fix: improve embedding documentation to use encoders

docs/guide/embedding.md

@@ -122,7 +122,11 @@ const __dirname = path.dirname(
 
 const llama = await getLlama();
 const model = await llama.loadModel({
-    modelPath: path.join(__dirname, "my-model.gguf")
+    /* 
+      You can also load quantized models such as "Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf", which generate embeddings 
+      using their intermediate layers. However, specialized encoders models are generally more accurate for search.
+    */
+    modelPath: path.join(__dirname, "nomic-embed-text-v1.5.f16.gguf")
 });
 const context = await model.createEmbeddingContext();
 

docs/index.md

@@ -117,7 +117,6 @@ const session = new LlamaChatSession({
     contextSequence: context.getSequence()
 });
 
-
 const q1 = "Hi there, how are you?";
 console.log("User: " + q1);
 
@@ -139,18 +138,17 @@ const __dirname = path.dirname(
 
 const llama = await getLlama();
 const model = await llama.loadModel({
-    modelPath: path.join(__dirname, "my-model.gguf")
+    modelPath: path.join(__dirname, "my-emb-model.gguf")
 });
-const context = await model.createEmbeddingContext();
-
-
-
 
+const context = await model.createEmbeddingContext();
 
 const text = "Hello world";
+
 console.log("Text:", text);
 
 const embedding = await context.getEmbeddingFor(text);
+
 console.log("Embedding vector:", embedding.vector);
 ```