From 22b39e11f2eca7dd70bcef3760cd5da149412d00 Mon Sep 17 00:00:00 2001
From: Kameshwara Pavan Kumar Mantha
 <25398886+pavanjava@users.noreply.github.com>
Date: Thu, 15 Aug 2024 04:08:37 +0530
Subject: [PATCH] llama_index serving integration documentation (#6973)

Co-authored-by: pavanmantha <pavan.mantha@thevaslabs.io>
---
 docs/source/serving/integrations.rst          |  1 +
 .../serving/serving_with_llamaindex.rst       | 27 +++++++++++++++++++
 2 files changed, 28 insertions(+)
 create mode 100644 docs/source/serving/serving_with_llamaindex.rst

diff --git a/docs/source/serving/integrations.rst b/docs/source/serving/integrations.rst
index 680ea523dfe94..7882e14f3b849 100644
--- a/docs/source/serving/integrations.rst
+++ b/docs/source/serving/integrations.rst
@@ -12,3 +12,4 @@ Integrations
    deploying_with_lws
    deploying_with_dstack
    serving_with_langchain
+   serving_with_llamaindex
diff --git a/docs/source/serving/serving_with_llamaindex.rst b/docs/source/serving/serving_with_llamaindex.rst
new file mode 100644
index 0000000000000..038e961344e47
--- /dev/null
+++ b/docs/source/serving/serving_with_llamaindex.rst
@@ -0,0 +1,27 @@
+.. _run_on_llamaindex:
+
+Serving with llama_index
+============================
+
+vLLM is also available via `llama_index <https://github.com/run-llama/llama_index>`_ .
+
+To install llamaindex, run
+
+.. code-block:: console
+
+    $ pip install llama-index-llms-vllm -q
+
+To run inference on a single or multiple GPUs, use ``Vllm`` class from ``llamaindex``.
+
+.. code-block:: python
+
+    from llama_index.llms.vllm import Vllm
+
+    llm = Vllm(
+        model="microsoft/Orca-2-7b",
+        tensor_parallel_size=4,
+        max_new_tokens=100,
+        vllm_kwargs={"swap_space": 1, "gpu_memory_utilization": 0.5},
+    )
+
+Please refer to this `Tutorial <https://docs.llamaindex.ai/en/latest/examples/llm/vllm/>`_ for more details.