Vladimir Blagojevic
Vladimir Blagojevic
@julian-risch @ZanSara approved new unit tests for the token limits and OpenAI; they have been merged now. Perhaps if we don't hear from @LisaGLH by the end of the sprint...
If I understand you correctly, you should set `max_seq_len` value of the EmbeddingRetriever. The default is 512, but these OpenAI embedding models support longer sequence lengths. So if you are...
@LisaGLH I believe the recommendation above will fix the issue you are dealing with. If not, please feel free to reopen.
Glad it worked @LisaGLH Our current EmbeddingRetriever design aims to hide as many complexities as possible. This means you could just modify the embedding model name and expect it to...
@anakin87 Addressed some of your concerns in this update. Let's have another pass when you get a chance. TIA 🙏
@masci please have another look at this one.
> @vblagoje code looks good, can you add the release notes? It should be gtg now @masci LMK
@AI-Ahmed, how's this one coming along, anything we can help with?
@ZanSara Ahmed says you are familiar with this use case. Any suggestions on what we should do here in case @AI-Ahmed doesn't update this PR?
@AI-Ahmed yes you were clear about what you want to achieve; thank you! What I am not clear about is how do we proceed from this point? It seems that...