Create and manage machines that read and write.
Determine the sentiment of the given text (positive, negative, or neutral). See the documentation.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Identify and extract significant keywords from the given text. See the documentation.
Generate a blog post based on the given prompt. See the documentation.
Generate a short summary for news headlines. See the documentation.
The Metatext.AI Pre-built AI Models API offers various artificial intelligence capabilities such as natural language processing, image recognition, and sentiment analysis. This API enables users to add AI features to their applications without the need for extensive machine learning expertise. Utilizing this API in Pipedream workflows allows for automation and integration with other services, making it possible to process and analyze text and images within a serverless environment efficiently.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
metatext_ai_pre_build_ai_models_api: {
type: "app",
app: "metatext_ai_pre_build_ai_models_api",
}
},
async run({steps, $}) {
const data = {
"text": `{your_text}`,
}
return await axios($, {
method: "post",
url: `https://api.metatext.ai/hub-inference/sentiment-analysis`,
headers: {
"Content-Type": `application/json`,
"x-api-key": `${this.metatext_ai_pre_build_ai_models_api.$auth.api_key}`,
},
data,
})
},
})
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}}