Skip to main content
Weaviate Docs (migrated from docs.weaviate.io) Docs

Search documentation

Type to search this documentation.

On this pageOverview

Text Embeddings

Weaviate's integration with OpenAI's APIs allows you to access their models' capabilities directly from Weaviate.

Configure a Weaviate vector index to use an OpenAI embedding model, and Weaviate will generate embeddings for various operations using the specified model and your OpenAI 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

Section titled “Requirements”

Weaviate configuration

Section titled “Weaviate configuration”

Your Weaviate instance must be configured with the OpenAI vectorizer integration (text2vec-openai) module.

For Weaviate Cloud (WCD) users

This integration is enabled by default on Weaviate Cloud (WCD) instances.

For self-hosted users

API credentials

Section titled “API credentials”

You must provide a valid OpenAI API key to Weaviate for this integration. Go to OpenAI to sign up and obtain an API key.

Provide the API key to Weaviate using one of the following methods:

  • Set the OPENAI_APIKEY environment variable that is available to Weaviate.
  • Provide the API key at runtime, as shown in the examples below.
Python
# Recommended: save sensitive data as environment variables
openai_key = os.getenv("OPENAI_API_KEY")
JavaScript/TypeScript
const openaiApiKey = process.env.OPENAI_API_KEY || '';  // Replace with your inference API key
Go
"X-OpenAI-Api-Key": os.Getenv("OPENAI_API_KEY"),

Configure the vectorizer

Section titled “Configure the vectorizer”

Configure a Weaviate index as follows to use an OpenAI embedding model:

Python
from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    vector_config=[        Configure.Vectors.text2vec_openai(            name="title_vector",            source_properties=["title"]        )    ],    # Additional parameters not shown)
JavaScript/TypeScript
await client.collections.create({  name: 'DemoCollection',  properties: [    {      name: 'title',      dataType: 'text' as const,    },  ],  vectorizers: [    weaviate.configure.vectors.text2VecOpenAI({      name: 'title_vector',      sourceProperties: ['title'],    },    ),  ],  // Additional parameters not shown});
Go
// Define the collectionbasicOpenAIVectorizerDef := &models.Class{  Class: "DemoCollection",  VectorConfig: map[string]models.VectorConfig{    "title_vector": {      Vectorizer: map[string]interface{}{        "text2vec-openai": map[string]interface{}{          "properties": []string{"title"},        },      },    },  },}// add the collectionerr = client.Schema().ClassCreator().WithClass(basicOpenAIVectorizerDef).Do(ctx)if err != nil {  panic(err)}

Select a model

Section titled “Select a model”

You can specify one of the available models for the vectorizer to use, as shown in the following configuration examples. If you do not set a model, Weaviate uses the server default, text-embedding-3-small.

For text-embedding-3 model family

Section titled “For text-embedding-3 model family”

For v3 models such as text-embedding-3-large, provide the model name and optionally the dimensions (e.g. 1024).

Python
from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    vector_config=[        Configure.Vectors.text2vec_openai(            name="title_vector",            source_properties=["title"],            # If using `text-embedding-3` model family            model="text-embedding-3-large",            dimensions=1024        )    ],    # Additional parameters not shown)
JavaScript/TypeScript
await client.collections.create({  name: 'DemoCollection',  properties: [    {      name: 'title',      dataType: 'text' as const,    },  ],  vectorizers: [    weaviate.configure.vectors.text2VecOpenAI({      name: 'title_vector',      sourceProperties: ['title'],      model: 'text-embedding-3-large',      dimensions: 1024    },    ),  ],  // Additional parameters not shown});
Go
// Define the collectionopenAIVectorizerWithModelDef := &models.Class{  Class: "DemoCollection",  VectorConfig: map[string]models.VectorConfig{    "title_vector": {      Vectorizer: map[string]interface{}{        "text2vec-openai": map[string]interface{}{          "properties": []string{"title"},          "model":      "text-embedding-3-large",          "dimensions": 1024, // Optional (e.g. 1024, 512, 256)        },      },    },  },}// add the collectionerr = client.Schema().ClassCreator().WithClass(openAIVectorizerWithModelDef).Do(ctx)if err != nil {  panic(err)}

For older model families (e.g. ada)

Section titled “For older model families (e.g. ada)”

For older models such as text-embedding-ada-002, provide the model name (ada), the type (text) and the model version (002).

