LlamaParse
LlamaIndex document parsing service that turns complex files into LLM-ready text as asynchronous parse jobs.
| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| accelerator | enum | none | gpu | asic | no | none | inherited |
| concurrency | integer | — | no | — | ▸ 5 |
| fanoutStrategy | enum | none | push | pull | hybrid | no | none | inherited |
| fanoutThreshold | integer | — | no | — | inherited |
| idempotent | boolean | — | no | false | ▸ false |
| instances | integer | — | no | — | inherited |
| managed | boolean | — | no | false | ▸ true |
| parseTier | enum | fast | cost-effective | agentic | agentic-plus | no | — | inherited |
| plan | enum | free | starter | pro | enterprise | no | free | inherited |
| rateControl | enum | none | fixed | aimd | no | none | inherited |
| schedule | string | — | no | — | inherited |
| trigger | enum | queue | stream | schedule | batch | manual | yes | — | ▸ queue |
| webhooks | 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.
Pure push fan-out over a social graph is brutal at the tail: one post from an account with millions of followers becomes millions of cache writes. A follower threshold above which readers merge at read time bounds that write amplification.
- — all of these hold:
- — the node's `fanoutStrategy` is "push"
- — the node's `fanoutThreshold` has no value
- — the design contains a node of kind graph-database
One worker pool consuming several queues lets a slow or poisoned queue starve the others. That is precisely what the design's per-queue isolation requirement forbids.
- — all of these hold:
- — the node has more than 1 incoming edge from a queue
- — the design requirement `isolation.perQueue` is true
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: "llamaparse", component: "llamaparse" }# yaml-language-server: $schema=../../schema/component.schema.json # LlamaParse: LlamaIndex's credit-billed document parsing service on LlamaCloud, run as asynchronous parse jobs. # Per "Rate Limits", parse job creation is capped at 500 requests per 10 seconds per organization on every plan, 429s carry # no Retry-After header and webhooks are preferred over polling; per "Billing and Usage" the Free plan allows 5 concurrent parse jobs. schemaVersion: "1" type: "component" id: "llamaparse" kind: "worker" provider: "default" docs: "https://developers.llamaindex.ai/python/cloud/general/rate_limits" defaults: managed: true trigger: "queue" idempotent: false concurrency: 5 properties: plan: type: "enum" values: ["free", "starter", "pro", "enterprise"] default: "free" parseTier: type: "enum" values: ["fast", "cost-effective", "agentic", "agentic-plus"] webhooks: type: "boolean" default: false