abogacia.uy
Technical FAQ Español (ES) View integration Request access →
Legal infrastructure · Powered by JustIA

Add Uruguayan legal search with verifiable citations in days

For LegalTechs, law firms and compliance teams that need traceable answers on Uruguayan legislation and case law, without building or maintaining the corpus from scratch.

API, internal product or private deployment · We never train models on your queries

POST api.abogacia.uy/v1/search 142ms p95
Request
"query": "dismissal over salary reduction", "sources": ["SCJ", "IMPO"], "top_k": 3, "mode": "hybrid", "rag": true
Response
"rag_answer": "A unilateral salary reduction entitles the worker to claim constructive dismissal under art. 4 of Law 10.489...", "citations": [ "SCJ-421-2023", "L-10489-Art4" ], "results"[0]."score": 0.94, "latency_ms": 138
14,832
Indexed rulings
+2,100
Laws and decrees
since 1830
National legislation
7
Official sources
<200ms
p95 latency
99.9%
Uptime SLA
Products

Three layers of legal infrastructure

Use one, two or all three. Each layer is independent and integrates over a REST API with Bearer authentication.

01 · Dataset

Corpus RAG

Normalized Uruguayan legislation and case law, legally chunked and vectorized. Ready to ingest into your vector store.

Legal chunking by article / subsection
Normalized metadata (source, date, court)
Precomputed embeddings (multilingual-e5)
Versioning and change auditing
Automatic updates from official sources
02 · Search

Search API

Semantic + keyword search endpoint with hybrid ranking calibrated for the Uruguayan legal domain.

Hybrid ranking: semantic + BM25
Filters by source, subject, court, year
Minimal, highly relevant snippets
Relevance score per result
Latency <200ms p95
03 · Generation

RAG Completions

Answers generated with verifiable citations. Send the query, get back the answer with the exact sources that support it.

Grounding in the Uruguayan legal corpus
Citations array with verifiable source IDs
Streaming available (SSE)
Configurable model (Claude / GPT-4o)
White-label: no references to JustIA
Why PDFs are not enough

Legal RAG is not dumping documents into a vector store

LegalBench-RAG research makes it clear: in law, what matters is retrieving minimal, highly relevant passages, not generic chunks. Bad chunking produces incorrect citations — and in the legal domain, that has consequences.

Legal chunking by article

Every article, subsection and paragraph is an independent semantic unit. Naïve token chunking splits clauses and loses cross-references between articles.

Normalization and repeals

Laws are amended, repealed and updated. Without versioning, your RAG may cite legislation that is no longer in force — the most critical problem in production.

Ranking calibrated for law

Pure BM25 fails with legal terminology. A semantic-only index fails with case names and ruling numbers. Hybrid ranking calibrated for Uruguay solves both.

Capability DIY abogacia.uy API
Legal chunking by articleManual✓ Included
Repeals and versioningNo✓ Automatic
Legal hybrid rankingNo✓ Calibrated for UY
Normalized metadataManual✓ Structured
Automatic updatesNo✓ Daily
Verifiable citationsNo✓ Auditable IDs
Access to judicial sourcesFragile scraping✓ Official SOAP + PJ
SLA and supportNo✓ 99.9% SLA
Implementation time6–12 monthsDays
Corpus coverage

Official sources, not scraping

Every source is ingested from its official channel. No PDFs of unknown origin, no third-party copies.

SC

Supreme Court of Justice

Rulings from every chamber. Civil, Labor, Criminal and Family chambers.

Daily updates · since 1985
TC

Administrative Court (TCA)

TCA rulings on administrative acts and public law.

Daily updates · since 1990
TA

Courts of Appeals

TAT, TAC, TAP, TAF — second-instance rulings by subject matter.

Weekly · since 2000
PJ

Judiciary (BJN)

National Case Law Database. Access via the Judiciary’s official web services.

Daily updates
IM

IMPO — Official Gazette

Complete national legislation since 1830. Open JSON data under IMPO license.

Real time · since 1830
PA

Parliament of Uruguay

Bills, enacted laws and verbatim transcripts of sessions.

Daily · active legislature
PR

Presidency / Decrees

Executive decrees, ministerial resolutions and administrative acts.

Daily
+

Coming soon

BCU financial regulation · DGI tax criteria · ratified ILO conventions.

On the Q3 2026 roadmap

About public legislation: IMPO declares its database as open data available for reuse. What we sell is not "the raw law" — it is the normalized, enriched, versioned and legally chunked corpus, plus the specialized search and retrieval infrastructure. That processing is where the value is.