Python
from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    vector_config=[        Configure.Vectors.text2vec_openai(            name="title_vector",            source_properties=["title"],            # If using older model family e.g. `ada`            model="ada",            model_version="002",            type_="text"        )    ],    # Additional parameters not shown)
JavaScript/TypeScript
await client.collections.create({  name: 'DemoCollection',  properties: [    {      name: 'title',      dataType: 'text' as const,    },  ],  vectorizers: [    weaviate.configure.vectors.text2VecOpenAI({      name: 'title_vector',      sourceProperties: ['title'],      model: 'ada',      modelVersion: '002',      type: 'text'    },    ),  ],  // Additional parameters not shown});
Go
// Define the collectionopenAIVectorizerWithLegacyModelDef := &models.Class{  Class: "DemoCollection",  VectorConfig: map[string]models.VectorConfig{    "title_vector": {      Vectorizer: map[string]interface{}{        "text2vec-openai": map[string]interface{}{          "properties":    []string{"title"},          "model":         "ada",          "model_version": "002",          "type":          "text",        },      },    },  },}// add the collectionerr = client.Schema().ClassCreator().WithClass(openAIVectorizerWithLegacyModelDef).Do(ctx)if err != nil {  panic(err)}

You can specify one of the available models for Weaviate to use. If no model is specified, Weaviate uses text-embedding-3-small.

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

Section titled “Vectorizer parameters”
  • model: The OpenAI model name or family. Defaults to text-embedding-3-small.
  • dimensions: The number of dimensions for the model.
  • modelVersion: The version string for the model.
  • type: The model type, either text or code.
  • baseURL: The URL to use (e.g. a proxy) instead of the default OpenAI URL.
  • endpoint: The API path that Weaviate appends to the base URL. Defaults to /v1/embeddings. Set it if an OpenAI-compatible service uses a different path.

For how Weaviate combines baseURL and endpoint into a request URL, see Header parameters.

(model & dimensions) or (model & modelVersion)

Section titled “(model & dimensions) or (model & modelVersion)”

For v3 models such as text-embedding-3-large, provide the model name and optionally the dimensions (e.g. 1024).

For older models such as text-embedding-ada-002, provide the model name (ada), the type (text) and the model version (002).

Example configuration

Section titled “Example configuration”

The following examples show how to configure OpenAI-specific options.

Python
from weaviate.classes.config import Configureclient.collections.create(    "DemoCollection",    vector_config=[        Configure.Vectors.text2vec_openai(            name="title_vector",            source_properties=["title"],            # # Further options            # model="text-embedding-3-large",            # model_version="002",  # Parameter only applicable for `ada` model family and older            # dimensions=1024,      # Parameter only applicable for `v3` model family and newer            # type_="text",            # base_url="<custom_openai_url>",        )    ],    # Additional parameters not shown)
JavaScript/TypeScript
await client.collections.create({  name: 'DemoCollection',  properties: [    {      name: 'title',      dataType: 'text' as const,    },  ],  vectorizers: [    weaviate.configure.vectors.text2VecOpenAI(      {        name: 'title_vector',        sourceProperties: ['title'],        // Further options        model: 'text-embedding-3-large',        // modelVersion: "002",   // Parameter only applicable for `ada` model family and older        // dimensions: 1024,    // Parameter only applicable for `v3` model family and newer        // type: 'text',        // baseURL: '<custom_openai_url>',      },    ),  ],  // Additional parameters not shown});
Go
// Define the collectionopenAIVectorizerFullDef := &models.Class{  Class: "DemoCollection",  VectorConfig: map[string]models.VectorConfig{    "title_vector": {      Vectorizer: map[string]interface{}{        "text2vec-openai": map[string]interface{}{          "properties":    []string{"title"},          "model":         "text-embedding-3-large",          "dimensions":    1024,   // Parameter only applicable for `v3` model family and newer          "model_version": "002",  // Parameter only applicable for `ada` model family and older          "type":          "text", // Parameter only applicable for `ada` model family and older          "base_url":      "<custom_openai_url>",        },      },    },  },}// add the collectionerr = client.Schema().ClassCreator().WithClass(openAIVectorizerFullDef).Do(ctx)if err != nil {  panic(err)}

For further details on model parameters, see the OpenAI API documentation.

