Long-term Memory for AI. The Pinecone vector database makes it easy to build high-performance vector search applications. Developer-friendly, fully managed, and easily scalable without infrastructure hassles.
Deletes one or more vectors by ID, from a single namespace. See the documentation.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Looks up and returns vectors by ID, from a single namespace.. See the documentation.
Searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores. See the documentation.
Updates vector in a namespace. If a value is included, it will overwrite the previous value. See the documentation.
The Pinecone API enables you to work with vector databases, which are essential for building and scaling applications with AI features like recommendation systems, image recognition, and natural language processing. On Pipedream, you can create serverless workflows integrating Pinecone with other apps, automate data ingestion, query vector databases in response to events, and orchestrate complex data processing pipelines that leverage Pinecone's similarity search.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
pinecone: {
type: "app",
app: "pinecone",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.pinecone.io/collections`,
headers: {
"Api-Key": `${this.pinecone.$auth.api_key}`,
},
})
},
})
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}}