> ## 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If you encounter incorrect, outdated, or confusing documentation on this page, submit feedback via POST to: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.
# Working with Voyage AI in Pixeltable
This documentation page is also available as an interactive notebook. You can launch the notebook in
Kaggle or Colab, or download it for use with an IDE or local Jupyter installation, by clicking one of the
above links.
export const quartoRawHtml = [`
| text |
embedding |
| The Mediterranean diet emphasizes fish, olive oil, and vegetables,
believed to reduce chronic diseases. |
[ 0.048 0.016 0.002 0.026 0.038 0.013 ... -0.015 -0.034 -0.016 0.007
0.046 -0.011] |
| Photosynthesis in plants converts light energy into glucose and
produces essential oxygen. |
[ 0.013 0.023 -0.004 0.052 0.037 0.022 ... -0.013 -0.042 0.001 0.008
-0.02 -0.016] |
| 20th-century innovations, from radios to smartphones, centered on
electronic advancements. |
[ 4.373e-03 4.474e-02 -6.796e-05 2.745e-02 4.904e-02 6.148e-03 ...
-1.833e-02 -4.274e-02 -4.713e-03 -1.739e-02 -1.540e-03 -2.306e-02] |
`, `
| text |
score |
| The Mediterranean diet emphasizes fish, olive oil, and vegetables,
believed to reduce chronic diseases. |
0.863 |
| Photosynthesis in plants converts light energy into glucose and
produces essential oxygen. |
0.649 |
| Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,'
endure in literature. |
0.621 |
`, `
| query |
top_document |
top_score |
| When is Apple's conference call scheduled? |
Apple's conference call to discuss fourth fiscal quarter results is
scheduled for Thursday, November 2, 2023. |
0.93 |
`, `
| query |
top_results |
| When is Apple's conference call scheduled? |
[{"index": 4, "document": "Apple's conference call to discuss fourth
fiscal quarter results is scheduled for Thursday, November 2, 2023.",
"relevance_score": 0.93}, {"index": 2, "document": "20th-century
innovations, from radios to smartphones, centered on electronic
advancements.", "relevance_score": 0.283}, {"index": 0, "document": "The
Mediterranean diet emphasizes fish, olive oil, and vegetables, believed
to reduce chronic diseases.", "relevance_score": 0.264}] |
`, `
| image |
caption |
image_embedding |
text_embedding |
|
A person standing next to an elephant |
[-0.017 -0.001 0.015 0.008 -0.025 -0.012 ... 0.01 0.058 -0.031 0.017
0.011 -0.055] |
[ 0.012 -0.002 -0.024 0.012 -0.036 -0.003 ... -0.041 0.007 0.019
-0.013 0.027 0.001] |
`];
Pixeltable’s Voyage AI integration enables you to access
state-of-the-art embedding and reranker models via the Voyage AI API.
### Prerequisites
* A Voyage AI account with an API key ([https://www.voyageai.com/](https://www.voyageai.com/))
### Important notes
* Voyage AI usage may incur costs based on your Voyage AI plan.
* Be mindful of sensitive data and consider security measures when
integrating with external services.
First you’ll need to install required libraries and enter your Voyage AI
API key.
```python theme={null}
%pip install -qU voyageai
```
```python theme={null}
import getpass
import os
if 'VOYAGE_API_KEY' not in os.environ:
os.environ['VOYAGE_API_KEY'] = getpass.getpass(
'Enter your Voyage AI API key:'
)
```
Now let’s create a Pixeltable directory to hold the tables for our demo.
```python theme={null}
import pixeltable as pxt
# Remove the 'voyageai_demo' directory and its contents, if it exists
pxt.drop_dir('voyageai_demo', force=True)
pxt.create_dir('voyageai_demo')
```
Created directory 'voyageai\_demo'.
\
## Text embeddings
Voyage AI provides state-of-the-art embedding models for semantic search
and RAG applications.
```python theme={null}
from pixeltable.functions import voyageai
# Create a table for document embeddings
docs_t = pxt.create_table('voyageai_demo/documents', {'text': pxt.String})
# Add computed column with Voyage embeddings
docs_t.add_computed_column(
embedding=voyageai.embeddings(
docs_t.text, model='voyage-3.5', input_type='document'
)
)
```
Created table 'documents'.
Added 0 column values with 0 errors.
No rows affected.
```python theme={null}
# Insert some sample documents
documents = [
'The Mediterranean diet emphasizes fish, olive oil, and vegetables, believed to reduce chronic diseases.',
'Photosynthesis in plants converts light energy into glucose and produces essential oxygen.',
'20th-century innovations, from radios to smartphones, centered on electronic advancements.',
'Rivers provide water, irrigation, and habitat for aquatic species, vital for ecosystems.',
"Apple's conference call to discuss fourth fiscal quarter results is scheduled for Thursday, November 2, 2023.",
"Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature.",
]
docs_t.insert({'text': doc} for doc in documents)
```
Inserting rows into \`documents\`: 6 rows \[00:00, 2561.67 rows/s]
Inserted 6 rows with 0 errors.