Header parameters

Section titled “Header parameters”

You can provide the API key as well as some optional parameters at runtime through additional headers in the request. The following headers are available:

  • X-OpenAI-Api-Key: The OpenAI API key.
  • X-OpenAI-Baseurl: The base URL to use (e.g. a proxy) instead of the default OpenAI URL.
  • X-OpenAI-Organization: The OpenAI organization ID.

Any additional headers provided at runtime will override the existing Weaviate configuration.

Provide the headers as shown in the API credentials examples above.

Data import

Section titled “Data import”

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

Python
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.use("DemoCollection")with collection.batch.fixed_size(batch_size=200) 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.")            breakfailed_objects = collection.batch.failed_objectsif failed_objects:    print(f"Number of failed imports: {len(failed_objects)}")    print(f"First failed object: {failed_objects[0]}")
JavaScript/TypeScript
let srcObjects = [
  { 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." }
];
Go
var sourceObjects = []map[string]string{  {"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."},}// Convert items into a slice of models.Objectobjects := []models.PropertySchema{}for i := range sourceObjects {  objects = append(objects, map[string]interface{}{    // Populate the object with the data    "title":       sourceObjects[i]["title"],    "description": sourceObjects[i]["description"],  })}// Batch write itemsbatcher := client.Batch().ObjectsBatcher()for _, dataObj := range objects {  batcher.WithObjects(&models.Object{    Class:      "DemoCollection",    Properties: dataObj,  })}// FlushbatchRes, err := batcher.Do(ctx)// Error handlingif err != nil {  panic(err)}for _, res := range batchRes {  if res.Result.Errors != nil {    for _, err := range res.Result.Errors.Error {      if err != nil {        fmt.Printf("Error details: %v\n", *err)        panic(err.Message)      }    }  }}

Searches

Section titled “Searches”

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

Embedding integration at search illustration

Vector (near text) search

Section titled “Vector (near text) search”

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.

Python
collection = client.collections.use("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"])
JavaScript/TypeScript
const collectionName = 'DemoCollection'
const myCollection = client.collections.use(collectionName)
Go
nearTextResponse, err := client.GraphQL().Get().  WithClassName("DemoCollection").  WithFields(    graphql.Field{Name: "title"},  ).  WithNearText(client.GraphQL().NearTextArgBuilder().    WithConcepts([]string{"A holiday film"})).  WithLimit(2).  Do(ctx)if err != nil {  panic(err)}fmt.Printf("%v", nearTextResponse)
Section titled “Hybrid search”

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.

Python
collection = client.collections.use("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"])
JavaScript/TypeScript
const collectionName = 'DemoCollection'
const myCollection = client.collections.use(collectionName)
Go
hybridResponse, err := client.GraphQL().Get().  WithClassName("DemoCollection").  WithFields(    graphql.Field{Name: "title"},  ).  WithHybrid(client.GraphQL().HybridArgumentBuilder().    WithQuery("A holiday film")).  WithLimit(2).  Do(ctx)if err != nil {  panic(err)}fmt.Printf("%v", hybridResponse)

References

Section titled “References”

Available models

Section titled “Available models”

The server default is text-embedding-3-small.

For document embeddings, choose from the following embedding model families:

  • text-embedding-3
    • Available dimensions values:
      • text-embedding-3-large: 256, 1024, 3072 (default)
      • text-embedding-3-small: 512, 1536 (default)
  • ada
  • babbage
  • davinci
Deprecated models

The following models are available, but deprecated:

  • Codex
  • babbage-001
  • davinci-001
  • curie

Source

Further resources

Section titled “Further resources”

Other integrations

Section titled “Other integrations”

Code examples

Section titled “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:

External resources

Section titled “External resources”

Questions and feedback

Section titled “Questions and feedback”

Have a question or feedback? Here's how to reach us.

Community Forum

Ask questions and connect with other developers on our Community forum.

Support

Weaviate Cloud user or customer? Find the right channel on the Support page.

Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu