PowerPlatformConnectors/independent-publisher-connectors/Pinecone

Pinecone

Pinecone makes it easy to provide long-term memory for high-performance AI applications. Pinecone is a managed, cloud-native vector database with no infrastructure hassles. Pinecone serves fresh, filtered query results with low latency at the scale of billions of vectors.

Publisher: Troy Taylor, Hitachi Solutions

Prerequisites

You will need to sign up for an account with Pinecone.

Obtaining Credentials

Once logged in to your account, you can find your API key under your project on the API Keys page.

Supported Operations

Get index stats

Returns statistics about the index's contents, including the vector count per namespace and the number of dimensions.

Query namespace

Searches a namespace, using a query vector. It retrieves the identifiers of the most similar items in a namespace, along with their similarity scores.

Delete vectors

Deletes vectors, by identifier, from a single namespace.

Get vectors

Returns vectors, by identifier, from a single namespace.

Update vector

Updates vector in a namespace.

Upsert vector

Writes vectors into a namespace.

Get collections

Returns a list of your Pinecone collections.

Create collection

Creates a collection.

Get collection description

Retrieve the description of a collection.

Delete collection

Deletes an existing collection.

Get indexes

Returns a list of your indexes.

Create index

Create an index.

Get index description

Retrieve the description for an index.

Delete index

Deletes an existing index.

Update index

Updates the pod type and number of replicas for an index.

Known Issues and Limitations

There are no known issues at this time.