Dániel Kántor
Dániel Kántor
When working in teams on a large repository, it could be useful to share database dumps automatically so that not all clients have to re-analize all files in the repository....
In some use cases it might be useful to get more context about a result file by adding a specific number of lines in the beginning or end of the...
see https://huggingface.co/hkunlp/instructor-xl https://github.com/chroma-core/docs/blob/main/docs/embeddings.md
It would be interesting to add fuzzy finding features in addition to vector search and keyword/regex search. It could be based on the regex search by allowing some typos in...
While SeaGOAT is primarily used locally, there seems to be interest in running it on servers. Since SeaGOAT makes subprocess calls, we should sanitize user input to make sure that...
This is a list of ideas to support huge repositories and monorepos - [ ] Allow creating separate caches for subfolders - [ ] Allow querying specific folders. In this...
When the remote server returns files that are not available locally, they are simply hidden from the results locally. That kinda makes sense, after all the file does not exist....
Some chunks might be repeating across several files. These will probably not lead to useful results and might not even contain a lot of useful information. We could experiment with...