You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+13-2Lines changed: 13 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -263,9 +263,20 @@ claude mcp add cocoindex-code \
263
263
264
264
Any model supported by LiteLLM works — see the [full list of embedding providers](https://docs.litellm.ai/docs/embedding/supported_embedding).
265
265
266
-
### GPU-optimised local model
266
+
### Local SentenceTransformers models
267
267
268
-
If you have a GPU, [`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
268
+
Use the `sbert/` prefix to load any [SentenceTransformers](https://www.sbert.net/) model locally (no API key required).
[`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
0 commit comments