Skip to main content


This section of the documentation is deprecated and will be removed in the future.
See the relevant model provider integration page for the most up-to-date information.


The text2vec-cohere module enables Weaviate to obtain vectors using Cohere.

Key notes:

  • As it uses a third-party API, you will need an API key.
  • Its usage may incur costs.
    • See the Cohere pricing page, especially before vectorizing large amounts of data.
  • This module is available on Weaviate Cloud (WCD).
  • Enabling this module will enable the nearText search operator.
  • The default model is embed-multilingual-v3.0.
  • Set the appropriate distance metric in your class configuration, depending on the model used.

Where to set module parameters

The module accepts parameters through the request header, collection configuration, or environment variables. Some parameters (such as the API key) can be set in multiple ways.

Where the same parameter can be set in multiple ways, setting it at query-time through the HTTP request header (if possible) will have the highest precedence.

We suggest you only set any given parameter in one place to avoid confusion.

Weaviate instance configuration


If you use Weaviate Cloud (WCD), this module is already enabled and pre-configured. You cannot edit the configuration in WCD.

Docker Compose file

To use text2vec-cohere, you must enable it in your Docker Compose file (docker-compose.yml). You can do so manually, or create one using the Weaviate configuration tool.


  • ENABLE_MODULES (Required): The modules to enable. Include text2vec-cohere to enable the module.
  • DEFAULT_VECTORIZER_MODULE (Optional): The default vectorizer module. You can set this to text2vec-cohere to make it the default for all classes.
  • COHERE_APIKEY (Optional): Your Cohere API key. You can also provide the key at query time.


This configuration enables text2vec-cohere, sets it as the default vectorizer, and sets the API keys.

version: '3.4'
restart: on-failure:0
- 8080:8080
- 50051:50051
ENABLE_MODULES: text2vec-cohere
COHERE_APIKEY: sk-foobar # Setting this parameter is optional, you can also provide the API key at query time.

Class configuration

You can configure how the module will behave in each class through the Weaviate schema.

API settings


modelNoembed-multilingual-v3.0The model to use.
truncateNoENDSets Cohere API input truncation behavior (NONE, START or END - read more).
baseURLNohttps://api.cohere.aiSets a proxy or other URL instead of the default URL.

Use a the protocol domain format:


The following example configures the Document class by setting the vectorizer to text2vec-cohere, distance metric to cosine, model to embed-multilingual-v3.0 and without input truncation by the Cohere API.


Different Cohere models use different distance metrics. Make sure to set this accordingly. See the distance metric section for more information.

"classes": [
"class": "Document",
"description": "A class called document",
"vectorizer": "text2vec-cohere",
"vectorIndexConfig": {
"distance": "cosine"
"moduleConfig": {
"text2vec-cohere": {
"model": "embed-multilingual-v3.0", // Defaults to embed-multilingual-v3.0 if not set
"truncate": "END", // Defaults to END if not set
"baseURL": "" // Optional. Can be overridden by one set in the HTTP header.

Vectorization settings

You can set vectorizer behavior using the moduleConfig section under each class and property:


  • vectorizer - what module to use to vectorize the data.
  • vectorizeClassName – whether to vectorize the class name. Default: true.


  • skip – whether to skip vectorizing the property altogether. Default: false
  • vectorizePropertyName – whether to vectorize the property name. Default: false


"classes": [
"class": "Document",
"description": "A class called document",
"vectorizer": "text2vec-cohere",
"vectorIndexConfig": {
"distance": "cosine"
"moduleConfig": {
"text2vec-cohere": {
"model": "embed-multilingual-v3.0", // Defaults to embed-multilingual-v3.0 if not set
"truncate": "END", // Defaults to END if not set
"vectorizeClassName": false
"properties": [
"name": "content",
"dataType": ["text"],
"description": "Content that will be vectorized",
"moduleConfig": {
"text2vec-cohere": {
"skip": false,
"vectorizePropertyName": false

Query-time parameters

You can supply parameters at query time by adding it to the HTTP header.

HTTP HeaderValuePurposeNote
"X-Cohere-Api-Key""YOUR-COHERE-API-KEY"Cohere API key
"X-Cohere-BaseURL""YOUR-COHERE-BASE-URL"Cohere base URLAvailable from version v1.22.3

Use the protocol domain format:

If specified, this will have precedence over the class-level setting.

Additional information

Available models

You can use any of the following models with text2vec-cohere (source):

  • embed-multilingual-v3.0 (Default)
  • embed-multilingual-light-v3.0
  • embed-multilingual-v2.0
  • embed-english-v3.0
  • embed-english-light-v3.0
  • embed-english-v2.0
  • embed-english-light-v2.0
Deprecated models

The following models are available, but deprecated:

  • multilingual-22-12
  • large
  • medium
  • small

text2vec-cohere defaults to the embed-multilingual-v3.0 embedding model unless specified otherwise.

embed-multilingual-v2.0 == multilingual-22-12

embed-multilingual-v2.0 reflects the new name.

Distance metric

Cohere's embed-multilingual-v2.0 model uses dot product distances. With the v3 models, you can use any distance metric (dot, cosine or Euclidean) (source).

You can see a list of supported distance metrics here.


If the input text contains too many tokens and is not truncated, the Cohere API will throw an error. The Cohere API can be set to automatically truncate your input text.

You can set the truncation option with the truncate parameter to any of "NONE", "START", "END". Passing END will discard the right side of the input, and passing START will discard the left side of the input. The remaining input is exactly the maximum input token length for the model. Cohere's default behavior is to truncate at the END if it is not set. (source)

  • The upside of truncating is that a batch import always succeeds.
  • The downside of truncating (i.e., NONE) is that a large text will be partially vectorized without the user being made aware of the truncation.

API rate limits

Since this module uses your API key, your account's corresponding rate limits will also apply to the module. Weaviate will output any rate-limit related error messages generated by the API.

More information about Cohere rate limits can be found here.

Import throttling

One potential solution to rate limiting would be to throttle the import within your application. We include an example below.

See code example
from weaviate import Client
import time

def configure_batch(client: Client, batch_size: int, batch_target_rate: int):
Configure the weaviate client's batch so it creates objects at `batch_target_rate`.

client : Client
The Weaviate client instance.
batch_size : int
The batch size.
batch_target_rate : int
The batch target rate as # of objects per second.

def callback(batch_results: dict) -> None:

# you could print batch errors here
time_took_to_create_batch = batch_size * (client.batch.creation_time/client.batch.recommended_num_objects)
max(batch_size/batch_target_rate - time_took_to_create_batch + 1, 0)


Usage example

This is an example of a nearText query with text2vec-cohere.

import weaviate
from weaviate.classes.query import MetadataQuery, Move
import os

client = weaviate.connect_to_local(
"X-Cohere-Api-Key": os.getenv("COHERE_APIKEY"),

publications = client.collections.get("Publication")

response = publications.query.near_text(
move_to=Move(force=0.85, concepts="haute couture"),
move_away=Move(force=0.45, concepts="finance"),

for o in response.objects:


Questions and feedback

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