To learn how to choose an appropriate index for your application scenarios, please read [How to Select an Index in Milvus](https://medium.com/@milvusio/how-to-choose-an-index-in-milvus-4f3d15259212).
Different index types use different index params in construction and query. All index params are represented by the structure of the map. This doc shows the map code in python.
**IVF** (_Inverted File_) is an index type based on quantization. It divides the points in space into `nlist` units by the clustering method. During searching vectors, it compares the distance between the target vector and the center of all units, and then selects the `nprobe` nearest unit. Afterwards, it compares all the vectors in these selected cells to get the final result.
**PQ** (_Product Quantization_) uniformly decomposes the original high-dimensional vector space into Cartesian products of `m` low-dimensional vector spaces and then quantizes the decomposed low-dimensional vector spaces. Instead of calculating the distances between the target vector and the center of all the units, product quantization enables the calculation of distances between the target vector and the clustering center of each low-dimensional space and greatly reduces the time complexity and space complexity of the algorithm.
IVF_PQ performs IVF index clustering, and then quantizes the product of vectors. Its index file is even smaller than IVF_SQ8, but it also causes a loss of accuracy during searching.
**IVF_SQ8** does scalar quantization for each vector placed in the unit based on IVF. Scalar quantization converts each dimension of the original vector from a 4-byte floating-point number to a 1-byte unsigned integer, so the IVF_SQ8 index file occupies much less space than the IVF_FLAT index file. However, scalar quantization results in a loss of accuracy during searching vectors.
An optimized version of IVF_SQ8 that requires both CPU and GPU to work. Unlike IVF_SQ8, IVF_SQ8H uses a GPU-based coarse quantizer, which greatly reduces the time to quantize.
**ANNOY** (_Approximate Nearest Neighbors Oh Yeah_) is an index that uses a hyperplane to divide a high-dimensional space into multiple subspaces, and then stores them in a tree structure.
When searching for vectors, ANNOY follows the tree structure to find subspaces closer to the target vector, and then compares all the vectors in these subspaces (The number of vectors being compared should not be less than `search_k`) to obtain the final result. Obviously, when the target vector is close to the edge of a certain subspace, sometimes it is necessary to greatly increase the number of searched subspaces to obtain a high recall rate. Therefore, ANNOY uses `n_trees` different methods to divide the whole space, and searches all the dividing methods simultaneously to reduce the probability that the target vector is always at the edge of the subspace.
**HNSW** (_Hierarchical Navigable Small World Graph_) is a graph-based indexing algorithm. It builds a multi-layer navigation structure for an image according to certain rules. In this structure, the upper layers are more sparse and the distances between nodes are farther; the lower layers are denser and the distances between nodes are closer. The search starts from the uppermost layer, finds the node closest to the target in this layer, and then enters the next layer to begin another search. After multiple iterations, it can quickly approach the target position.
**RHNSW_PQ** is a variant index type combining PQ and HNSW. It first uses PQ to quantize the vector, then uses HNSW to quantize the PQ quantization result to get the index.
**RHNSW_SQ** is a variant index type combining SQ and HNSW. It uses SQ to quantize the vector, then uses HNSW to quantize the SQ quantization result to get the index.
**NSG** (_Refined Navigating Spreading-out Graph_) is a graph-based indexing algorithm. It sets the center position of the whole image as a navigation point, and then uses a specific edge selection strategy to control the out-degree of each point (less than or equal to `out_degree`). Therefore, it can reduce memory usage and quickly locate the target position nearby during searching vectors.
The graph construction process of NSG is as follows:
1. Find `knng` nearest neighbors for each point.
2. Iterate at least `search_length` times based on `knng` nearest neighbor nodes to select `candidate_pool_size` possible nearest neighbor nodes.
3. Construct the out-edge of each point in the selected `candidate_pool_size` nodes according to the edge selection strategy.
The query process is similar to the graph building process. It starts from the navigation point and iterates at least `search_length` times to get the final result.
- building parameters:
**search_length**: Number of query iterations.
**out_degree**: Maximum out-degree of the node.
**candidate_pool_size**: Candidate pool size of the node.
