From b6a8710dee88acc1c52c44ad6673e29ac282a494 Mon Sep 17 00:00:00 2001 From: ajosh0504 Date: Tue, 8 Oct 2024 14:58:15 -0700 Subject: [PATCH] Making things clearer --- docs/40-dev-env/1-dev-setup.mdx | 2 +- docs/50-prepare-the-data/2-chunk-data.mdx | 2 +- docs/60-perform-semantic-search/1-concepts.mdx | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/40-dev-env/1-dev-setup.mdx b/docs/40-dev-env/1-dev-setup.mdx index 2095f60c..e0ce67c7 100644 --- a/docs/40-dev-env/1-dev-setup.mdx +++ b/docs/40-dev-env/1-dev-setup.mdx @@ -16,7 +16,7 @@ To do this, choose one of the **Save a copy** options in the **File** menu. That's it! You're ready for the lab! -## Local setup +## [Backup] Local setup :::caution Run the notebook locally ONLY IF Google Colab is not an option/doesn't work for you. diff --git a/docs/50-prepare-the-data/2-chunk-data.mdx b/docs/50-prepare-the-data/2-chunk-data.mdx index 9d422e53..4ade00ba 100644 --- a/docs/50-prepare-the-data/2-chunk-data.mdx +++ b/docs/50-prepare-the-data/2-chunk-data.mdx @@ -13,7 +13,7 @@ The answers for code blocks in this section are as follows:
```python RecursiveCharacterTextSplitter.from_tiktoken_encoder( - encoding_name="cl100k_base", separators=separators, chunk_size=200, chunk_overlap=30 + model_name="gpt-4", separators=separators, chunk_size=200, chunk_overlap=30 ) ```
diff --git a/docs/60-perform-semantic-search/1-concepts.mdx b/docs/60-perform-semantic-search/1-concepts.mdx index c1a40713..ceb289b4 100644 --- a/docs/60-perform-semantic-search/1-concepts.mdx +++ b/docs/60-perform-semantic-search/1-concepts.mdx @@ -11,7 +11,7 @@ To perform vector search on your data in MongoDB, you need to create a vector se "type": "vector", "path": "embedding", "numDimensions": 1536, - "similarity": "euclidean | cosine | dotProduct" + "similarity": "cosine" }, { "type": "filter",