Denis Lapchev

Results 28 comments of Denis Lapchev

Plans for RRF?

Hi @saswat0 It crossed my mind as well, are you aware of any benefits of RRF compared to cross-encoder (besides speed)? In RRF, there are manual hyper-parameters that the user...

Plans for RRF?

Makes sense, think it is worth implementing in sake of feature completeness, not as a priority though

Scope for batched predictions

Hi, Thanks for the suggestion. How do you think batched prompts can be useful in the context of RAG?

Scope for batched predictions

I will add it as a potential improvement when implementing support for vLLM in the future. Thanks for the suggestion.

GPU not being used during inference

Thanks for taking the time to investigate it. I will update the setvars.sh and the documentation based on your findings. You are right - llamacpp is being compiled during the...

GPU not being used during inference

The relevant config is here - https://llm-search.readthedocs.io/en/latest/configure_model.html#ollama-litellm But can add more elaborate instructions

IndexError: index (2864) out of range when not re-creating index or restarting webapp after config change

Updating or creating an index via CLI and web interface are independent operations, i.e. when index is updated from cli, the web ui is not aware of it. You can...

IndexError: index (2864) out of range when not re-creating index or restarting webapp after config change

Just to understand better how to reproduce: * You are creating an index with specifc doc_path configured * You are adding a new doc path in the config and running...