Amazon Comprehend
Managed natural language processing for entities, sentiment, PII and custom text models.
- Provider
- aws
- Kind
- AI service
- Category
- Compute
| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| analysisMode | enum | synchronous | batch | asynchronous | no | synchronous | inherited |
| auth | enum | api-key | oauth | iam | none | no | — | ▸ iam |
| contentFiltering | boolean | — | no | — | inherited |
| customModels | boolean | — | no | false | inherited |
| customerManagedKeys | boolean | — | no | — | ▸ false |
| dataResidency | enum | us | eu | asia | global | no | — | inherited |
| dataRetentionDays | integer | — | no | — | inherited |
| keyStore | boolean | — | no | false | inherited |
| managed | boolean | — | no | false | ▸ true |
| maxActiveAsyncJobs | integer | — | no | 10 | inherited |
| maxDocumentSizeKb | integer | — | no | 100 | inherited |
| maxDocumentsPerBatch | integer | — | no | 25 | inherited |
| modality | enum | text | vision | speech | multimodal | structured | image | video | audio | embedding | rerank | no | — | ▸ text |
| publicEndpoint | boolean | — | no | — | ▸ true |
| quotaUnitsPerMinute | integer | — | no | — | inherited |
| rateLimitRpm | integer | — | no | — | inherited |
| rateLimitTpm | integer | — | no | — | inherited |
| viaGateway | boolean | — | no | false | inherited |
Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.
This AI vendor is reached with an API key, and nothing in the design holds or rotates that key. It ends up in environment files or code, every caller shares it, and a single leak runs up the vendor bill until someone notices. Put the key in a key-management component, or say it is held there with keyStore.
- — all of these hold:
- — the node's `auth` is "api-key"
- — the node's `keyStore` is false
- — the node has at least one incoming edge from an app-server, worker or client
- — this does not hold:
- — the design contains a node of kind key-management
A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.
- — all of these hold:
- — the node's `stateless` is false
- — the node sits inside exactly 1 availability-zone group
- — this does not hold:
- — the node sits inside at least one cell group
nodes:
- { id: "comprehend", component: "aws-comprehend" }# yaml-language-server: $schema=../../schema/component.schema.json # Amazon Comprehend: managed NLP over UTF-8 text (entities, key phrases, language, sentiment, PII) with optional custom classifiers and entity recognizers. # "Guidelines and quotas" gives the built-in synchronous limits: 100 KB per document for entity, key-phrase and language detection, 25 documents per batch request, 10 active asynchronous jobs per operation, and dynamic throttling instead of a fixed request rate; "AI services opt-out policies" states content may be stored for service improvement unless an Organizations opt-out policy is set. schemaVersion: "1" type: "component" id: "aws-comprehend" kind: "ai-service" provider: "aws" docs: "https://docs.aws.amazon.com/comprehend/latest/dg/guidelines-and-limits.html" defaults: auth: "iam" managed: true modality: "text" publicEndpoint: true customerManagedKeys: false properties: analysisMode: type: "enum" values: ["synchronous", "batch", "asynchronous"] default: "synchronous" maxDocumentSizeKb: type: "integer" default: 100 maxDocumentsPerBatch: type: "integer" default: 25 maxActiveAsyncJobs: type: "integer" default: 10 customModels: type: "boolean" default: false