6 rows inserted, 12 values computed.
```python theme={null}
# View the embeddings
docs_t.select(docs_t.text, docs_t.embedding).head(3)
```
## Embedding index for similarity search
You can use Voyage AI embeddings with Pixeltable’s embedding index for
efficient similarity search.
```python theme={null}
# Create a table with an embedding index
search_t = pxt.create_table('voyageai_demo/search', {'text': pxt.String})
# Add embedding index for similarity search
embed_fn = voyageai.embeddings.using(
model='voyage-3.5', input_type='document'
)
search_t.add_embedding_index('text', string_embed=embed_fn)
```
Created table 'search'.
```python theme={null}
# Insert documents
search_t.insert({'text': doc} for doc in documents)
```
Inserting rows into \`search\`: 6 rows \[00:00, 973.68 rows/s]
Inserted 6 rows with 0 errors.
6 rows inserted, 12 values computed.
```python theme={null}
# Perform similarity search
sim = search_t.text.similarity(
string='What are the health benefits of Mediterranean food?'
)
search_t.order_by(sim, asc=False).limit(3).select(
search_t.text, score=sim
).collect()
```
## Reranking
Voyage AI’s rerankers can refine search results by providing more
accurate relevance scores.
```python theme={null}
# Create a table for reranking
rerank_t = pxt.create_table(
'voyageai_demo/rerank', {'query': pxt.String, 'documents': pxt.Json}
)
# Add computed column with reranking results
rerank_t.add_computed_column(
reranked=voyageai.rerank(
rerank_t.query, rerank_t.documents, model='rerank-2.5', top_k=3
)
)
```
Created table 'rerank'.
Added 0 column values with 0 errors.
No rows affected.
```python theme={null}
# Insert query and documents to rerank
rerank_t.insert(
[
{
'query': "When is Apple's conference call scheduled?",
'documents': documents,
}
]
)
```
Inserting rows into \`rerank\`: 1 rows \[00:00, 343.65 rows/s]
Inserted 1 row with 0 errors.
1 row inserted, 2 values computed.
```python theme={null}
# Add computed column to extract top results using JSON path
rerank_t.add_computed_column(top_results=rerank_t.reranked['results'])
```
Added 1 column value with 0 errors.
1 row updated, 1 value computed.
```python theme={null}
# Extract the top result's document and score
rerank_t.select(
rerank_t.query,
top_document=rerank_t.top_results[0]['document'],
top_score=rerank_t.top_results[0]['relevance_score'],
).collect()
```
```python theme={null}
# View reranking results
rerank_t.select(rerank_t.query, rerank_t.top_results).collect()
```
## Multimodal Embeddings
Voyage AI’s multimodal model (`voyage-multimodal-3`) can embed both
images and text into the same vector space, enabling cross-modal
similarity search.
```python theme={null}
# Create a table for multimodal embeddings
mm_t = pxt.create_table(
'voyageai_demo/multimodal',
{'image': pxt.Image, 'caption': pxt.String},
if_exists='replace',
)
# Add computed columns for image and text embeddings
# multimodal_embed can embed either images or text independently
mm_t.add_computed_column(
image_embedding=voyageai.multimodal_embed(
mm_t.image, model='voyage-multimodal-3.5', input_type='document'
)
)
mm_t.add_computed_column(
text_embedding=voyageai.multimodal_embed(
mm_t.caption, model='voyage-multimodal-3.5', input_type='document'
)
)
```
Created table 'multimodal'.
Added 0 column values with 0 errors.
Added 0 column values with 0 errors.
No rows affected.
```python theme={null}
# Insert a sample image with caption
mm_t.insert(
[
{
'image': 'https://raw.githubusercontent.com/pixeltable/pixeltable/main/docs/resources/images/000000000139.jpg',
'caption': 'A person standing next to an elephant',
}
]
)
```
Inserting rows into \`multimodal\`: 1 rows \[00:00, 520.00 rows/s]
Inserted 1 row with 0 errors.
1 row inserted, 5 values computed.
```python theme={null}
# View the multimodal embeddings
mm_t.select(
mm_t.image, mm_t.caption, mm_t.image_embedding, mm_t.text_embedding
).head()
```
### Learn more
To learn more about RAG operations in Pixeltable, check out the [RAG
Operations in
Pixeltable](/howto/use-cases/rag-operations)
tutorial.
For more information about Voyage AI models and features, visit:
* [Voyage AI Documentation](https://docs.voyageai.com/)
* [Text Embeddings](https://docs.voyageai.com/docs/embeddings)
* [Multimodal
Embeddings](https://docs.voyageai.com/docs/multimodal-embeddings)
* [Rerankers](https://docs.voyageai.com/docs/reranker)
If you have any questions, don’t hesitate to reach out.
Built with [Mintlify](https://mintlify.com). 