Value example

A useful answer, with the source right next to it

The point is not to generate convincing legal text. It is to retrieve the correct rule or ruling, show where it comes from, and leave an auditable trail so a lawyer can review it.

Answers with mandatory citations, not unsupported text.
Hybrid ranking to combine legal concepts, law numbers and case law.
Ready to expose in your product, legal intranet or compliance flow.
Example output Verifiable citations
Question
Can a worker claim constructive dismissal if their salary is reduced?

Generated answer: In principle, a unilateral salary reduction may constitute a serious breach by the employer and entitle the worker to claim constructive dismissal. The final outcome depends on the evidence, the size of the reduction, its permanence and the context of the employment relationship.

SCJ · LAB-421-20230.94

Labor case-law criterion

Ruling on unilateral modification of essential conditions of the employment contract.

IMPO · Law 10.4890.89

Applicable labor legislation

Statutory reference related to salary, labor claims and recovery.

Use cases

Who it makes sense to buy it for

The same infrastructure is packaged differently per buyer: API for products, private demo for law firms and an internal solution for companies.

LegalTechs and legal software

Add Uruguayan legal search and answers with citations inside your product without building your own scraping, embeddings, legislative updates or legal ranking.

Search APIRAG CompletionsWhite-label

Law firms

Internal search over the public corpus and your own documents: precedents, contracts, briefs and frequent queries. Private deployment option for teams with sensitive data.

Private demoPrivate deploymentOwn documents

Companies with compliance

Internal queries for HR, compliance, finance or legal departments with answers grounded in current Uruguayan legislation and source traceability.

Legal intranetComplianceAuditable citations

Universities and research

Complete corpus for legal NLP research, case-law analysis and academic studies. Export in Parquet or JSON for offline analysis.

Corpus exportParquet / JSONAcademic license

Consultancies and Big4

AI-assisted due diligence and regulatory analysis. Search across DGI, BCU and sector regulations with auditable citations for client reports.

Due diligenceSearch APIAuditable citations

Legal portals and media

Embed a case-law search widget in your portal. Your users search rulings directly from your platform, with your branding.

Embed widgetSearch APIWhite-label
Why abogacia.uy

Built for serious legal production

Processed Uruguayan corpus, verifiable citations and integration designed for teams that need reliable answers, not approximations. Built for:

LegalTech and startups
Law firms
Fintech · Compliance
Universities · Research
Consultancies · Due diligence
+ Your company
The corpus is normalized and legally chunked by article — not raw PDFs dumped into a vector store. Processed to answer in production, not in a demo.
Production-ready corpus
Legal chunking by article
Every result links to the official article or ruling. No unsupported answers: real traceability for reports, due diligence and compliance.
Verifiable citations
Every answer to its source
Search API and RAG-as-a-service over the Uruguayan corpus. Integrate in days with a REST API and SDKs, without building or maintaining the corpus yourself.
Integrate in days
REST API + SDKs
Integration

Three steps to integrate

Standard REST API. SDKs for Python and JavaScript. Compatible with any stack.

01 · AUTHENTICATION

Get your API key

Request access and we send your credentials within 24h. Standard Bearer token on every endpoint.

02 · FIRST SEARCH

First query in minutes

One POST to the search endpoint and you already get legal results with score and normalized metadata.

03 · PRODUCTION

Scale without friction

Rate limits configurable per plan. Webhooks for corpus updates. Monitoring dashboard included.

Python JavaScript cURL
# pip install abogacia-py from abogacia import AbogaciaClient client = AbogaciaClient("sk-abg-...") # Semantic search results = client.search( query="constructive dismissal over salary reduction", sources=["SCJ", "IMPO"], top_k=5, mode="hybrid" ) # RAG Completion with citations response = client.complete( query="What deadline does the worker have?", stream=True ) for chunk in response: print(chunk.text, end="") # citations: ["SCJ-421-2023", "L-10489-Art4"]
Security and compliance

Designed for demanding production environments

Built from day one to meet the standards required by law firms, fintechs and companies with sensitive data.

Namespace isolation

Each client operates in a fully isolated namespace. No data, query or result crosses between accounts. Multi-tenant architecture with database-level separation.

Encryption in transit and at rest

TLS 1.3 on every endpoint. Vectorized data and indexed corpus encrypted at rest with AES-256. API keys are never stored in plain text.

