide
• Node resources
• Sizing examples
• Topology and resizing
• Streaming search
• Benchmarking
• Benchmarking using Vespa Cloud
• Memory visualizer
• Profiling
• Container tuning
• Rate-limiting queries
• Graceful degradation
• Caches
• HTTP performance testing
• HTTP/2
• Feature tuning
• Valgrind

Operations

• Environments
• Zones
• Production deployment
• Deployment variants
• Automated deployments
• Autoscaling
• Enclave: Bring your own cloud
  • Enclave
  • AWS getting started
  • AWS architecture
  • Azure getting started
  • Azure architecture
  • GCP getting started
  • GCP architecture
  • Log archive
  • Operations
• Reindexing
• Data management and backup
• Cloning applications and data
• Monitoring
• Metrics
• Notifications
• Deployment patterns
• Private endpoints
• Endpoint routing
• Access logging
• Artefact archive
  • Archive guide
  • Archive Guide AWS
  • Archive Guide GCP
• Deleting applications
• Self-managed
  • Admin procedures
  • Multinode Systems
  • Files, Processes, Ports, Environment
  • Node Setup
  • Using Kubernetes
  • Build and install
  • Monitoring
  • Content node recovery
  • Configuration Servers
  • Live Vespa upgrade procedure
  • Config Sentinel
  • Config Proxy
  • Docker Containers
  • Docker Containers GPU setup
  • CPU Support
  • Service Location Broker
  • Change from attribute to index procedure
  • Container
  • Monitoring

Security

• Security overview
• Security Guide
• Secret Store
• Cloudflare Workers
• Security Whitepaper
• Securing a Vespa installation
• mTLS

Clients

• Command line client (Vespa CLI)
• Python client (pyVespa)
• Java feed client
• HTTP best practices

Modules

• E-commerce
  • Multi-currency filtering

Reference

• APIs
  • APIs overview
  • The query API
  • /document/v1 API
  • /state/v1 API
  • /application/v2 API (deployment)
  • /application/v2/tenant API
  • /config/v2 API
  • /cluster/v2 API
  • /metrics/v1 API
  • /metrics/v2 API
  • /prometheus/v1 API
• Applications and components
  • Application packages
  • services.xml
    • services.xml
    • services.xml - admin
    • services.xml - container
    • services.xml - content
    • services.xml - docproc
    • services.xml - http
    • services.xml - processing
    • services.xml - search
  • deployment.xml
  • hosts.xml
  • validation-overrides.xml
  • Components
  • Configuration files
  • System test
  • System test (Java)
• Schemas and documents
  • Schemas
  • Document JSON format
  • Document field path language
• Reading and writing
  • Indexing language
  • Document selector language
• Querying
  • The YQL query language
  • The simple query language
  • Select
  • Grouping
  • Sorting
  • Query profiles
  • Semantic rules
  • The default result format
  • The page result format
  • Page templates
• Ranking and inference
  • Ranking expressions
  • Tensor evaluation
  • Rank features
  • nativeRank
  • String segment match
  • Rank feature configuration
  • Rank types
  • Model files
  • Constant tensors
• RAG and embedding
  • Chunking
  • Embedding
• Operations
  • Health checks
  • Log files
  • Tools
  • Metrics
    • Metrics
    • Default metric set
    • Vespa metric set
    • Metric units
    • Container metrics
    • Distributor metrics
    • Search node metrics
    • Storage metrics
    • Configserver metrics
    • Logd metrics
    • Node Admin metrics
    • Slobrok metrics
    • Cluster controller metrics
    • Sentinel metrics
  • Self-managed
    • Tools
• Security
  • Mtls
• Clients
  • Vespa CLI
    • vespa
    • vespa activate
    • vespa auth
    • vespa clone
    • vespa config
    • vespa curl
    • vespa deploy
    • vespa destroy
    • vespa document
    • vespa feed
    • vespa fetch
    • vespa inspect
    • vespa log
    • vespa prepare
    • vespa prod
    • vespa query
    • vespa status
    • vespa test
    • vespa version
    • vespa visit
• Release notes
  • Vespa 7
  • Vespa 8
  • Vespa 9 (upcoming)