Skip to content

Commit 6dc5c7b

Browse files
committed
docs: link to bge-small-en-v1.5 in the Embedding example
1 parent ab2f52a commit 6dc5c7b

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

docs/guide/embedding.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -43,7 +43,7 @@ const __dirname = path.dirname(
4343

4444
const llama = await getLlama();
4545
const model = await llama.loadModel({
46-
modelPath: path.join(__dirname, "Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf")
46+
modelPath: path.join(__dirname, "bge-small-en-v1.5-q8_0.gguf")
4747
});
4848
const context = await model.createEmbeddingContext();
4949

@@ -110,6 +110,7 @@ console.log("Document:", topSimilarDocument);
110110
> query: What is the tallest mountain on Earth?
111111
> Document: Mount Everest is the tallest mountain in the world
112112
> ```
113+
> This example uses [bge-small-en-v1.5](https://huggingface.co/CompendiumLabs/bge-small-en-v1.5-gguf/blob/main/bge-small-en-v1.5-q8_0.gguf)
113114
114115
## Getting Raw Vectors {#raw-vector}
115116
To get the raw embedding vectors, you can use the [`vector`](../api/classes/LlamaEmbedding.md#vector) property of the [`LlamaEmbedding`](../api/classes/LlamaEmbedding.md) object:

0 commit comments

Comments
 (0)