From 5cc69d4f419117a75d9fb561af9b0badb2350e87 Mon Sep 17 00:00:00 2001
From: ajosh0504 <apoorva.joshi@mongodb.com>
Date: Thu, 1 Aug 2024 14:13:28 +0200
Subject: [PATCH] Updating embedding section

---
 docs/50-prepare-the-data/4-embed-data.mdx              | 10 +++++++---
 .../2-create-vector-index.mdx                          |  4 ++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/docs/50-prepare-the-data/4-embed-data.mdx b/docs/50-prepare-the-data/4-embed-data.mdx
index c9fe502..c0511bc 100644
--- a/docs/50-prepare-the-data/4-embed-data.mdx
+++ b/docs/50-prepare-the-data/4-embed-data.mdx
@@ -12,7 +12,7 @@ The answers for code blocks in this section are as follows:
 <summary>Answer</summary>
 <div>
 ```python
-SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
+SentenceTransformer("thenlper/gte-small")
 ```
 </div>
 </details>
@@ -35,9 +35,13 @@ return embedding.tolist()
 <summary>Answer</summary>
 <div>
 ```python
-for doc in split_docs:
+for doc in tqdm(split_docs):
     doc["embedding"] = get_embedding(doc["body"])
     embedded_docs.append(doc)
 ```
 </div>
-</details>
\ No newline at end of file
+</details>
+
+:::caution
+If the embedding generation is taking too long (> 2-3 min), kill/interrupt the cell and move on to the next step with the documents that have been embedded up until that point.
+:::
\ No newline at end of file
diff --git a/docs/60-perform-semantic-search/2-create-vector-index.mdx b/docs/60-perform-semantic-search/2-create-vector-index.mdx
index e4a71b9..530b4c9 100644
--- a/docs/60-perform-semantic-search/2-create-vector-index.mdx
+++ b/docs/60-perform-semantic-search/2-create-vector-index.mdx
@@ -23,7 +23,7 @@ Select the `mongodb_rag_lab` database and the `knowledge` collection, change the
     {
       "type": "vector",
       "path": "embedding",
-      "numDimensions": 1024,
+      "numDimensions": 384,
       "similarity": "cosine"
     }
   ]
@@ -31,5 +31,5 @@ Select the `mongodb_rag_lab` database and the `knowledge` collection, change the
 ```
 
 :::info
-The number of dimensions in the index definition is 1024 since we are using Mixedbread AI's open-source [mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) model to generate embeddings in this lab.
+The number of dimensions in the index definition is 384 since we are using the [gte-small](https://huggingface.co/thenlper/gte-small) model to generate embeddings in this lab.
 :::
\ No newline at end of file