Hugging Face Embeddings with Weaviate

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

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

Requirements

Weaviate configuration

Your Weaviate instance must be configured with the Hugging Face vectorizer integration (text2vec-huggingface) module.

For Weaviate Cloud (WCD) users

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

For self-hosted users

• Check the cluster metadata to verify if the module is enabled.
• Follow the how-to configure modules guide to enable the module in Weaviate.

API credentials

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

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

• Set the HUGGINGFACE_APIKEY environment variable that is available to Weaviate.
• Provide the API key at runtime, as shown in the examples below.

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

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

# Recommended: save sensitive data as environment variables
huggingface_key = os.getenv("HUGGINGFACE_APIKEY")
headers = {
    "X-HuggingFace-Api-Key": huggingface_key,
}

client = weaviate.connect_to_weaviate_cloud(
    cluster_url=weaviate_url,                       # `weaviate_url`: your Weaviate URL
    auth_credentials=Auth.api_key(weaviate_key),      # `weaviate_key`: your Weaviate API key
    headers=headers
)

# Work with Weaviate

client.close()

import weaviate from 'weaviate-client'

const huggingFaceApiKey = process.env.HUGGINGFACE_APIKEY || '';  // Replace with your inference API key

const client = await weaviate.connectToWeaviateCloud(
  'WEAVIATE_INSTANCE_URL',  // Replace with your instance URL
  {
    authCredentials: new weaviate.ApiKey('WEAVIATE_INSTANCE_APIKEY'),
    headers: {
      'X-HuggingFace-Api-Key': huggingFaceApiKey,
    }
  }
)

// Work with Weaviate

client.close()

// Set these environment variables
// WEAVIATE_HOSTNAME            your Weaviate instance hostname, excluding the scheme (https://)
// WEAVIATE_API_KEY          your Weaviate instance API key
// <PROVIDER>_APIKEY       your model provider API key (or token)

package main

import (
    "context"
    "fmt"
    "os"

    "github.com/weaviate/weaviate-go-client/v5/weaviate"
    "github.com/weaviate/weaviate-go-client/v5/weaviate/auth"
)

func main() {
    cfg := weaviate.Config{
        Host:       os.Getenv("WEAVIATE_HOSTNAME"),
        Scheme:     "https",
        AuthConfig: auth.ApiKey{Value: os.Getenv("WEAVIATE_API_KEY")},
        Headers: map[string]string{
            "X-HuggingFace-Api-Key": os.Getenv("HUGGINGFACE_APIKEY"),
        },
    }

    client, err := weaviate.NewClient(cfg)
    if err != nil {
        fmt.Println(err)
    }

    // Work with Weaviate
}

Configure the vectorizer

Configure a Weaviate index as follows to use a Hugging Face embedding model:

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vector_config=[
        Configure.Vectors.text2vec_huggingface(
            name="title_vector",
            source_properties=["title"],
            model="sentence-transformers/all-MiniLM-L6-v2",
        )
    ],
    # Additional parameters not shown
)

await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectors.text2VecHuggingFace({
      name: 'title_vector',
      sourceProperties: ['title'],
      model: 'sentence-transformers/all-MiniLM-L6-v2',
    }),
  ],
  // Additional parameters not shown
});

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    basicHuggingfaceVectorizerDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-huggingface": map[string]interface{}{
                        "properties": []string{"title"},
                        "model":      "sentence-transformers/all-MiniLM-L6-v2",
                    },
                },
            },
        },
    }

    // add the collection
    err = client.Schema().ClassCreator().WithClass(basicHuggingfaceVectorizerDef).Do(ctx)
    if err != nil {
        panic(err)
    }
}

You must specify one of the available models for the vectorizer to use.

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

The following examples show how to configure Hugging Face-specific options.

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    "DemoCollection",
    vector_config=[
        Configure.Vectors.text2vec_huggingface(
            name="title_vector",
            source_properties=["title"],
            # NOTE: Use only one of (`model`), (`passage_model` and `query_model`), or (`endpoint_url`)
            model="sentence-transformers/all-MiniLM-L6-v2",
            # passage_model="sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base",    # Required if using `query_model`
            # query_model="sentence-transformers/facebook-dpr-question_encoder-single-nq-base", # Required if using `passage_model`
            # endpoint_url="<custom_huggingface_url>",
            #
            # wait_for_model=True,
            # use_cache=True,
            # use_gpu=True,
        )
    ],
    # Additional parameters not shown
)

await client.collections.create({
  name: 'DemoCollection',
  properties: [
    {
      name: 'title',
      dataType: 'text' as const,
    },
  ],
  vectorizers: [
    weaviate.configure.vectors.text2VecHuggingFace({
      name: 'title_vector',
      sourceProperties: ['title'],
      model: 'sentence-transformers/all-MiniLM-L6-v2',
      // endpointURL: <custom_huggingface_url>,
      // passageModel: 'sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base',    // Required if using `query_model`
      // queryModel: 'sentence-transformers/facebook-dpr-question_encoder-single-nq-base', // Required if using `passage_model`
      // waitForModel: true,
      // useCache: true,
      // useGPU: true,
    }),
  ],
  // Additional parameters not shown
});

