semantic_search

Pro

Search case law using natural language and AI embeddings. Finds conceptually related cases, not just keyword matches.

Parameters

Parameter	Type	Required	Description
`query`	string	Yes	Natural language query describing the legal concept
`court`	string	No	Filter by court ID (e.g., `scotus`, `ca9`)
`date_after`	string	No	Cases after this date (YYYY-MM-DD)
`date_before`	string	No	Cases before this date (YYYY-MM-DD)
`limit`	number	No	Max results (1-50, default: 10)

Example Request

{
  "query": "employer retaliation after employee reports safety violations",
  "court": "ca9",
  "limit": 5
}

Example Response

{
  "results": [
    {
      "cluster_id": 4567890,
      "case_name": "Smith v. Acme Corp.",
      "citation": "45 F.4th 123 (9th Cir. 2022)",
      "court": "ca9",
      "date_filed": "2022-08-15",
      "similarity_score": 0.92,
      "snippet": "...employer terminated plaintiff within weeks of her OSHA complaint..."
    }
  ],
  "query_embedding_model": "bge-base-en-v1.5"
}

How It Works

Unlike keyword search, semantic search understands meaning:

Query	Keyword Search	Semantic Search
"fired for complaining"	Matches "fired" and "complaining"	Also finds "terminated", "retaliated", "adverse action"
"workplace discrimination"	Exact phrase only	Finds related concepts like "hostile environment", "disparate treatment"

Use Cases

Finding cases with similar fact patterns
Discovering precedents using plain English
Research when you don't know the legal terminology

semantic_search

semantic_search

Parameters

Example Request

Example Response

How It Works

Use Cases

See Also

On this page