Update vector-search.md

Author: jcodella

articles/cosmos-db/nosql/vector-search.md

@@ -118,7 +118,7 @@ The container vector policy can be described as JSON objects. Here are two examp
 A few points to note:
   - The `flat` and `quantizedFlat` index types uses Azure Cosmos DB's index to store and read each vector when performing a vector search. Vector searches with a `flat` index are brute-force searches and produce 100% accuracy or recall. That is, it's guaranteed to find the most similar vectors in the dataset. However, there's a limitation of `505` dimensions for vectors on a flat index.
 
-  - The `quantizedFlat` index stores quantized (compressed) vectors on the index. Vector searches with `quantizedFlat` index are also brute-force searches, however their accuracy might be slightly less than 100% since the vectors are quantized before adding to the index. However, vector searches with `quantized flat` should have lower latency, higher throughput, and lower RU cost than vector searches on a `flat` index. This is a good option for scenarios where you're using query filters to narrow down the vector search to a relatively small set of vectors, and near-perfect accuracy is required.
+  - The `quantizedFlat` index stores quantized (compressed) vectors on the index. Vector searches with `quantizedFlat` index are also brute-force searches, however their accuracy might be slightly less than 100% since the vectors are quantized before adding to the index. However, vector searches with `quantized flat` should have lower latency, higher throughput, and lower RU cost than vector searches on a `flat` index. This is a good option for scenarios where you're using query filters to narrow down the vector search to a relatively small set of vectors (fewer than 100,000) and near-perfect accuracy is required. 
 
   - The `diskANN` index is a separate index defined specifically for vectors using [DiskANN](https://www.microsoft.com/research/publication/diskann-fast-accurate-billion-point-nearest-neighbor-search-on-a-single-node/), a suite of high performance vector indexing algorithms developed by Microsoft Research. DiskANN indexes can offer some of the lowest latency, highest throughput, and lowest RU cost queries, while still maintaining high accuracy. However, since DiskANN is an approximate nearest neighbors (ANN) index, the accuracy can be lower than `quantizedFlat` or `flat`.
 
@@ -173,6 +173,8 @@ Here are examples of valid vector index policies:
     ]
 }
 ```
+> [!NOTE]
+> The Quantized Flat index requires that at least 1,000 vectors to be inserted. This is to ensure accuracy of the quantization process. If there are fewer than 1,000 vectors, a full scan is executed instead, and will lead to higher RU charges for a vector search query.
 
 ## Perform vector search with queries using VectorDistance()