Pinecone.NET 1.2.0

.NET 7.0 This package targets .NET 7.0. The package is compatible with this framework or higher.
There is a newer version of this package available.
See the version list below for details. 
dotnet add package Pinecone.NET --version 1.2.0                

                    
                

            
NuGet\Install-Package Pinecone.NET -Version 1.2.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="Pinecone.NET" Version="1.2.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add Pinecone.NET --version 1.2.0                

                    
                

            
#r "nuget: Pinecone.NET, 1.2.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
// Install Pinecone.NET as a Cake Addin
#addin nuget:?package=Pinecone.NET&version=1.2.0

// Install Pinecone.NET as a Cake Tool
#tool nuget:?package=Pinecone.NET&version=1.2.0

Pinecone.NET

Pinecone.NET is a C# library for the Pinecone vector database. It aims to provide identical functionality to the official Python and Rust libraries.

Features

  • Standard Index operations
  • gRPC and REST transports for vector operations
  • Sparse-dense vectors
  • Efficient vector serialization
  • Metadata support
  • NativeAOT compatibility

Installation

dotnet add package Pinecone.NET or Install-Package Pinecone.NET

Usage

Working with indexes

using Pinecone;

// Initialize the client with your API key and environment
var apiKey = "<your-api-key>";
var environment = "<your-environment>"; // for example us-east4-gcp

using var pinecone = new PineconeClient(apiKey, environment);

// List all indexes
var indexes = await pinecone.ListIndexes();

// Create a new index if it doesn't exist
var indexName = "myIndex";
if (!indexes.Contains(indexName))
{
    await pinecone.CreateIndex(indexName, 1536, Metric.Cosine);
}

// Get an index (uses gRPC transport by default)
using var index = await pinecone.GetIndex(indexName);

// Get an index that uses specific transport
using Pinecone.Rest;
...
using var index = await pinecone.GetIndex<RestTransport>(indexName);

// Configure an index
await pinecone.ConfigureIndex(indexName, replicas: 2, podType: "p2");

// Delete an index
await pinecone.DeleteIndex(indexName);

Working with vectors

// Assuming you have an instance of `index`
// Create and upsert vectors
var vectors = new[]
{
    new Vector
    {
        Id = "vector1",
        Values = new float[] { 0.1f, 0.2f, 0.3f },
        Metadata = new MetadataMap
        {
            ["genre"] = "horror",
            ["duration"] = 120
        }
    }
};
await index.Upsert(vectors);

// Fetch vectors by IDs
var fetched = await index.Fetch(new[] { "vector1" });

// Query scored vectors by ID
var scored = await index.Query("vector1", topK: 10);

// Query scored vectors by a new, previously unseen vector
var vector = new[] { 0.1f, 0.2f, 0.3f, ... };
var scored = await index.Query(vector, topK: 10);

// Delete vectors by vector IDs
await index.Delete(new[] { "vector1" });

// Delete vectors by metadata filter
await index.Delete(new MetadataMap
{
  ["genre"] = new MetadataMap
  {
     ["$in"] = new MetadataValue[] { "documentary", "action" }
  }
});

// Delete all vectors in the index
await index.DeleteAll();

Working with Collections

using Pinecone;

// Assuming you have an instance of `PineconeClient` named `pinecone`
  
// List all collections
var collections = await pinecone.ListCollections();

// Create a new collection
await pinecone.CreateCollection("myCollection", "myIndex");

// Describe a collection
var details = await pinecone.DescribeCollection("myCollection");

// Delete a collection
await pinecone.DeleteCollection("myCollection");

Contributing

Contributions are welcome! Feel free open an issue or a PR.

Product Compatible and additional computed target framework versions.
.NET net7.0 is compatible.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (3)

Showing the top 3 NuGet packages that depend on Pinecone.NET:

Package Downloads
Microsoft.SemanticKernel.Connectors.Pinecone

Pinecone connector for Semantic Kernel plugins and semantic memory
Squidex.AI

Squidex Internal Libraries
OBotService

OBase Framework

GitHub repositories (2)

Showing the top 2 popular GitHub repositories that depend on Pinecone.NET:

Repository Stars
microsoft/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
Azure-Samples/azure-search-openai-demo-csharp
A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
Version Downloads Last updated
3.0.0 1,247 9/27/2024
2.1.1 48,929 6/21/2024
2.1.0 2,993 6/5/2024
2.0.0 677 5/18/2024
1.4.0 6,753 12/17/2023
1.3.2 8,787 11/21/2023
1.3.1 645 11/14/2023
1.3.0 24,693 8/15/2023
1.2.2 2,416 7/27/2023
1.2.1 4,949 7/7/2023
1.2.0 2,392 5/15/2023
1.1.0 110 5/13/2023
1.0.0 327 5/10/2023

https://github.com/neon-sunset/Pinecone.NET/releases/tag/1.2.0