Devis Lucato

@marcominerva what if we had 3 query providers, so we can merge now and support everyone? 1. query provider using VARBINARY column 2. query provider using VECTOR type 3. DefaultQueryProvider

hi @ZakFahey did you try TikToken with "gpt-4"? Something like: install nuget `Microsoft.ML.Tokenizers` version `0.22.0-preview.24179.1` and ```csharp public sealed class Tokenizer { private static readonly Tokenizer s_tokenizer = Tokenizer.CreateTiktokenForModel( "gpt-4",...

Closing as part of repository maintenance - no further action planned on this issue.

looks like a bug in the underlying Azure.AI.OpenAI 2.0.0-beta.5, I reported it here https://github.com/Azure/azure-sdk-for-net/issues/46109 including a workaround

@RogerBarreto the outstanding open issue here is the reliance on a pre-release package with [a noticeable (quite annoying) bug](https://github.com/Azure/azure-sdk-for-net/issues/46109) that impacts all SK consumers. Rather than waiting for the Azure...

FYI, I'm using this handler as a workaround: ```csharp public class AuthFixHandler : DelegatingHandler { protected override Task SendAsync( HttpRequestMessage request, CancellationToken cancellationToken) { if (request.Headers.TryGetValues("Authorization", out var headers) &&...

Closing as part of repository maintenance - no further action planned on this issue.

Without function calling and without embeddings, foundry local doesn't provide any compelling reason to switch from Ollama, LM Studio and similar free + cross-platform solutions.