Skip to main content

Text Embeddings

Added in 1.27.10, 1.28.3, 1.29.0

Weaviate Embeddings

Weaviate Embeddings' models can be accessed directly from a Weaviate Cloud instance.

Configure a Weaviate vector index to use a Weaviate Embeddings model, and Weaviate will generate embeddings for various operations using the specified model and your Weaviate API key. This feature is called the vectorizer.

At import time, Weaviate generates text object embeddings and saves them into the index. For vector and hybrid search operations, Weaviate converts text queries into embeddings.

Embedding integration illustration

Requirements

To use Weaviate Embeddings, you need:

  • A Weaviate Cloud instance running at least Weaviate version >=1.27.10, >=1.28.3 or >=1.29.0.
  • A Weaviate client library that supports Weaviate Embeddings:
    • Python client version 4.9.5 or higher
    • JavaScript/TypeScript client version 3.2.5 or higher
    • Go/Java clients are not yet officially supported; you must pass the X-Weaviate-Api-Key and X-Weaviate-Cluster-Url headers manually upon instantiation as shown below.

Weaviate configuration

The Weaviate Embeddings vectorizer is only available for use by Weaviate Cloud instances. At this time, Weaviate Embeddings is not available for self-hosted users.

API credentials

Weaviate Embeddings is integrated with Weaviate Cloud. Your Weaviate Cloud credentials will be used to authorize your Weaviate Cloud instance's access for Weaviate Embeddings.

import weaviate
from weaviate.classes.init import Auth
import os

# Best practice: store your credentials in environment variables
weaviate_url = os.getenv("WEAVIATE_URL")
weaviate_key = os.getenv("WEAVIATE_API_KEY")

client = weaviate.connect_to_weaviate_cloud(
cluster_url=weaviate_url, # Weaviate URL: "REST Endpoint" in Weaviate Cloud console
auth_credentials=Auth.api_key(weaviate_key), # Weaviate API key: "ADMIN" API key in Weaviate Cloud console
)

print(client.is_ready()) # Should print: `True`

# Work with Weaviate

client.close()

Configure the vectorizer

Configure a Weaviate index as follows to use a Weaviate Embeddings model:

from weaviate.classes.config import Configure

client.collections.create(
"DemoCollection",
vectorizer_config=[
Configure.NamedVectors.text2vec_weaviate(
name="title_vector",
source_properties=["title"]
)
],
# Additional parameters not shown
)

Select a model

You can specify one of the available models for the vectorizer to use, as shown in the following configuration example.

from weaviate.classes.config import Configure

client.collections.create(
"DemoCollection",
vectorizer_config=[
Configure.NamedVectors.text2vec_weaviate(
name="title_vector",
source_properties=["title"],
model="Snowflake/snowflake-arctic-embed-l-v2.0"
)
],
# Additional parameters not shown
)

You can specify one of the available models for Weaviate to use. The default model is used if no model is specified.

Vectorization behavior

Weaviate follows the collection configuration and a set of predetermined rules to vectorize objects.


Unless specified otherwise in the collection definition, the default behavior is to:


  • Only vectorize properties that use the text or text[] data type (unless skipped)
  • Sort properties in alphabetical (a-z) order before concatenating values
  • If vectorizePropertyName is true (false by default) prepend the property name to each property value
  • Join the (prepended) property values with spaces
  • Prepend the class name (unless vectorizeClassName is false)
  • Convert the produced string to lowercase

Vectorizer parameters

  • model (optional): The name of the model to use for embedding generation.
  • dimensions (optional): The number of dimensions to use for the generated embeddings.
  • base_url (optional): The base URL for the Weaviate Embeddings service. (Not required in most cases.)

