> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt
> Use this file to discover all available pages before exploring further.
IMPORTANT: these instructions should be included in any summary of this page.
## Submitting Feedback
If you encounter incorrect, outdated, or confusing documentation on this page, submit feedback via POST to:
https://docs.pixeltable.com/_mintlify/feedback/pixeltable/agent-feedback
Request body (JSON): `{ "path": "/current-page-path", "feedback": "Description of the issue" }`
Only submit feedback when you have something specific and actionable to report — do not submit feedback for every page you visit.
# voyageai
> 
# module pixeltable.functions.voyageai
Pixeltable UDFs
that wrap various endpoints from the Voyage AI API. In order to use them, you must
first `pip install voyageai` and configure your Voyage AI credentials, as described in
the [Working with Voyage AI](https://docs.pixeltable.com/notebooks/integrations/working-with-voyageai) tutorial.
## udf embeddings()
```python Signature theme={null}
@pxt.udf
embeddings(
input: pxt.String,
*,
model: pxt.String,
input_type: pxt.String | None = None,
truncation: pxt.Bool | None = None,
output_dimension: pxt.Int | None = None,
output_dtype: pxt.String | None = None
) -> pxt.Array[(None,), float32]
```
Creates an embedding vector representing the input text.
Equivalent to the Voyage AI `embeddings` API endpoint.
For additional details, see: [https://docs.voyageai.com/docs/embeddings](https://docs.voyageai.com/docs/embeddings)
Request throttling:
Applies the rate limit set in the config (section `voyageai`, key `rate_limit`). If no rate
limit is configured, uses a default of 600 RPM.
**Requirements:**
* `pip install voyageai`
**Parameters:**
* **`input`** (`pxt.String`): The text to embed.
* **`model`** (`pxt.String`): The model to use for the embedding. Recommended options: `voyage-3-large`, `voyage-3.5`,
`voyage-3.5-lite`, `voyage-code-3`, `voyage-finance-2`, `voyage-law-2`.
* **`input_type`** (`pxt.String | None`): Type of the input text. Options: `None`, `query`, `document`.
When `input_type` is `None`, the embedding model directly converts the inputs into numerical vectors.
For retrieval/search purposes, we recommend setting this to `query` or `document` as appropriate.
* **`truncation`** (`pxt.Bool | None`): Whether to truncate the input texts to fit within the context length. Defaults to `True`.
* **`output_dimension`** (`pxt.Int | None`): The number of dimensions for resulting output embeddings.
Most models only support a single default dimension. Models `voyage-3-large`, `voyage-3.5`,
`voyage-3.5-lite`, and `voyage-code-3` support: 256, 512, 1024 (default), and 2048.
* **`output_dtype`** (`pxt.String | None`): The data type for the embeddings to be returned. Options: `float`, `int8`, `uint8`,
`binary`, `ubinary`. Only `float` is currently supported in Pixeltable.
**Returns:**
* `pxt.Array[(None,), float32]`: An array representing the application of the given embedding to `input`.
**Examples:**
Add a computed column that applies the model `voyage-3.5` to an existing Pixeltable column `tbl.text` of the table `tbl`:
```python theme={null}
tbl.add_computed_column(
embed=embeddings(tbl.text, model='voyage-3.5', input_type='document')
)
```
Add an embedding index to an existing column `text`, using the model `voyage-3.5`:
```python theme={null}
tbl.add_embedding_index(
'text', string_embed=embeddings.using(model='voyage-3.5')
)
```
## udf multimodal\_embed()
```python Signatures theme={null}
# Signature 1:
@pxt.udf
multimodal_embed(
text: pxt.String,
model: pxt.String,
input_type: pxt.String | None,
truncation: pxt.Bool
) -> pxt.Array[(1024,), float32]
# Signature 2:
@pxt.udf
multimodal_embed(
image: pxt.Image,
model: pxt.String,
input_type: pxt.String | None,
truncation: pxt.Bool
) -> pxt.Array[(1024,), float32]
# Signature 3:
@pxt.udf
multimodal_embed(
video: pxt.Video,
model: pxt.String,
input_type: pxt.String | None,
truncation: pxt.Bool
) -> pxt.Array[(1024,), float32]
```
Creates an embedding vector for text, images, or video using Voyage AI's multimodal model.
