Match a job Paths Subjects Questions Quizzes Pricing
Overview Read Practice

Practice — Chunking and Embedding Strategies (5 questions)

Pro content

Sign up free, then start a 14-day Pro trial — no card needed.

Intermediate Open Free

Choosing a Chunking Strategy for a Legal Contract Corpus Permalink →

You're building RAG over a corpus of 20,000 signed legal contracts for an internal "ask a question about any contract" tool used by the legal team. Contracts have numbered clauses and sub-clauses (structure), but individual clauses are dense — a single clause can reference definitions from three sections earlier, and a question like "what's our liability cap under this contract?" may need the definitions section plus the liability clause plus an exceptions sub-clause to answer correctly.

  1. Which chunking strategy would you start with, and why?
  2. Legal wants citations down to the exact clause. How does that constrain your design?
  3. How would you handle the cross-reference problem (a clause that only makes sense alongside a definition several sections away)?

Share this question

Intermediate Open Pro

Diagnosing a Recall Drop After a Chunk-Size Change

Unlock this question →
Intermediate Open Pro

Planning an Embedding Model Migration

Unlock this question →
Intermediate Open Pro

Designing Chunk Metadata for a Multi-Tenant, Multi-Product Knowledge Base

Unlock this question →
Intermediate Open Pro

Designing an Empirical Comparison of Two Chunking Configs

Unlock this question →

We use cookies for product analytics to improve OmniAtlas. See our Privacy Policy.