I was interested in how the duplicate detection of issues is working. It uses Cohere API for embeddings (full issue text) [1] and vector-based similarity search [2].

[1] https://github.com/tegonhq/tegon/blob/158b54af8d6f7cf4195c61...

[2] https://github.com/tegonhq/tegon/blob/158b54af8d6f7cf4195c61...