From b706966ebc7e17cef3ced81c8e59c8f2d648a8c8 Mon Sep 17 00:00:00 2001 From: Tomoko Uchida Date: Wed, 22 Mar 2023 01:06:35 +0900 Subject: [PATCH] Add setup instruction in Getting Started for Indexing (#1847) `VectorstoreIndexCreator` [uses Chroma as the vectorstore by default](https://github.com/hwchase17/langchain/blob/1c22657256a69ecf739134da7d9cec5e9365a75f/langchain/indexes/vectorstore.py#L49). It may be helpful to add a short note for the setup. You can see how the notebook looks here. https://github.com/mocobeta/langchain/blob/feat/add-setup-instruction-to-index-getting-started/docs/modules/indexes/getting_started.ipynb --- docs/modules/indexes/getting_started.ipynb | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/docs/modules/indexes/getting_started.ipynb b/docs/modules/indexes/getting_started.ipynb index 2e7fe1a230..def30575ee 100644 --- a/docs/modules/indexes/getting_started.ipynb +++ b/docs/modules/indexes/getting_started.ipynb @@ -7,6 +7,12 @@ "source": [ "# Getting Started\n", "\n", + "By default, LangChain uses [Chroma](../../ecosystem/chroma.md) as the vectorstore to index and search embeddings. To walk through this tutorial, we'll first need to install `chromadb`.\n", + "\n", + "```\n", + "pip install chromadb\n", + "```\n", + "\n", "This example showcases question answering over documents.\n", "We have chosen this as the example for getting started because it nicely combines a lot of different elements (Text splitters, embeddings, vectorstores) and then also shows how to use them in a chain.\n", "\n",