> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pulsejet.jetengine.tech/llms.txt
> Use this file to discover all available pages before exploring further.

# Index Types

> Vector indexing capabilities of PulsejetDB.

Pulsejet has 7 types of indexes. These indexes has different characteristics and optimizations based on different input.

<Check> We are working on **custom index implementation** and it will become Pulsejet's de-facto index implementation. </Check>

### Index Types

1. `FlatL2` - Flat Index with L2 distance calculation
   * It is exact search with L2 (Euclidean Distance).
2. `FlatIP` - Flat Index with Cosine Similarity (Inner Product) distance
   * It is exact search with Inner Product
3. `HNSW` - [Hierarchical Navigable Small Worlds](https://arxiv.org/pdf/1603.09320)
4. `IVFFlat` - Inverted File Index - Flat
5. `IVFScalar` - Inverted File Index - Scalar
6. `IVFPQ` - Inverted File Index - Product Quantized
7. `OPQPQ` - [Optimized PQ](https://www.microsoft.com/en-us/research/wp-content/uploads/2013/11/pami13opq.pdf) chained with Flat Product Quantization

### How to select my index type?

Below you can find how to select which index and their general starting requirements.

<Tip>
  Whatever your selection will be (unless you don't disable optimizer) your indexes will optimized to better indexes through time by Pulsejet (with given constraints.)

  Learn more about [Optimizer Structure](/design/optimizer).
</Tip>

<Tabs>
  <Tab title="FlatL2">
    First, you can use `FlatL2` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "FlatL2",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    ☝️ Welcome to the content that you can only see inside the first Tab.
  </Tab>

  <Tab title="FlatIP">
    First, you can use `FlatIP` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "FlatIP",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    ✌️ Here's content that's only inside the second Tab.
  </Tab>

  <Tab title="HNSW">
    First, you can use `HNSW` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "HNSW",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    💪 Here's content that's only inside the third Tab.
  </Tab>

  <Tab title="IVFFlat">
    First, you can use `IVFFlat` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "IVFFlat",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    💪 Here's content that's only inside the third Tab.
  </Tab>

  <Tab title="IVFScalar">
    First, you can use `IVFScalar` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "IVFScalar",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    💪 Here's content that's only inside the third Tab.
  </Tab>

  <Tab title="IVFPQ">
    First, you can use `IVFPQ` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "IVFPQ",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    💪 Here's content that's only inside the third Tab.
  </Tab>

  <Tab title="OPQPQ">
    First, you can use `OPQPQ` index at [collection creation](/api-reference/collection/create_collection) with:

    ```json
    {
        "name": "sift1m",
        "vector_config": {
            "size": 128,
            "index_type": "OPQPQ",
            "on_disk": true
        },
        "optimizer_config": {}
    }
    ```

    💪 Here's content that's only inside the third Tab.
  </Tab>
</Tabs>