Legal Precedent Finder - USA

How is the legal data indexed and embeddings created?

• We gather our data from a wide array of court decisions across the United States, capturing the complexities of numerous legal issues.
• We then standardize this data to ensure accuracy and uniformity, preparing it for the next step.
• The textual information is extracted from the case laws, preprocessed to remove irrelevant elements and special characters, and tokenized.
• We utilize a specialized indexing algorithm tailored for legal text that takes into account the complex structure and hierarchies of legal regulations.
• High-dimensional vector embeddings with 1536 dimensions are created using the OpenAI text-embedding-ada-002 model.
• These embeddings are then safely stored in a database optimized for high-dimensional data, ensuring efficient storage and retrieval.

How do we keep the data updated?

Our system is connected to numerous U.S. court databases, allowing us to stay updated with the latest court decisions. We monitor and collect any new rulings, process and index them to ensure that our AI tool remains accurate and current in identifying legal issues.

How to use

• Python
• Curl

Python Code

You can retrieve the legal issue identifier embeddings using the embedelite Python package or by making a CURL request.

# This provides a list of embeddings
from embedelite import load_embedding

embeddings = load_embedding("legal-issues-us")
print(len(embeddings))
print(embeddings[1])

# This provides an object ready for database insertion
result = load_embedding("legal-issues-us", embed_for="embedelite")
# The result is {"embeddings": [], "documents": [], "ids": []}
print(result["embeddings"])
print(result["documents"])
print(result["ids"])

Curl

Request

curl -X POST -H "Content-Type: application/json" -d '{
  "doc_id": "legal-issues-us"
}' https://api.embedelite.com/v1/embeddings/download/

Response

{
  "mappings": {
    "properties": {
      "doc_source": { "type": "keyword" },
      "sentence": { "type": "text" },
      "embeddings": { "type": "dense_vector", "dims": 1536, "index": false },
      "doc_source": { "type": "keyword" }
    }
  }
}