AI Power Ups
Contents

Research and reading · Official sources, SearchApi and Firecrawl

legal.read

Read an identified EUR-Lex document, Library of Congress U.S. Reports opinion, Google Scholar case or the original 1890 Right to Privacy article. Returns bounded text chunks with source provenance; more continues the same document. PDF page indices and printed court pages remain distinct. Source access failures are reported instead of returning a challenge page as text.
Operation
POST /v1/capabilities/legal.read/execute
operationId
executeLegalRead
Typical credits
0
Search deadline
40 s server-side
Paging
local
Availability
ConfiguredChecked 2026-09-23 21:02 UTC
Cost basis: Direct official and historical texts are free. Scholar case retrieval uses SearchApi at $0.004. EUR-Lex and historical-source fallback uses actual Firecrawl credits × $0.005. Buffered text and cached details are free. Availability is reported per deployment by GET /v1/catalog (available). The timestamped snapshot describes configuration, not provider uptime or your account's enabled choices. Check the catalog with your own key before a call. Credits are explained under credits and limits.

Request

Body of POST /v1/capabilities/legal.read/execute, JSON, validated against the LegalReadRequest component of the public OpenAPI document. Defaults are applied server-side, so an omitted optional field behaves exactly as its default.

Request fields of legal.read
FieldTypeRequiredDefaultConstraints and description
documentobject | object | object | objectyes
document.sourcewhen source = "eurlex""eurlex"yes
document.celexwhen source = "eurlex"stringyespattern ^[0-9][0-9A-Z()_/-]{5,50}$
Exact CELEX document identifier, e.g.62012CJ0131. Use legal.search for discovery; no case-number guessing.
document.languagewhen source = "eurlex""BG" | "CS" | "DA" | "DE" | "EL" | "EN" | "ES" | "ET" | "FI" | "FR" | "GA" | "HR" | "HU" | "IT" | "LT" | "LV" | "MT" | "NL" | "PL" | "PT" | "RO" | "SK" | "SL" | "SV"no"EN"
document.sourcewhen source = "us_reports""us_reports"yes
document.item_idwhen source = "us_reports"stringyespattern ^usrep[0-9]{6}$
Library of Congress U.S. Reports item, e.g.usrep532514. Text extracted from official PDF; printed pages and PDF indices remain distinct.
document.sourcewhen source = "scholar""scholar"yes
document.caselaw_idwhen source = "scholar"stringyespattern ^[0-9]{1,25}$
document.sourcewhen source = "historical""historical"yes
document.work_idwhen source = "historical""warren-brandeis-right-to-privacy-1890"yes
numintegerno3min 1, max 10
  • Unknown keys are rejected with 400 invalid_request.

Rules the schema cannot express

Checked after schema validation; violations return 400 invalid_request with a plain message.

  • An invalid U.S. Reports identifier is refused before any fetch.

Examples

Google Spain judgment

curl
curl -s -X POST https://api.powerups-ai.store/v1/capabilities/legal.read/execute \
  -H "Authorization: Bearer $AIPA_API_KEY" -H "Content-Type: application/json" \
  -d '{"document":{"source":"eurlex","celex":"62012CJ0131","language":"EN"},"num":3}'

A US privacy case

curl
curl -s -X POST https://api.powerups-ai.store/v1/capabilities/legal.read/execute \
  -H "Authorization: Bearer $AIPA_API_KEY" -H "Content-Type: application/json" \
  -d '{"document":{"source":"us_reports","item_id":"usrep532514"},"num":3}'

The original 1890 argument

curl
curl -s -X POST https://api.powerups-ai.store/v1/capabilities/legal.read/execute \
  -H "Authorization: Bearer $AIPA_API_KEY" -H "Content-Type: application/json" \
  -d '{"document":{"source":"historical","work_id":"warren-brandeis-right-to-privacy-1890"},"num":3}'
No recorded response is published for this capability yet. The envelope is the ExecuteResponse component (see sessions and records); the record keys below are what the adapter emits. A first call with the example above returns search_id, the records and the charge.

Result record

Every item in results[] carries record_id and title (contract, always present) and usually url and snippet. The keys below are the documented tier: produced deterministically by this capability, omitted when the source has no value, checked against recorded source fixtures in our test suite, and published as the LegalReadRecord component (all optional, extra keys allowed) so generated clients type them. The wire schema itself still validates only the base keys. See stability tiers.

Record keys of legal.read
KeyTypePresenceNote
identifierstringalways
source_classstringalways
languagestringwhen the source has it
sectionintegeralways
total_sectionsintegeralways
pdf_pageintegerwhen the source has itPDF sources.
printed_pagestringwhen the source has itU.S. Reports.
paragraph_anchorsstring[]when the source has it
extraction_methodstringalways

Caveats

  • more continues the same document; source access failures are reported as provider_error, never replaced with text.

Follow-ups

  • Paging: Whole result set held in the session; more is served locally and costs nothing. Send { "search_id": "…", "action": "more" } while has_more is true; tolerate an empty page and stop after a bounded number of pages.
  • Update: Re-run with changed parameters (merged into the stored query); page state resets, search_id stays. Params accept any subset of the request fields (LegalReadUpdateParams).
  • Record actions:
    • details: The complete selected text chunk with source references and attribution.
  • Detail behaviour: Stored at search time; details is free and never calls the provider. details returns the complete stored text chunk at no charge.
record action
curl -s -X POST https://api.powerups-ai.store/v1/follow-up \
  -H "Authorization: Bearer $AIPA_API_KEY" -H "Content-Type: application/json" \
  -d '{"record_id":"rec_…","action":"details"}'

details detail keys (owned, documented tier)

The complete stored text chunk with document metadata and provenance. Built entirely by our code and published as the LegalReadDetailsDetail component; the wire contract of detail stays untyped, extra keys may appear.

Detail keys of legal.read details
FieldTypeRequiredDefaultConstraints and description
titlestringyes
identifierstringyes
sourcestringyes
source_class"official_publication" | "institutional_transcription" | "reproduction"yes
languagestringyes
source_urlstringyes
retrieved_atstringyes
source_sha256stringyes
extraction_methodstringyes
legal_status"not_assessed"yes
textstringyes
anchorsstring[]no
pdf_pageintegerno
printed_pagestringno
sectionintegeryesmin 1
total_sectionsintegeryesmin 1
complete_document_available_through_moretrueyes

Other record detail objects are provider-shaped: documented by observation, not by schema. Full follow-up semantics: follow-up.

Typed client

With types generated from the public document (see types, client and samples) the call is path-keyed and the body is checked at compile time:

TypeScript (openapi-fetch)
const { data, error } = await client.POST("/v1/capabilities/legal.read/execute", {
  body: {
    "document": {
      "source": "eurlex",
      "celex": "62012CJ0131",
      "language": "EN"
    },
    "num": 3
  },
});
if (error) throw new Error(`${error.error.code}: ${error.error.message}`);
for (const record of data.results) console.log(record.record_id, record.title);