nalcos
nalcos copied to clipboard
Search Git commits in natural language
Currently, we are using [multi-qa-MiniLM-L6-cos-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1), which has a speed (sentences encoded/sec on 1 V100 GPU) of 14200 and a model size of 80 MB. We should try out other models...
Do #28 before this Original idea from [this tweet](https://twitter.com/TheSankesara/status/1439963223428636676?s=20)
Do #28 before this Currently, the project is using an unauthenticated GH API which is capped to 60 requests per hour from an IP address. We can add the option...
Instead of the `--look-past` flag, the user should be given the choice to enter a date range using `--from` and `--to` flags.