Module 2Chunking Strategies
Embedding models have a maximum token limit. all-MiniLM-L6-v2 from Module 1 takes 256 tokens, larger models take 8,000 or more, and anything past the limit is dropped without an error. Check your model’s card for its limit.
Fitting isn’t the only reason to split. A chunk is the unit that gets retrieved, so one vector covering several topics averages them together and matches every query weakly, while a chunk that’s too small loses the context that made the result useful.
| Strategy | How it works | Trade-off |
|---|---|---|
| Fixed-Size | Split every N tokens regardless of content boundaries | May cut sentences mid-thought |
| Semantic | New chunk when topic or meaning shifts | Slower; needs a model to detect shifts |
| Sliding Window | Chunks overlap to preserve context across the cut | More storage; duplicate content across results |
Fixed-Size
Semantic
Sliding Window
