Embeddings

​

Before implementing embeddings

When selecting an embeddings provider, there are several factors you can consider depending on your needs and preferences:

• 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
• Inference performance: embedding lookup speed and end-to-end latency. This is a particularly important consideration for large scale production deployments
• Customization: options for continued training on private data, or specialization of models for very specific domains. This can improve performance on unique vocabularies

​

How to get embeddings with Anthropic

Anthropic does not offer its own embedding model. One embeddings provider that has a wide variety of options and capabilities encompassing all of the above considerations is Voyage AI.

Voyage AI makes state-of-the-art embedding models and offers customized models for specific industry domains such as finance and healthcare, or bespoke fine-tuned models for individual customers.

The rest of this guide is for Voyage AI, but we encourage you to assess a variety of embeddings vendors to find the best fit for your specific use case.

​

Getting started with Voyage AI

To access Voyage embeddings:

1. Sign up on Voyage AI’s website
2. Obtain an API key
3. Set the API key as an environment variable for convenience:

export VOYAGE_API_KEY="<your secret key>"

You can run the embeddings by either using the official voyageai Python package or HTTP requests, as described below.

​

Voyage Python package

The voyageai package can be installed using the following command:

pip install -U voyageai

Then, you can create a client object and start using it to embed your texts:

import voyageai

vo = voyageai.Client()
# This will automatically use the environment variable VOYAGE_API_KEY.
# Alternatively, you can use vo = voyageai.Client(api_key="<your secret key>")

texts = ["Sample text 1", "Sample text 2"]

result = vo.embed(texts, model="voyage-2", input_type="document")
print(result.embeddings[0])
print(result.embeddings[1])

result.embeddings will be a list of two embedding vectors, each containing 1024 floating-point numbers.

After running the above code, the two embeddings will be printed on the screen:

[0.02012746, 0.01957859, ...]  # embedding for "Sample text 1"
[0.01429677, 0.03077182, ...]  # embedding for "Sample text 2"

When creating the embeddings, you may specify a few other arguments to the embed() function. Here is the specification:

voyageai.Client.embed(texts : List[str], model : str, input_type : Optional[str] = None, truncation : Optional[bool] = None)

• texts (List[str]) - A list of texts as a list of strings, such as ["I like cats", "I also like dogs"]. Currently, the maximum length of the list is 128, and total number of tokens in the list is at most 320K for voyage-2 and 120K for voyage-large-2/voyage-code-2.
• model (str) - Name of the model. Recommended options: voyage-2, voyage-large-2, voyage-code-2.
• input_type (str, optional, defaults to None) - Type of the input text. Defaults to None. Other options: query, document
  • When the input_type is set to None, the input text will be directly encoded by Voyage’s embedding model. Alternatively, when the inputs are documents or queries, the users can specify input_type to be query or document, respectively. In such cases, Voyage will prepend a special prompt to input text and send the extended inputs to the embedding model
  • For retrieval/search use cases, we recommend specifying this argument when encoding queries or documents to enhance retrieval quality. Embeddings generated with and without the input_type argument are compatible
• truncation (bool, optional, defaults to None) - Whether to truncate the input texts to fit within the context length.
  • If True, over-length input texts will be truncated to fit within the context length, before being vectorized by the embedding model
  • If False, an error will be raised if any given text exceeds the context length
  • If not specified (defaults to None), Voyage will truncate the input text before sending it to the embedding model if it slightly exceeds the context window length. If it significantly exceeds the context window length, an error will be raised

​

Voyage HTTP API

You can also get embeddings by requesting the Voyage HTTP API. For example, you can send an HTTP request through the curl command in a terminal:

curl https://api.voyageai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VOYAGE_API_KEY" \
  -d '{
    "input": ["Sample text 1", "Sample text 2"],
    "model": "voyage-2"
  }'

The response you would get is a JSON object containing the embeddings and the token usage:

{
  "object": "list",
  "data": [
    {
      "embedding": [0.02012746, 0.01957859, ...],
      "index": 0
    },
    {
      "embedding": [0.01429677, 0.03077182, ...],
      "index": 1
    }
  ],
  "model": "voyage-2",
  "usage": {
    "total_tokens": 10
  }
}

Voyage AI’s embedding endpoint is https://api.voyageai.com/v1/embeddings (POST). The request header must contain the API key. The request body is a JSON object containing the following arguments:

• input (str, List[str]) - A single text string, or a list of texts as a list of strings. Currently, the maximum length of the list is 128, and total number of tokens in the list is at most 320K for voyage-2 and 120K for voyage-large-2/voyage-code-2.
• model (str) - Name of the model. Recommended options: voyage-2, voyage-large-2, voyage-code-2.
• input_type (str, optional, defaults to None) - Type of the input text. Defaults to None. Other options: query, document
• truncation (bool, optional, defaults to None) - Whether to truncate the input texts to fit within the context length
  • If True, over-length input texts will be truncated to fit within the context length before being vectorized by the embedding model
  • If False, an error will be raised if any given text exceeds the context length
  • If not specified (defaults to None), Voyage will truncate the input text before sending it to the embedding model if it slightly exceeds the context window length. If it significantly exceeds the context window length, an error will be raised
• encoding_format (str, optional, default to None) - Format in which the embeddings are encoded. Voyage currently supports two options:
  • If not specified (defaults to None): the embeddings are represented as lists of floating-point numbers
  • "base64": the embeddings are compressed to Base64 encodings

​

Voyage embedding example

Now that we know how to get embeddings with Voyage, let’s see it in action with a brief example.

Suppose we have a small corpus of six documents to retrieve from

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 and business updates is scheduled for Thursday, November 2, 2023 at 2:00 p.m. PT / 5:00 p.m. ET.",
    "Shakespeare's works, like 'Hamlet' and 'A Midsummer Night's Dream,' endure in literature."
]

We will first use Voyage to convert each of them into an embedding vector

import voyageai

vo = voyageai.Client()

# Embed the documents
doc_embds = vo.embed(
    documents, model="voyage-2", input_type="document"
).embeddings

The embeddings will allow us to do semantic search / retrieval in the vector space. We can then convert an example query,

query = "When is Apple's conference call scheduled?"

into an embedding, and then conduct a nearest neighbor search to find the most relevant document based on the distance in the embedding space.

import numpy as np

# Embed the query
query_embd = vo.embed(
    [query], model="voyage-2", input_type="query"
).embeddings[0]

# Compute the similarity
# Voyage embeddings are normalized to length 1, therefore dot-product
# and cosine similarity are the same.
similarities = np.dot(doc_embds, query_embd)

retrieved_id = np.argmax(similarities)
print(documents[retrieved_id])

Note that we use input_type="document" and input_type="query" for embedding the document and query, respectively. More specification can be found here.

The output would be the 5th document, which is indeed the most relevant to the query:

Apple’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.

​

Available Voyage models

Voyage recommends using the following embedding models:

voyage-2 and voyage-large-2 are generalist embedding models, which achieve state-of-the-art performance across domains and retain high efficiency. voyage-code-2 is optimized for the code field, offering 4x the context length for more flexible usage, albeit at a relatively higher latency.

Voyage is actively developing more advanced and specialized models, and also offers fine-tuning services to customize bespoke models for individual customers. Email your Anthropic account manager or reach out to Anthropic support for further information on bespoke models.

• voyage-finance-2: coming soon
• voyage-law-2: coming soon
• voyage-multilingual-2: coming soon
• voyage-healthcare-2: coming soon

​

Voyage on the AWS Marketplace

Voyage embeddings are also available on AWS Marketplace. Here are the instructions for accessing Voyage on AWS:

1. Subscribe to the model package
   1. Navigate to the model package listing page and select the model to deploy
   2. Click on the Continue to subscribe button
   3. Carefully review the details on the Subscribe to this software page. If you agree with the standard End-User License Agreement (EULA), pricing, and support terms, click on “Accept Offer”
   4. After selecting Continue to configuration and choosing a region, you will be presented with a Product Arn. This is the model package ARN required for creating a deployable model using Boto3
      1. Copy the ARN that corresponds to your selected region and use it in the subsequent cell
2. Deploy the model package

From here, create a JupyterLab space in Sagemaker Studio, upload Voyage’s notebook, and follow the instructions within.

​

FAQ

import numpy as np

similarity = np.dot(embd1, embd2)
# Voyage embeddings are normalized to length 1, therefore cosine similarity
# is the same as dot-product.

import voyageai

vo = voyageai.Client()
total_tokens = vo.count_tokens(["Sample text"])

​

Pricing

Visit Voyage’s pricing page for the most up to date pricing details.