Generative and reranker models

Embedding models / Vectorizers

Visit the Vectorizer and vector config guide to find out how to configure an embedding model for your collection or to fine-tune the vector index settings.

Specify a reranker model integration

Configure a reranker model integration for reranking retrieved results.

Related pages

• Available reranker model integrations

Python Client v4

from weaviate.classes.config import Configure, Property, DataType

client.collections.create(
    "Article",
    vectorizer_config=Configure.Vectorizer.text2vec_openai(),
    reranker_config=Configure.Reranker.cohere()
)

  API docs

Python Client v3

class_obj = {
    "class": "Article",
    "vectorizer": "text2vec-openai",  # set your vectorizer module
    "moduleConfig": {
        "reranker-cohere": {}  # set your reranker module
    }
}

client.schema.create_class(class_obj)

  API docs  Deprecated (v3)

JS/TS Client v3

import { vectorizer, reranker } from 'weaviate-client';

await client.collections.create({
  name: 'Article',
  vectorizers: vectorizer.text2VecOpenAI(),
  reranker: reranker.cohere(),
})

  API docs

JS/TS Client v2

const classWithReranker = {
  class: 'Article',
  properties: [
    {
      name: 'title',
      dataType: ['text'],
    },
  ],
  vectorizer: 'text2vec-openai', // this could be any vectorizer
  moduleConfig: {
    'reranker-cohere': {}, // set your reranker module
  },
};

// Add the class to the schema
result = await client.schema.classCreator().withClass(classWithReranker).do();

Go

  articleClass := &models.Class{
    Class:       "Article",
    Description: "Collection of articles",
    Vectorizer:  "text2vec-openai",
    ModuleConfig: map[string]interface{}{
      "reranker-cohere": map[string]interface{}{
        "model": "rerank-v3.5",
      },
    },
  }

  API docs

Update the reranker model integration

Available from v1.25.23, v1.26.8 and v1.27.1

The reranker and generative configurations are mutable from v1.25.23, v1.26.8 and v1.27.1.

Update the reranker model integration for reranking retrieved results.

Python Client v4

from weaviate.classes.config import Reconfigure

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

collection.config.update(
    reranker_config=Reconfigure.Reranker.cohere()  # Update the reranker module
)

  API docs

Python Client v3

class_obj = {
    "moduleConfig": {
        "reranker-cohere": {}  # Update your reranker module
    }
}

client.schema.update_config("Article", class_obj)

  API docs  Deprecated (v3)

JS/TS Client v3

import { reconfigure } from 'weaviate-client';

const collection = client.collections.get('Article')

await collection.config.update({
    reranker: reconfigure.reranker.cohere()  // Update the reranker module
})

  API docs

JS/TS Client v2

// Collection definition updates are not available in the v2 API.
// Consider upgrading to the v3 API, or deleting and recreating the collection.

Go

  updatedArticleClassConfig := &models.Class{
    // Note: The new collection config must be provided in full,
    // including the configuration that is not being updated.
    // We suggest using the original class config as a starting point.
    Class: "Article",
    ModuleConfig: map[string]interface{}{
      "reranker-cohere": map[string]interface{}{
        "model": "rerank-v3.5",
      },
    },
  }

  API docs

Specify a generative model integration

Specify a generative model integration for a collection (for RAG).

Related pages

• Available generative model integrations

Python Client v4

from weaviate.classes.config import Configure, Property, DataType

client.collections.create(
    "Article",
    vectorizer_config=Configure.Vectorizer.text2vec_openai(),
    generative_config=Configure.Generative.openai(
        model="gpt-4o"  # set your generative model (optional parameter)
    ),
)

  API docs

Python Client v3

class_obj = {
    "class": "Article",
    "vectorizer": "text2vec-openai",  # set your vectorizer module
    "moduleConfig": {
        "generative-openai": {
            "model": "gpt-4o"  # set your generative model (optional parameter)
        }
    }
}

client.schema.create_class(class_obj)

