gkiri issues

Results 6 issues of


                                            gkiri

context length exceeded message for GPT-3.5-turbo even for for few tokens

When GPT-3.5-turbo model is configured , below message is seen even though query is one or two tokens.Irrespective of token length below message is seen for all queries. Note: GPT4...

text2vec-ollama is not working

### How to reproduce this bug? Enable the text2vec-ollama module ### What is the expected behavior? able to import ### What is the actual behavior? skipping the module ### Supporting...

bug

Support for whisper models in Ollama

feature request

Can't give answers without adding any documents.It should work even with no documents .

TTFT latency for long context (16K) is very high around 15 seconds for llama3.1 70b model. (same or worse than vLLM)

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

high priority

performance

Great project and thank you for open sourcing .For the folks who would like to order ready made kit , Can you please provide info on where to order full Omni next kit with all 4fisheye cameras integrated.