From 5c5c5ccd343bcd9b8096d8dec2e6ae1e585c4691 Mon Sep 17 00:00:00 2001
From: Ben Sowell <ben@aryn.ai>
Date: Fri, 6 Sep 2024 09:59:51 -0700
Subject: [PATCH] Update docs with more info on dependencies. (#769)

---
 docs/source/sycamore/get_started.rst            | 17 +++++++++++++++++
 .../sycamore/tutorials/etl_for_opensearch.md    |  2 +-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/docs/source/sycamore/get_started.rst b/docs/source/sycamore/get_started.rst
index c3d7ff2e0..d07e96ee9 100644
--- a/docs/source/sycamore/get_started.rst
+++ b/docs/source/sycamore/get_started.rst
@@ -12,6 +12,23 @@ We recommend installing the Sycmaore library using ``pip``:
 
 ..
 
+Connectors for vector databases can be installed via extras. For example,
+
+.. code-block:: python
+
+    pip install sycamore-ai[opensearch]
+
+..
+
+will install Sycamore with OpenSearch support. You can find a list of supported connectors :doc:`here </sycamore/connectors>`.
+
+By default, Sycamore works with the Aryn Partitioning Service to process PDFs. To run inference locally, install the `local-inference` extra as follows:
+
+.. code-block:: python
+
+    pip install sycamore-ai[local-inference]
+
+..
 
 Next, you can set the proper API keys for related services, like the Aryn Partitioning Service (APS) for processing PDFs (`sign-up here <https://www.aryn.ai/get-started>`_ for free) or OpenAI to use GPT with Sycamore's LLM-based transforms.
 
diff --git a/docs/source/sycamore/tutorials/etl_for_opensearch.md b/docs/source/sycamore/tutorials/etl_for_opensearch.md
index 175a1731a..a3d5a0400 100644
--- a/docs/source/sycamore/tutorials/etl_for_opensearch.md
+++ b/docs/source/sycamore/tutorials/etl_for_opensearch.md
@@ -6,7 +6,7 @@ In this example, we will be using PDF documents from the [Sort Benchmark](http:/
 
 ## Steps
 
-1. Install Sycamore using pip using [these instructions](../sycamore/get_started.rst)
+1. Install Sycamore using pip using [these instructions](/sycamore/get_started)
 
 2. Create a Python script and import Sycamore. In the following code snippet, we are initializing Sycamore and creating a DocSet by reading all the files from a local path.