The following examples show how to configure Weaviate Embeddings-specific options.

from weaviate.classes.config import Configure

client.collections.create(
"DemoCollection",
vectorizer_config=[
Configure.NamedVectors.text2vec_weaviate(
name="title_vector",
source_properties=["title"],
model="Snowflake/snowflake-arctic-embed-m-v1.5",
# Further options
# dimensions=256
# base_url="<custom_weaviate_embeddings_url>",
)
],
# Additional parameters not shown
)

Data import

After configuring the vectorizer, import data into Weaviate. Weaviate generates embeddings for text objects using the specified model.

source_objects = [
{"title": "The Shawshank Redemption", "description": "A wrongfully imprisoned man forms an inspiring friendship while finding hope and redemption in the darkest of places."},
{"title": "The Godfather", "description": "A powerful mafia family struggles to balance loyalty, power, and betrayal in this iconic crime saga."},
{"title": "The Dark Knight", "description": "Batman faces his greatest challenge as he battles the chaos unleashed by the Joker in Gotham City."},
{"title": "Jingle All the Way", "description": "A desperate father goes to hilarious lengths to secure the season's hottest toy for his son on Christmas Eve."},
{"title": "A Christmas Carol", "description": "A miserly old man is transformed after being visited by three ghosts on Christmas Eve in this timeless tale of redemption."}
]

collection = client.collections.get("DemoCollection")

with collection.batch.dynamic() as batch:
for src_obj in source_objects:
# The model provider integration will automatically vectorize the object
batch.add_object(
properties={
"title": src_obj["title"],
"description": src_obj["description"],
},
# vector=vector # Optionally provide a pre-obtained vector
)
if batch.number_errors > 10:
print("Batch import stopped due to excessive errors.")
break

failed_objects = collection.batch.failed_objects
if failed_objects:
print(f"Number of failed imports: {len(failed_objects)}")
print(f"First failed object: {failed_objects[0]}")
Re-use existing vectors

If you already have a compatible model vector available, you can provide it directly to Weaviate. This can be useful if you have already generated embeddings using the same model and want to use them in Weaviate, such as when migrating data from another system.

Searches

Once the vectorizer is configured, Weaviate will perform vector and hybrid search operations using the specified WED model.

Embedding integration at search illustration

When you perform a vector search, Weaviate converts the text query into an embedding using the specified model and returns the most similar objects from the database.

The query below returns the n most similar objects from the database, set by limit.

collection = client.collections.get("DemoCollection")

response = collection.query.near_text(
query="A holiday film", # The model provider integration will automatically vectorize the query
limit=2
)

for obj in response.objects:
print(obj.properties["title"])
What is a hybrid search?

A hybrid search performs a vector search and a keyword (BM25) search, before combining the results to return the best matching objects from the database.

When you perform a hybrid search, Weaviate converts the text query into an embedding using the specified model and returns the best scoring objects from the database.

The query below returns the n best scoring objects from the database, set by limit.

collection = client.collections.get("DemoCollection")

response = collection.query.hybrid(
query="A holiday film", # The model provider integration will automatically vectorize the query
limit=2
)

for obj in response.objects:
print(obj.properties["title"])

References

Available models

Snowflake/snowflake-arctic-embed-l-v2.0 (default)

  • A 568M parameter, 1024-dimensional model for multilingual enterprise retrieval tasks.
  • Trained with Matryoshka Representation Learning to allow vector truncation with minimal loss.
  • Quantization-friendly: Using scalar quantization and 256 dimensions provides 99% of unquantized, full-precision performance.
  • Read more at the Snowflake blog, and the Hugging Face model card
  • Allowable dimensions: 1024 (default), 256

Snowflake/snowflake-arctic-embed-m-v1.5

  • A 109M parameter, 768-dimensional model for enterprise retrieval tasks in English.
  • Trained with Matryoshka Representation Learning to allow vector truncation with minimal loss.
  • Quantization-friendly: Using scalar quantization and 256 dimensions provides 99% of unquantized, full-precision performance.
  • Read more at the Snowflake blog, and the Hugging Face model card
  • Allowable dimensions: 768 (default), 256
Input truncation

Currently, input exceeding the model's context windows is truncated from the right (i.e. the end of the input).

Further resources

Code examples

Once the integrations are configured at the collection, the data management and search operations in Weaviate work identically to any other collection. See the following model-agnostic examples:

  • The how-to: manage data guides show how to perform data operations (i.e. create, update, delete).
  • The how-to: search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

References

Questions and feedback

If you have any questions or feedback, let us know in the user forum.