Why would you index sentences but provide the surrounding paragraph as context?

Explain the pattern of searching for small, granular chunks but feeding a larger "parent" context to the LLM. Why is this more accurate?

If your user queries are short "slang" phrases but your documents are formal legal texts, how do you ensure the embedding model can bridge that semantic gap?

How does the "Extraction, Transformation, and Loading" process differ when preparing data for a Vector Database versus a traditional SQL database?