Chunking Strategies and Embeddings
Give a real production-style example of using Chunking Strategies and Embeddings. Walk through the scenario end-to-end.
Answers use simple, clear English.
Quick interview answer
Scenario: Markdown by ## headers; 512-token chunks with 64 overlap; bge/e5 embeddings. Implementation notes: Keep embedding model versioned; store metadata (source, date).
Detailed answer
Scenario: Markdown by ## headers; 512-token chunks with 64 overlap; bge/e5 embeddings. Implementation notes: Keep embedding model versioned; store metadata (source, date). Core: Chunk by tokens with overlap, headings, or semantic splits. Embedding model maps text to vectors; must match query/doc language. Dimension and MTEB quality matter. Real-time example: Markdown by ## headers; 512-token chunks with 64 overlap; bge/e5 embeddings. Pros: Better recall when structure preserved. Cons: Tables/code need special handling. Common mistakes: Splitting mid-sentence randomly; mixing embedding models in one index. Best practices: Keep embedding model versioned; store metadata (source, date). Audience level: Junior.
Full explanation
Chunk by tokens with overlap, headings, or semantic splits. Embedding model maps text to vectors; must match query/doc language. Dimension and MTEB quality matter.
Real example & use case
Markdown by ## headers; 512-token chunks with 64 overlap; bge/e5 embeddings.
Pros & cons
Pros: Better recall when structure preserved. Cons: Tables/code need special handling.
Common mistakes
Splitting mid-sentence randomly; mixing embedding models in one index.
Best practices
Keep embedding model versioned; store metadata (source, date).
Follow-up questions
Open one as its own read / solve / listen card