230 Vector indexing
Course overview​
This course is self-contained. However, we recommend that you go through one of the 101-level courses, such as that for working with text, your own vectors, or multimodal data.
The vector index is a key component of Weaviate's search capabilities. It allows you to search for vectors based on their similarity to a query vector, and to retrieve the objects that are associated with those vectors.
Weaviate offers multiple types of vector indexes, each with its own strengths and weaknesses. Each index is also configurable, allowing you to tune its performance to your specific use case.
This course will introduce you to the different types of vector indexes available in Weaviate, and how to configure them to best suit your use case.
Learning objectives​
  Here, we will cover:
Learning Goals- What vector index types are available, when to select each one and how to configure them.
  By the time you are finished, you will be able to:
Learning Outcomes- Name available vector index types in Weaviate.
- Select an appropriate index type for a given use case.
- Recite relationships between HNSW parameters and search performance.
- Describe how quantization affects each index type.
- Create collections with your chosen vector index type and preferred parameters.
Units​
1. Vector index: Overview
What is a vector index, and why is it important?
2. HNSW index in depth
Learn about the HNSW index type, and how to tune it for your use case.
3. Flat index in depth
Learn about the flat index type, and how to tune it for your use case.
4. Dynamic index in depth
Learn about the dynamic index type, and how to tune it for your use case.