feat: Waiting for embedding & rerank models

janhq / jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

https://jan.ai/

GNU Affero General Public License v3.0

21.15k stars 1.22k forks source link

Open hkwz2023 opened 2 months ago

hkwz2023 commented 2 months ago

It would be perfect if server could add embedding and reRank model loading and corresponding api, looking forward to it.

BradKML commented 2 months ago

Seconding this as currently places like LocalAI and Xinterface has them, and Ollama+LiteLLM might integrate Rerank models as well.