# Layer — Full documentation Search endpoint: https://hevlayer.com/api/ask/pro - [Agents](https://hevlayer.com/docs/pro/agents): Use the Layer docs and layer CLI from your coding agent with one-file skills that work across agent harnesses. - [Dashboard](https://hevlayer.com/docs/pro/dashboard): Running the in-cluster operations dashboard: the access it needs, networking, auth, and turning it off. - [Concepts](https://hevlayer.com/docs/pro/concepts): How the gateway composes turbopuffer, the document cache, PostgreSQL, S3, and metrics — and the core nouns you'll work with. - [Layer CLI](https://hevlayer.com/docs/pro/cli): The layer CLI manages environments, initializes namespace sharding, observes data-supply resources, indexes, pipelines, and UDFs, mints API keys, and runs Function manifests. - [Document model](https://hevlayer.com/docs/pro/document-model): A Layer document and the reserved attributes the gateway manages on every row. - [Failure Modes](https://hevlayer.com/docs/pro/failure-modes): How reads and writes degrade when the gateway, cache, or pipeline runs into trouble. - [FAQ](https://hevlayer.com/docs/pro/faq): Licensing, pricing, trials, and how to get started. - [Introduction](https://hevlayer.com/docs/pro): Layer is a gateway and function runtime for modern retrieval systems. It scales compute for multi-stage indexing pipelines and runs functions across every row of your index, with all durable state in object storage. - [Demos](https://hevlayer.com/docs/pro/demos): Live applications built on Layer — query routing, hybrid text fusion, semantic image search, and a full storefront workload — each composing shipped gateway features over a different corpus. - [No Guarantees](https://hevlayer.com/docs/pro/guarantees): Layer can't offer guarantees — here's what we commit to instead. - [Install](https://hevlayer.com/docs/pro/install): Install Layer Pro in your AWS account with Terraform and Helm. - [Limits](https://hevlayer.com/docs/pro/limits): Current ceilings inherited from the components we ship with, and what we don't cap. - [Licensing](https://hevlayer.com/docs/pro/licensing): How to get, install, and monitor a hev layer trial or commercial license. - [Health and metrics](https://hevlayer.com/docs/pro/observability): Check gateway health, inspect metrics, and control anonymous telemetry. - [Quickstart](https://hevlayer.com/docs/pro/quickstart): Start a 30-day Pro trial, install Layer in your AWS account, and point your client at the gateway. - [Changelog](https://hevlayer.com/docs/pro/roadmap): What has shipped in hev layer, and what is coming next. - [Tradeoffs](https://hevlayer.com/docs/pro/tradeoffs): The current product posture and the cases it is not trying to cover. - [Agentic search](https://hevlayer.com/docs/pro/api/agents): Run a configured reasoning loop over your indices: plan, fan out for recall, score for relevance, and return the standard row shape. - [Blobs](https://hevlayer.com/docs/pro/api/blobs): Durable content-addressed bytes served through the gateway. - [Checkpoints](https://hevlayer.com/docs/pro/api/checkpoints): Immutable labels over namespace snapshot watermarks. - [Data connections](https://hevlayer.com/docs/pro/api/data-supply): Find the API reference for vector stores and warehouses. - [Embed](https://hevlayer.com/docs/pro/api/embed): Send text and images to Layer and it computes the vectors, either on CPU beside the gateway or on a GPU worker serving open-weights models you declare. - [Federated query](https://hevlayer.com/docs/pro/api/federated-query): Federate one query across a set of namespaces and merge the results into a single ranked list, scoped by the key's entitlements. - [Lattice](https://hevlayer.com/docs/pro/api/lattice): A compact static retriever served in the gateway process, for text workloads where CPU throughput and deployment size outrank retrieval quality. - [License](https://hevlayer.com/docs/pro/api/license): Read the gateway's local license state. - [API keys](https://hevlayer.com/docs/pro/api/keys): Mint, verify, and revoke keys over REST; entitlements open stores, warehouses, or Layer itself. - [Namespace metadata](https://hevlayer.com/docs/pro/api/namespace-metadata): Read namespace metadata enriched with Layer freshness signals. - [Pipelines](https://hevlayer.com/docs/pro/api/pipelines): Organize a two-stage indexing pipeline: extract + chunk on CPU, embed on GPU, trigger runs and wait for completion. - [Query & Fetch](https://hevlayer.com/docs/pro/api/query): Vector similarity search with stable reads, query by id, and cached document fetch. - [Introduction](https://hevlayer.com/docs/pro/api/introduction): What Layer adds on top of the turbopuffer-compatible client wire, and how to point a client at the gateway. - [Scan](https://hevlayer.com/docs/pro/api/scans): On-demand row selection by filter, full-text, hybrid-text, or radius — IDs, count, or values. - [Response Headers](https://hevlayer.com/docs/pro/api/response-headers): Layer metadata returned alongside wire-compatible response bodies. - [Query History](https://hevlayer.com/docs/pro/api/search-history): Per-namespace query and clickstream history backed by JSONL in S3. - [Snapshot History](https://hevlayer.com/docs/pro/api/snapshots): Facet snapshot jobs, history, bodies, and activity streams. - [Warehouses](https://hevlayer.com/docs/pro/api/warehouses): List and inspect upstream warehouse connections through the gateway. - [VectorStores](https://hevlayer.com/docs/pro/api/vectorstores): List and inspect vector-store connections through the gateway. - [Search](https://hevlayer.com/docs/pro/api/search): One call that embeds the query, runs text and vector legs across every shard, fuses them, and optionally reranks the pool to a calibrated probability per row. - [Warm cache](https://hevlayer.com/docs/pro/api/warm-cache): Warm a namespace's document cache and snapshot mirror. - [Write & Stage](https://hevlayer.com/docs/pro/api/write): Write rows to a namespace and stage documents in the cache. - [Agent CRD](https://hevlayer.com/docs/pro/kubernetes/agent-crd): Agentic search as a Kubernetes resource: a governed reasoning loop over your indices, bound to a model, a budget, and an entitlement. - [ApiKey CRD](https://hevlayer.com/docs/pro/kubernetes/apikey-crd): Minted API keys as Kubernetes resources: lifecycle, entitlements, and opaque claims. - [Function CRD](https://hevlayer.com/docs/pro/kubernetes/function-crd): Stateless user-defined functions declared as Kubernetes resources. - [Index CRD](https://hevlayer.com/docs/pro/kubernetes/index-crd): Declarative representation of a namespace managed by Layer. - [InfraRules CRD](https://hevlayer.com/docs/pro/kubernetes/scaling-crd): Cluster-wide compute pools, document cache rules, and workload scaling. - [VectorStore CRD](https://hevlayer.com/docs/pro/kubernetes/vectorstore-crd): Backend connection and gateway inbound auth policy for a Layer install. - [Operator Overview](https://hevlayer.com/docs/pro/kubernetes/operator): What layer-operator reconciles and how it relates to the gateway. - [Warehouse CRD](https://hevlayer.com/docs/pro/kubernetes/warehouse-crd): Declared upstream data source: identity, credential, and verified reachability. - [Pipeline CRD](https://hevlayer.com/docs/pro/kubernetes/pipeline-crd): Staged row-changing work declared as a Kubernetes resource.