  API docs  Deprecated (v3)

JS/TS Client v3

import { vectorizer, generative } from 'weaviate-client';

await client.collections.create({
  name: 'Article',
  vectorizers: vectorizer.text2VecOpenAI(),
  generative: generative.openAI({
    model: "gpt-4o"  // set your generative model (optional parameter)
  }),
})

  API docs

JS/TS Client v2

const classWithGenerative = {
  class: 'Article',
  properties: [
    {
      name: 'title',
      dataType: ['text'],
    },
  ],
  vectorizer: 'text2vec-openai', // this could be any vectorizer
  moduleConfig: {
    'generative-openai': {
      model: 'gpt-4o'  // set your generative model (optional parameter)
    },
  },
};

// Add the class to the schema
result = await client.schema.classCreator().withClass(classWithGenerative).do();

Go

  articleClass := &models.Class{
    Class:       "Article",
    Description: "Collection of articles",
    Vectorizer:  "text2vec-openai",
    ModuleConfig: map[string]interface{}{
      "generative-openai": map[string]interface{}{
        "model": "gpt-4o",
      },
    },
  }

  API docs

Java

// Configure OpenAI text2vec module settings
Map<String, Object> text2vecOpenAI = new HashMap<>();
Map<String, Object> text2vecOpenAISettings = new HashMap<>();
text2vecOpenAISettings.put("model", "text-embedding-3-small"); // or your preferred embedding model
text2vecOpenAI.put("text2vec-openai", text2vecOpenAISettings);

// Configure OpenAI generative module settings
Map<String, Object> generativeOpenAI = new HashMap<>();
Map<String, Object> generativeOpenAISettings = new HashMap<>();
generativeOpenAISettings.put("model", "gpt-4");
generativeOpenAI.put("generative-openai", generativeOpenAISettings);

// Combine module configurations
Map<String, Object> moduleConfig = new HashMap<>();
moduleConfig.put("text2vec-openai", text2vecOpenAI);
moduleConfig.put("generative-openai", generativeOpenAI);

// Create the Article collection with vectorizer and generative configuration
WeaviateClass articleCollection = WeaviateClass.builder()
    .className(collectionName)
    .vectorizer("text2vec-openai") // Set the vectorizer
    .moduleConfig(moduleConfig) // Set both vectorizer and generative configs
    .build();

// Add the collection to the schema
Result<Boolean> result = client.schema().classCreator()
    .withClass(articleCollection)
    .run();

  API docs

Update the generative model integration

Available from v1.25.23, v1.26.8 and v1.27.1

The reranker and generative configurations are mutable from v1.25.23, v1.26.8 and v1.27.1.

Update a generative model integration.

Python Client v4

from weaviate.classes.config import Reconfigure

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

collection.config.update(
    generative_config=Reconfigure.Generative.cohere()  # Update the generative module
)

  API docs

Python Client v3

class_obj = {
    "class": "Article",
    "moduleConfig": {
        "generative-cohere": {}  # Update your generative module
    }
}

client.schema.update_config("Article", class_obj)

  API docs  Deprecated (v3)

JS/TS Client v3

import { reconfigure } from 'weaviate-client';

const collection = client.collections.get("Article")

await collection.config.update({
    generative: weaviate.reconfigure.generative.cohere()  // Update the generative module
})

  API docs

JS/TS Client v2

// Collection definition updates are not available in the v2 API.
// Consider upgrading to the v3 API, or deleting and recreating the collection.

Go

  updatedArticleClassConfig := &models.Class{
    Class: "Article",
    ModuleConfig: map[string]interface{}{
      "generative-cohere": map[string]interface{}{},
    },
  }

  API docs

tip

You can override the generative integration settings at query time without updating it in the collection configuration.

Further resources

• API References: REST: Schema

• References: Configuration: Schema
• Concepts: Data structure

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.