Astra for LawOpenAI
|
TILDEielab
|
|||||
Related Products
|
||||||
About
Astra for Law is an AI foundation for law firms and legal technology companies to build products and workflows around their expertise. It combines GPT-6 Astra with settings, tools, and context tailored for professional legal work, including a legal search index and instructions for legal analysis and writing. It can search U.S. case law, statutes, regulations, court rules, and administrative decisions across a corpus of more than 230 million URLs, with sources added daily. It is designed to find relevant authorities and passages, assess how relevant and binding they are, and apply that research to client facts, arguments, deal terms, and legal strategy. Custom instructions help distinguish court holdings from other observations, address authorities that weaken an argument, explain contractual risk, and identify uncertainty. Firms can customize workflows around their own precedents, methods, proprietary data, permitted sources, and review processes.
|
About
TILDE (Term Independent Likelihood moDEl) is a passage re-ranking and expansion framework built on BERT, designed to enhance retrieval performance by combining sparse term matching with deep contextual representations. The original TILDE model pre-computes term weights across the entire BERT vocabulary, which can lead to large index sizes. To address this, TILDEv2 introduces a more efficient approach by computing term weights only for terms present in expanded passages, resulting in indexes that are 99% smaller than those of the original TILDE. This efficiency is achieved by leveraging TILDE as a passage expansion model, where passages are expanded using top-k terms (e.g., top 200) to enrich their content. It provides scripts for indexing collections, re-ranking BM25 results, and training models using datasets like MS MARCO.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Law firms, legal professionals, and legal technology developers needing to perform and build AI-powered legal research, analysis, drafting, and professional workflows
|
Audience
Academic researchers and developers searching for a tool to implement efficient and scalable passage re-ranking and expansion techniques
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Supported
Free Trial
Not Supported
|
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationOpenAI
Founded: 2015
United States
openai.com/index/astra-for-law/
|
Company Informationielab
United States
github.com/ielab/TILDE/tree/main
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
GPT-6 Astra
Supported
GPT-6 Luna
Supported
GPT-6 Sol
Supported
GPT-6.1 Sol
Supported
Harvey AI
Supported
Holo4
Supported
Hugging Face
Not Supported
Legora
Supported
OpenAI
Supported
Python
Not Supported
|
Integrations
GPT-6 Astra
Not Supported
GPT-6 Luna
Not Supported
GPT-6 Sol
Not Supported
GPT-6.1 Sol
Not Supported
Harvey AI
Not Supported
Holo4
Not Supported
Hugging Face
Supported
Legora
Not Supported
OpenAI
Not Supported
Python
Supported
|
|||||
|
|
|