Use AI and machine learning models in a few click.

A set of models, endpoints and tools ready to use!


State of the art embeddings in more than 100 languages.

Chat Completion

GPT-3.5 Turbo, GPT-4 and Open Source LLMs.


Chain prompts and models.

Vectorization and RAG

Read, store and query your documents for RAG.

Start using our models with a simple API call.​

					# Example using Gwenlake API for documents embedding

import gwenlake

documents = [
    "Do Not Watch This Movie!",
    "This movie is SOOOO funny!!! The acting is WONDERFUL.",
    "Everything about this movie is horrible, from the acting to the editing.",

api_key = "sk-XXX" # get in touch to get your API Key

client = gwenlake.Client(api_key)

response = client.embeddings.create(input=list_of_texts, model="e5-base-v2")

for item in