⚖️ CourtListener RAG extractor: legal opinions as searchable chunks

Turn public court opinions into RAG-ready chunks in one run. Search CourtListener case law by court and filing date, keep citation context on every record, and get consistent 512-token chunks for retrieval.
RESEARCH AND REGULATORY RAG EXTRACTORS   •  Turns arXiv, bioRxiv/medRxiv, PubMed, CourtListener case law, and SEC EDGAR filings into RAG-ready, chunked JSON for grounded LLM retrieval.
CourtListener ➤ You are here	PubMed RAG PubMed literature, chunked	SEC EDGAR 10-K/10-Q/8-K, chunked	arXiv RAG arXiv papers, chunked

Court opinions, delivered as a clean chunked research corpus Search public CourtListener opinions by court and filing date, then get standardized records with citations and consistent 512-token chunks for retrieval.

⚖️ Court coverage Common federal slugs or another public court slug

🔎 Focused search Narrow a corpus by filing dates and topic

🧩 Ready-to-use chunks 512 tokens with citation context preserved

🛡️ Honest fallback Records stay useful when full text is unavailable

🔍 What does CourtListener RAG Extractor do?

CourtListener RAG Extractor collects public opinions and turns them into structured records with citations, source links, and consistent text chunks. It starts with common U.S. federal courts and also accepts other public CourtListener court slugs.

Use it for case-law search, legal research, citation review, and retrieval workflows that need a dependable source URL beside every record.

🎯 Why use it?

• Build legal research corpora without copying opinions by hand.
• Get standardized record shape across courts: opinion ID, cluster ID, case naming, docket, filing date, citations, and source URL.
• Keep chunk size consistent for embedding and reranking workflows (512 tokens with 50-token overlap).
• Support litigation analytics and case-law search features with structured citation metadata.
• Schedule repeatable research exports with consistent dataset output.

🚀 How to use it?

STEP 1 Choose Select courts, dates, and an optional topic.

STEP 2 Collect Start with a bounded opinion count.

STEP 3 Review Use the overview or citation view for your research workflow.

📋 Input fields

Field	Type	Required	Description
courtIds	array of court slugs	No	Use common federal slugs or another public CourtListener slug. Leave empty for the common federal set.
dateFrom	date	Yes	Inclusive filing-date start in YYYY-MM-DD format.
dateTo	date	Yes	Inclusive filing-date end in YYYY-MM-DD format.
searchQuery	text	No	Optional topic or phrase to narrow the search.
maxOpinions	integer	No	Maximum opinion records saved in one run.
courtListenerApiKey	secret text	No	Optional CourtListener account key for richer public detail retrieval.

📤 Output schema

Each dataset item is one opinion record:

{
    "opinion_id": "11314034",
    "cluster_id": "10846667",
    "court": "scotus",
    "court_full": "Supreme Court of the United States",
    "case_name": "Enbridge Energy, LP v. Nessel",
    "case_name_short": null,
    "docket_number": "24-783",
    "date_filed": "2026-04-22",
    "citation_count": 21,
    "citations": ["608 U.S. ___"],
    "absolute_url": "https://www.courtlistener.com/opinion/11314034/enbridge-energy-lp-v-nessel/",
    "source": "summary",
    "chunks": [
        { "idx": 0, "text": "...", "tokens": 512 },
        { "idx": 1, "text": "...", "tokens": 213 }
    ]
}

📊 Data table

Field	Type	Description
opinion_id	string	CourtListener opinion identifier.
court	string	CourtListener court slug.
case_name	string	Canonical case name.
docket_number	string	Docket number when published.
date_filed	date	Filing date.
citation_count	number	Citation count when published by the source.
citations	array	Published citation strings.
source	string	Whether the chunks came from full text or a public summary.
chunks	array	Text chunks with their order and token count.
absolute_url	URL	Direct public opinion page.

💰 Pricing

This Actor uses pay-per-event pricing. Empty runs cost nothing, and there are no subscriptions.

⭐ Enjoying CourtListener RAG Extractor?

⭐ ⭐ ⭐ ⭐ ⭐ One run replaces days of manually copying opinions and building embedding-ready chunks by hand. A 5-star rating takes 10 seconds and helps other legal AI and RAG engineers find this actor. Your feedback also tells us what to build next.

★  Rate this Actor on Apify

💡 Tips for better results

• Add a CourtListener account key when you need richer public detail retrieval.
• Narrow with searchQuery for topic-specific corpora.
• Keep date windows smaller for incremental backfills.
• Start with low maxOpinions for schema checks, then scale.

🚧 Limits

• The common federal court list is used when no court slugs are supplied.
• Additional court slugs depend on what CourtListener publishes publicly.
• No majority/concurrence/dissent section separation in v1.
• No citation graph extraction in v1.

⚠️ Legal disclaimer

This Actor extracts publicly available U.S. federal court opinions from CourtListener (operated by the Free Law Project). Output is not legal advice. Users are responsible for compliance with local professional-responsibility rules when using this data.

❓ FAQ

Do I need a CourtListener API key? No, but it is strongly recommended. Without a key, the Actor uses conservative rate limits and may rely more heavily on summary-level fields.

What happens when opinion detail endpoints are unavailable? The run continues with available search metadata and summary fallback so records still remain schema-consistent.

Does this include citation graph relationships? No. v1 includes citation strings and counts, not graph topology.

🛟 Support

If you need feature requests or issue triage, open a ticket in this repo's Issues tab.

🔗 Other actors

• arXiv scraper for RAG: papers as chunked JSON ↗ - pulls arXiv papers into fixed-token chunks for embedding pipelines.
• bioRxiv and medRxiv scraper for RAG: chunked JSON ↗ - extracts preprint biology and medicine papers as RAG-ready JSON.
• PubMed Scraper for RAG: Papers as Chunked JSON ↗ - normalizes PubMed biomedical literature into chunked records for retrieval.
• SEC EDGAR Scraper for RAG: 10-K/10-Q/8-K as JSON ↗ - converts SEC filings into structured, chunked JSON for financial AI corpora.