From cc61fd808321459d0dae7161997b07ec92790b60 Mon Sep 17 00:00:00 2001
From: Xi Yan <xiyan@meta.com>
Date: Sat, 9 Nov 2024 09:00:18 -0800
Subject: [PATCH] docs

---
 docs/source/getting_started/index.md | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md
index cee79fea0..0804a3eb5 100644
--- a/docs/source/getting_started/index.md
+++ b/docs/source/getting_started/index.md
@@ -244,16 +244,6 @@ $ llama stack build --template meta-reference-gpu --image-type conda
 ```
 $ llama stack run ~/.llama/distributions/llamastack-meta-reference-gpu/meta-reference-gpu-run.yaml
 ```
-:::
-
-:::{tab-item} tgi
-1. Install the `llama` CLI. See [CLI Reference](https://llama-stack.readthedocs.io/en/latest/cli_reference/index.html)
-
-2. Build the `tgi` distribution
-
-```bash
-llama stack build --template tgi --image-type conda
-```
 
 Note: If you wish to use pgvector or chromadb as memory provider. You may need to update generated `run.yaml` file to point to the desired memory provider. See [Memory Providers](https://llama-stack.readthedocs.io/en/latest/api_providers/memory_api.html) for more details. Or comment out the pgvector or chromadb memory provider in `run.yaml` file to use the default inline memory provider, keeping only the following section: 
 ```
@@ -267,6 +257,17 @@ memory:
         db_path: ~/.llama/runtime/faiss_store.db
 ```
 
+:::
+
+:::{tab-item} tgi
+1. Install the `llama` CLI. See [CLI Reference](https://llama-stack.readthedocs.io/en/latest/cli_reference/index.html)
+
+2. Build the `tgi` distribution
+
+```bash
+llama stack build --template tgi --image-type conda
+```
+
 3. Start a TGI server endpoint
 
 4. Make sure in your `run.yaml` file, your `conda_env` is pointing to the conda environment and inference provider is pointing to the correct TGI server endpoint. E.g.