Václav Černý

Exactly the same issue. The connection freezes after approx. 40+ seconds every time on iPhone 8. No logs on providers side, even with -debug switch on. The problem is indeed:...

Hello, I have tried to change the default embedding model for "mxbai-embed-large-v1". Docker build went fine, but when I try to ingest any document I get error: "Embedding dimension 1024...

I have a feeling this will be sorted out in upcoming v0.1.118. Lets see.

Hello, reporting the same problem with error "cuda driver library failed to get device context 801": `time=2024-09-17T05:56:32.395Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx2 cuda_v11 cuda_v12 rocm_v60102 cpu cpu_avx]" time=2024-09-17T05:56:32.395Z level=DEBUG...

As I found out the hard way, the support for custom LLMs and/or AzureAI models exists only on paper.. For any serious evaluations one needs access to OpenAI API, sadly.

llama.cpp is about to get ranking support, better to start working on those endpoints :) https://github.com/ggerganov/llama.cpp/pull/9510#issuecomment-2367526441

Hello @constantinidan , after a few months, is there any solution for Chainlit + Haystack streaming? Thanks!

Having exactly the same use case - peer can access the public Internet only via HTTP PROXY (defined in $HTTP_PROXY or similar env variable). The proxy itself is Squid. Btw....

This does not help.. You can see below that curl works, because it by default uses $HTTP_PROXY. Direct connection by Netbird does not. > 2025-05-22T13:14:05Z INFO util/grpc/dialer.go:89: DialContext error: context...

Hi, do you think this would be ever achievable?