Search Rebuilt for AI. The Exa API retrieves the best content on the web using embeddings-based search.
Find similar links to the link provided. See the documentation](https://docs.metaphor.systems/reference/findsimilar)
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Retrieve contents of documents based on a list of document IDs. See the documentation. It is used to instantly
get content for documents, given the IDs of the documents. We currently support extracts - the first 1000 tokens (~750 words) of parsed HTML for a site. Note that each piece of content retrieved costs 1 request. Also note that instant
is a little bit of a lie if you are using keyword search, in which case contents might take a few seconds to retrieve.
Perform a search with a Metaphor prompt-engineered query and retrieve a list of relevant results. See the documentation
The Exa (Formerly Metaphor) API enables you to enrich your applications with machine learning-powered insights and data processing capabilities. With Exa, you can perform advanced data analysis, extract meaningful patterns, and automate decision-making processes within your projects. By integrating this API with Pipedream, you can create seamless workflows that leverage these intelligent features alongside other services to streamline your operations, enhance data intelligence, and drive innovation.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
metaphor: {
type: "app",
app: "metaphor",
}
},
async run({steps, $}) {
const data = {
"query": `test`,
}
return await axios($, {
method: "post",
url: `https://api.metaphor.systems/search`,
headers: {
"accept": `application/json`,
"Content-Type": `application/json`,
"x-api-key": `${this.metaphor.$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}}