> For the complete documentation index, see [llms.txt](https://epsilla-inc.gitbook.io/epsilladb/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://epsilla-inc.gitbook.io/epsilladb/epsilla-vector-database/advanced-topics/dense-vector-vs.-sparse-vector.md).

# Dense vector vs. sparse vector

## Dense Vectors

Dense vectors are numerical representations of semantic meaning, typically generated by embedding models like [OpenAI/text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings/second-generation-models), [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2), etc. These vectors, where most or all elements are non-zero, are particularly effective for semantic search, returning the most similar results according to specific distance metrics even in the absence of exact matches.

Dense vector enable complex semantic queries, useful in scenarios where understanding the context or meaning is more important than keyword matches. It is widely used in (1) Natural language processing, where dense vectors can represent word embeddings where each dimension captures a syntactic or semantic property; (2) Image and video analysis, where dense vectors are ideal for representing pixel-based data in images and videos; (3) Recommendation systems, where dense vectors represent user or item profiles in a feature space for content-based filtering.

Compared with sparse vectors, computational and storage requirements are higher due to the nature of dense vectors, especially for large datasets.

### Define dense vector field in Epsilla table:

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.create_table(
    table_name="MyTable",
    table_fields=[
        {"name": "Embedding", "dataType": "VECTOR_FLOAT", "dimensions": 1536}
    ]
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
await db.createTable('MyTable',
  [
    {"name": "Embedding", "dataType": "VECTOR_FLOAT", "dimensions": 1536}
  ]
);
```

{% endtab %}
{% endtabs %}

### Insert a dense vector record:

Epsilla represents dense vector as an array of float32 numbers.

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.insert(
  table_name="MyTable",
  records=[
    {"Embedding": [-0.074163,0.238575,-0.141831,0.117338, ...]},
  ]
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
await db.insert('MyTable',
  [
    {"Embedding": [-0.074163,0.238575,-0.141831,0.117338, ...]}
  ]
);
```

{% endtab %}
{% endtabs %}

### Query a dense vector field:

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.query(
  table_name="MyTable",
  query_field="Embedding",
  query_vector=[-0.074163,0.238575,-0.141831,0.117338, ...],
  limit=2
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
const query = await db.query(
  'MyTable',
  {
    queryField: 'Embedding',
    queryVector: [-0.074163,0.238575,-0.141831,0.117338, ...],
    limit: 2
  }
);
```

{% endtab %}
{% endtabs %}

## Sparse Vectors

Sparse vectors, characterized by a large number of dimensions with few non-zero values, are ideal for keyword-based searches. Each vector represents a document where dimensions are words from a dictionary, and values indicate the importance of these words in the document. This representation is effective in situations where precise keyword matches and their frequency are critical.

Famous sparse vector generation algorithms including [BM25](https://www.wikiwand.com/en/Okapi_BM25), [SPLADE](https://arxiv.org/abs/2109.10086), etc. Algorithms like BM25 computes text document relevance based on keyword matches and their distribution. They are very efficient in keyword-based search, and especially effective for data with large, but sparsely populated feature spaces.

Compared with dense vectors, sparse vectors are less effective in capturing the context or semantic meaning.

### Define sparse vector field in Epsilla table:

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.create_table(
    table_name="MyTable",
    table_fields=[
        {
            "name": "Embedding",
            "dataType": "SPARSE_VECTOR_FLOAT",
            "dimensions": 65535,
            "metricType": "DOT_PRODUCT"
        }
    ]
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
await db.createTable('MyTable',
  [
    {
      "name": "Embedding",
      "dataType": "SPARSE_VECTOR_FLOAT",
      "dimensions": 65535,
      "metricType": "DOT_PRODUCT"
    }
  ]
);
```

{% endtab %}
{% endtabs %}

### Insert a sparse vector record:

Epsilla represents sparse values as a dictionary of two arrays: **indices** and **values**. The elements of indices have type uint32; the elements of values have type float32.

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.insert(
  table_name="MyTable",
  records=[
    {
      "Embedding": {
        "indices": [32, 103, 2345, 10384],
        "values": [0.074163, 0.238575, 0.141831, 0.117338]
      }
    }
  ]
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
await db.insert('MyTable',
  [
    {
      "Embedding": {
        "indices": [32, 103, 2345, 10384],
        "values": [0.074163, 0.238575, 0.141831, 0.117338]
      }
    }
  ]
);
```

{% endtab %}
{% endtabs %}

### Query a sparse vector field:

{% tabs %}
{% tab title="Python" %}

```python
status_code, response = db.query(
  table_name="MyTable",
  query_field="Embedding",
  query_vector={
    "indices": [32, 103, 2345, 10384],
    "values": [0.074163, 0.238575, 0.141831, 0.117338]
  },
  limit=2
)
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
const query = await db.query(
  'MyTable',
  {
    queryField: 'Embedding',
    queryVector: {
      "indices": [32, 103, 2345, 10384],
      "values": [0.074163, 0.238575, 0.141831, 0.117338]
    },
    limit: 2
  }
);
```

{% endtab %}
{% endtabs %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://epsilla-inc.gitbook.io/epsilladb/epsilla-vector-database/advanced-topics/dense-vector-vs.-sparse-vector.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.