| ▲ | m4r71n 3 days ago | |
How does this work under the hood? Does it build an in-memory vector database of the input sources and runs queries on top of that data to supplement the context window? | ||
| ▲ | brokegrammer 3 days ago | parent | next [-] | |
No idea how it's implemented because it's proprietary. Details here: https://support.anthropic.com/en/articles/11473015-retrieval... | ||
| ▲ | menaerus 2 days ago | parent | prev [-] | |
RAG commonly implies some sort of vector database to be built and which will then be used for response augmentation. If it operates over the repo, I believe it will index your codebase using those vector embeddings. | ||