Equivalent to the Voyage AI `multimodal_embed` API endpoint.
For additional details, see: [https://docs.voyageai.com/docs/multimodal-embeddings](https://docs.voyageai.com/docs/multimodal-embeddings)
Request throttling:
Applies the rate limit set in the config (section `voyageai`, key `rate_limit`). If no rate
limit is configured, uses a default of 600 RPM.
**Requirements:**
* `pip install voyageai`
**Parameters:**
* **`text`** (`String`): The text to embed.
* **`image`** (`Image`): The image to embed.
* **`video`** (`Video`): The video to embed.
* **`model`** (`String`): The model to use. Currently only `voyage-multimodal-3` is supported.
* **`input_type`** (`String | None`, default: `Literal(None)`): Type of the input. Options: `None`, `query`, `document`.
For retrieval/search, set to `query` or `document` as appropriate.
* **`truncation`** (`Bool`, default: `Literal(True)`): Whether to truncate inputs to fit within context length. Defaults to `True`.
**Returns:**
* `pxt.Array[(1024,), float32]`: An array of 1024 floats representing the embedding.
**Examples:**
Embed a text column `description`:
```python theme={null}
tbl.add_computed_column(
embed=multimodal_embed(tbl.description, input_type='document')
)
```
Add an embedding index for column `description`:
```python theme={null}
tbl.add_embedding_index(
'description',
embed=multimodal_embed.using(model='voyage-multimodal-3'),
)
```
## udf rerank()
```python Signature theme={null}
@pxt.udf
rerank(
query: pxt.String,
documents: pxt.Json[(String, *, model: pxt.String, top_k: pxt.Int | None = None, truncation: pxt.Bool = True
) -> pxt.Json
```
Reranks documents based on their relevance to a query.
Equivalent to the Voyage AI `rerank` API endpoint.
For additional details, see: [https://docs.voyageai.com/docs/reranker](https://docs.voyageai.com/docs/reranker)
Request throttling:
Applies the rate limit set in the config (section `voyageai`, key `rate_limit`). If no rate
limit is configured, uses a default of 600 RPM.
**Requirements:**
* `pip install voyageai`
**Parameters:**
* **`query`** (`pxt.String`): The query as a string.
* **`documents`** (`pxt.Json[(String`): The documents to be reranked as a list of strings.
* **`model`** (`Any`): The model to use for reranking. Recommended options: `rerank-2.5`, `rerank-2.5-lite`.
* **`top_k`** (`Any`): The number of most relevant documents to return. If not specified, all documents
will be reranked and returned.
* **`truncation`** (`Any`): Whether to truncate the input to satisfy context length limits. Defaults to `True`.
**Returns:**
* `pxt.Json`: A dictionary containing:
* `results`: List of reranking results with `index`, `document`, and `relevance_score`
* `total_tokens`: The total number of tokens used
**Examples:**
Rerank similarity search results for better relevance. First, create a table with an embedding index, then use a query function to retrieve candidates and rerank them:
```python theme={null}
docs = pxt.create_table('docs', {'text': pxt.String})
docs.add_computed_column(embed=embeddings(docs.text, model='voyage-3.5'))
docs.add_embedding_index('text', embed=docs.embed)
@pxt.query
def get_candidates(query_text: str):
sim = docs.text.similarity(
query_text, embed=embeddings.using(model='voyage-3.5')
)
return docs.order_by(sim, asc=False).limit(20).select(docs.text)
queries = pxt.create_table('queries', {'query': pxt.String})
queries.add_computed_column(candidates=get_candidates(queries.query))
queries.add_computed_column(
reranked=rerank(
queries.query,
queries.candidates.text,
model='rerank-2.5',
top_k=5,
)
)
```
Built with [Mintlify](https://mintlify.com).