No query retention

The queries you send to the API are not stored, not logged with content and never used to train or fine-tune models. Configurable retention period (default: 0 days).

99.9% SLA with monitoring

Guaranteed uptime with a public status page. The Enterprise plan includes an SLA with financial penalties for breaches and on-call technical support.

On-premise deployment (Enterprise)

The corpus and the API can run in your private infrastructure or VPC. No dependence on our servers, no data traffic outside your environment. Available on the Enterprise plan.

Source auditing

Every corpus fragment has full traceability: official source, ingestion date, version and validity status. You can audit any citation back to its origin.

Data residency: By default, data is processed on infrastructure located in the region. For Enterprise customers with specific data sovereignty requirements, we offer deployment in Uruguay or the SA region. Contact us to assess your case.

Pricing

API plans

Pay for what you use. No volume commitments on the first two tiers.

Prices in USD · no setup costs · cancel anytime
Starter
$0/mo

To evaluate the API and build a POC. No credit card.

500 queries/mo
Search API (semantic mode)
Sources: SCJ + IMPO
Full documentation
RAG Completions
White-label
Request access
Enterprise
Custom

Private deployment, isolated namespace, guaranteed SLA and dedicated support.

Everything in Pro, unlimited
Corpus export (Parquet / pgvector)
On-premise / private VPC deployment
Full white-label
99.9% SLA with penalties
Dedicated support + onboarding
Talk to sales
FAQ

Questions before buying or integrating

The answers that business, legal and tech teams usually need before moving forward with a pilot.

Buying and usage
Does this replace the lawyer?

No. It is designed as search, retrieval and assistance infrastructure. The professional decision still belongs to the lawyer or legal team. That is why every answer includes sources, citations and traceability.

What happens if the AI gets it wrong?

The system is designed to reduce that risk with grounding, hybrid ranking and mandatory citations. If it does not retrieve enough sources, it can be configured not to answer. For critical flows we recommend human review.

Can I run a pilot before signing up?

Yes. The Starter plan allows a technical POC at no cost. For law firms or companies we can arrange a private demo with real team cases and a limited scope.

Is it useful if I have no technical team?

Yes. For non-technical teams we package it as a private demo, internal search tool or assisted integration. The API is one way to integrate, not the only way to use the corpus.

Can I mix the public corpus with my own documents?

Yes, on Pro and Enterprise plans. You can upload contracts, internal precedents, manuals or briefs to your namespace. Private documents are never accessible from other accounts.

Data and integration
Is there rate limiting? How does it work?

Yes, per API key. Starter: 10 req/min, 500/mo. Pro: 100 req/min, 20,000/mo. Enterprise: configurable. Response headers include X-RateLimit-Remaining and X-RateLimit-Reset. 429 responses include Retry-After.

Is RAG Completions compatible with the OpenAI format?

Partially. The /v1/complete endpoint follows a structure similar to chat/completions but with additional fields: citations[], sources[] and grounding_score. There is an openai_compat: true mode that omits those extra fields if you already have an OpenAI client configured.

Are there webhooks for corpus updates?

Yes, on Pro and Enterprise plans. You configure filters (by source, subject, keywords) and receive a POST to your endpoint when new matching content arrives. Useful for keeping a local index synced or triggering automatic alerts.

What if I need more queries than my plan allows?

On Starter, the overage blocks until the next month. On Pro and Enterprise, overage is billed at a per-query rate agreed in advance — we never cut off service without notice. You can set up automatic alerts when you reach 80% of your quota.

Do you have an SDK or do I have to use cURL?

Official SDK for Python (pip install abogacia-py) and JavaScript/TypeScript (npm install @abogacia/client). Both include types, error handling, automatic retries and streaming support. For other languages, the API is standard REST — cURL works perfectly.

Next step

Try it with a real case from your team

Request API access, a private demo or a limited pilot. We reply with the best path for your case: product, law firm, compliance or research.

API key within 24 business hours
Free Starter tier to evaluate with no commitment
Private demo for law firms and legal teams
Technical or commercial onboarding depending on the buyer
Enterprise: private deployment and your own documents

Request access or a demo

We reply in under 24 business hours.

No spam. We never share your information with third parties. See our privacy policy.

Request received!

We will contact you in under 24 business hours with your access credentials and next steps.

Integrate the Uruguayan legal corpus in days, not months.

API key within 24 hours. No bureaucracy. Free Starter tier so you can evaluate before committing.

Part of the JustIA.uy ecosystem · Legal infrastructure for Uruguay