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    // Define the collection
    fullHuggingfaceVectorizerDef := &models.Class{
        Class: "DemoCollection",
        VectorConfig: map[string]models.VectorConfig{
            "title_vector": {
                Vectorizer: map[string]interface{}{
                    "text2vec-huggingface": map[string]interface{}{
                        "properties": []string{"title"},
                        //  Note: Use only one of (`model`), (`passage_model` and `query_model`), or (`endpoint_url`)
                        "model": "sentence-transformers/all-MiniLM-L6-v2",
                        // "passage_model":  "sentence-transformers/facebook-dpr-ctx_encoder-single-nq-base",      // Required if using `query_model`
                        // "query_model":    "sentence-transformers/facebook-dpr-question_encoder-single-nq-base", // Required if using `passage_model`
                        // "endpoint_url":   "<custom_huggingface_url>",
                        // // Optional parameters
                        // "wait_for_model": true,
                        // "use_cache":      true,
                        // "use_gpu":        true,
                    },
                },
            },
        },
    }

    // add the collection
    err = client.Schema().ClassCreator().WithClass(fullHuggingfaceVectorizerDef).Do(ctx)
    if err != nil {
        panic(err)
    }
}

Model selection parameters

Only select one of the following parameters to specify the model:

• model,
• passageModel and queryModel, or
• endpointURL

Differences between model, passageModel/queryModel and endpointURL

The passageModel and queryModel parameters are used together to specify a DPR passage and query model.

The endpointURL parameter is used to specify a custom Hugging Face Inference Endpoint. This parameter overrides the model, passageModel, and queryModel parameters.

Additional parameters

• options.waitForModel: If the model is not ready, wait for it rather than returning a 503 error.
• options.useGPU: Use a GPU for inference if your account plan supports it.
• options.useCache: Use a cached result if available. (For non-deterministic models to prevent the caching mechanism from being used.)

Data import

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

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

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.")
            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]}")

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." }
];

const collectionName = 'DemoCollection'
const myCollection = client.collections.use(collectionName)

let dataObjects = new Array();

for (let srcObject of srcObjects) {
  dataObjects.push({
    title: srcObject.title,
    description: srcObject.description,
  });
}

const response = await myCollection.data.insertMany(dataObjects);

console.log(response);

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    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.Object
    objects := []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 items
    batcher := client.Batch().ObjectsBatcher()
    for _, dataObj := range objects {
        batcher.WithObjects(&models.Object{
            Class:      "DemoCollection",
            Properties: dataObj,
        })
    }

    // Flush
    batchRes, err := batcher.Do(ctx)

    // Error handling
    if 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)
                }
            }
        }
    }
}

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 Hugging Face model.

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.

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

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"])

const collectionName = 'DemoCollection'
const myCollection = client.collections.use(collectionName)

let result;

result = await myCollection.query.nearText(
  'A holiday film',  // The model provider integration will automatically vectorize the query
  {
    limit: 2,
  }
)

console.log(JSON.stringify(result.objects, null, 2));

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    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)
}

Hybrid search

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.

PythonJavaScript/TypeScriptGo

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

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"])

const collectionName = 'DemoCollection'
const myCollection = client.collections.use(collectionName)

result = await myCollection.query.hybrid(
  'A holiday film',  // The model provider integration will automatically vectorize the query
  {
    limit: 2,
  }
)

console.log(JSON.stringify(result.objects, null, 2));

// package, imports not shown

func main() {
    // Instantiation not shown

    ctx := context.Background()

    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

Available models

You can use any Hugging Face embedding model with text2vec-huggingface, including public and private Hugging Face models. Sentence similarity models generally work best.

Further resources

• Hugging Face integrations (locally hosted)

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 collections and How-to: Manage objects guides show how to perform data operations (i.e. create, read, update, delete collections and objects within them).
• The How-to: Query & Search guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation.

External resources

• Hugging Face Inference API documentation
• Hugging Face Model Hub

Questions and feedback

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

Technical questions

If you have questions feel free to post on our Community forum.

Documentation feedback

Leave feedback by opening a GitHub issue.