Nyckel makes image and text classification easy for everyone. In just a few minutes, you can build an AI model to categorize images and text using any labels you want. No machine learning experience needed.
Classifies image data based on pre-trained classifiers in Nyckel. See the documentation
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Classifies text data based on pre-trained classifiers in Nyckel. See the documentation
The Nyckel API offers machine learning capabilities, enabling you to add custom image and text classification to your applications without needing a data science background. With Nyckel, you can train models, make predictions, and refine your model iteratively as new data comes in. On Pipedream, you can integrate Nyckel to automate various tasks such as processing images uploaded to cloud storage, categorizing customer support tickets, or augmenting content moderation workflows. By harnessing the power of serverless on Pipedream, you can create efficient pipelines that respond in real-time to events, without managing infrastructure.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
nyckel: {
type: "app",
app: "nyckel",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://www.nyckel.com/v1/functions`,
headers: {
Authorization: `Bearer ${this.nyckel.$auth.oauth_access_token}`,
},
})
},
})
Develop, run and deploy your Python code in Pipedream workflows. Integrate seamlessly between no-code steps, with connected accounts, or integrate Data Stores and manipulate files within a workflow.
This includes installing PyPI packages, within your code without having to manage a requirements.txt
file or running pip
.
Below is an example of using Python to access data from the trigger of the workflow, and sharing it with subsequent workflow steps:
def handler(pd: "pipedream"):
# Reference data from previous steps
print(pd.steps["trigger"]["context"]["id"])
# Return data for use in future steps
return {"foo": {"test":True}}