v3.1.0

Pinecone .NET SDK 3.1.0 Release Notes

This release introduces new record-based APIs that simplify working with Pinecone indexes, especially for semantic search applications. These new APIs allow you to focus on your data rather than vector details, making the SDK more accessible for application developers.

New Features

Record-Based APIs

Two new endpoints have been added that offer a simplified interface for working with Pinecone:

UpsertRecordsAsync

await client.UpsertRecordsAsync(
    namespace,
    [
        new UpsertRecord
        {
            Id = "rec1",
            AdditionalProperties =
            {
                ["chunk_text"] = "Your text content here",
                ["category"] = "Your category",
            },
        },
        // Additional records...
    ]
);

• Allows direct insertion of records with structured data
• Automatically handles vector embedding behind the scenes
• Supports custom metadata through AdditionalProperties dictionary

SearchRecordsAsync

var response = await client.SearchRecordsAsync(
    namespace,
    new SearchRecordsRequest
    {
        Query = new SearchRecordsRequestQuery
        {
            TopK = 4,
            Inputs = new Dictionary<string, object?> { { "text", "Your search query" } },
        },
        Fields = ["category", "chunk_text"],
    }
);

• Search using natural language queries instead of vectors
• Specify which fields to include in the response
• Automatically handles query embedding and vector similarity search

Migration Guide

These new APIs are complementary to the existing vector-based APIs. If you're building semantic search applications, we recommend using these new record-based APIs for a more streamlined development experience.

Full Changelog: 3.0.0...3.1.0