This will automatically use the environment variable VOYAGE_API_KEY. changedbuild-with-claude/embeddings
Nearest release: v2.1.307, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+8added
Lines−8removed
From line
1
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits5to this page, all time
The whole hunk
from line 1, old and new numbered
/
from line 1
11---
22title: Embeddings
33url: https://platform.claude.com/docs/en/build-with-claude/embeddings
4description: Text embeddings are numerical representations of text that enable measuring semantic similarity. This guide introduces embeddings, their applications, and how to use embedding models for tasks like search, recommendations, and anomaly detection.
4description: Text embeddings are numerical representations of text that let you measure semantic similarity. This guide introduces embeddings, their applications, and how to use embedding models for tasks such as search, recommendations, and anomaly detection.
55---
66
77## Before implementing embeddings
from line 8
88
99When selecting an embeddings provider, there are several factors you can consider depending on your needs and preferences:
1010
11* Dataset size & domain specificity: size of the model training dataset and its relevance to the domain you want to embed. Larger or more domain-specific data generally produces better in-domain embeddings
12* Inference performance: embedding lookup speed and end-to-end latency. This is a particularly important consideration for large scale production deployments
11* Dataset size and domain specificity: size of the model training dataset and its relevance to the domain you want to embed. Larger or more domain-specific data generally produces better in-domain embeddings
12* Inference performance: embedding lookup speed and end-to-end latency. This is a particularly important consideration for large-scale production deployments
1313* Customization: options for continued training on private data, or specialization of models for very specific domains. This can improve performance on unique vocabularies
1414
1515## How to get embeddings with Anthropic
from line 140
140140 }'
141141```
142142
143The response you would get is a JSON object containing the embeddings and the token usage:
143The response is a JSON object containing the embeddings and the token usage:
144144
145145```json
146146{
from line 176
176176
177177The following brief example shows how to use embeddings.
178178
179Suppose you have a small corpus of six documents to retrieve from
179Suppose you have a small corpus of six documents to retrieve from:
180180
181181```python
182182documents = [
from line 200
200200doc_embds = vo.embed(documents, model="voyage-4", input_type="document").embeddings
201201```
202202
203The embeddings allow you to do semantic search / retrieval in the vector space. Given an example query,
203The embeddings allow you to do semantic search / retrieval in the vector space. Consider the following example query:
204204
205205```python
206206query = "When is Apple's conference call scheduled?"
from line 231
231231Apple's conference call to discuss fourth fiscal quarter results and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.
232232```
233233
234If you are looking for a detailed set of recipes on how to do RAG with embeddings, including vector databases, check out the [RAG recipe](https://platform.claude.com/cookbook/third-party-pinecone-rag-using-pinecone).
234If you are looking for a detailed set of recipes on how to do RAG with embeddings, including vector databases, see the [RAG recipe](https://platform.claude.com/cookbook/third-party-pinecone-rag-using-pinecone).
235235
236236## FAQ
237237
from line 272
272272
273273 Voyage AI embeddings are normalized to length 1, which means that:
274274
275 * Cosine similarity is equivalent to dot-product similarity, while the latter can be computed more quickly.
275 * Cosine similarity is equivalent to dot-product similarity, although the latter can be computed more quickly.
276276 * Cosine similarity and Euclidean distance result in identical rankings.
277277 </Accordion>
278278
No line in this hunk matches that.