Release v1.1.0

Features

Inference API

You can now try out Pinecone's Inference API, which is currently in public preview. See the README for more details.

ctx := context.Background()

pc, err := pinecone.NewClient(pinecone.NewClientParams{
   ApiKey: "YOUR_API_KEY",
})
if err !=  nil {
   log.Fatalf("Failed to create Client: %v", err)
}

embeddingModel := "multilingual-e5-large"
documents := []string{
   "Turkey is a classic meat to eat at American Thanksgiving."
   "Many people enjoy the beautiful mosques in Turkey."
}
docParameters := pinecone.EmbedParameters{
   InputType: "passage",
   Truncate: "END",
}

docEmbeddingsResponse, err := pc.Inference.Embed(ctx, &pinecone.EmbedRequest{
   Model: embeddingModel,
   TextInputs: documents,
   Parameters: docParameters,
})
if err != nil {
   log.Fatalf("Failed to embed documents: %v", err)
}
fmt.Printf("docs embedding response: %+v", docEmbeddingsResponse)

// << Upsert documents into Pinecone >>

Changes overview

• Refactor Integration Tests by @austin-denoble in #65
• Change "client" to "SDK" by @jseldess in #64
• Add GH release workflow and bump-version action, fix hard-coded client version by @austin-denoble in #66
• Implement Inference API by @austin-denoble in #67
• Fix runner in release workflow by @austin-denoble in #69
• Pass currentVersion in release workflow by @austin-denoble in #70

New Contributors

• @jseldess made their first contribution in #64

Full Changelog: v1.0.0...v1.1.0