update vLLM integration page

integrations/vllm.md

@@ -1,7 +1,7 @@
 ---
 layout: integration
 name: vLLM Invocation Layer
-description: Use a vLLM server or locally hosted instance in your Prompt Node
+description: Use the vLLM inference engine with Haystack
 authors:
   - name: Lukas Kreussel
     socials:
@@ -25,15 +25,67 @@ Simply use [vLLM](https://github.com/vllm-project/vllm) in your haystack pipelin
     </a>
 </p>
 
-## Installation
+### Table of Contents
+
+- [Overview](#overview)
+- [Haystack 2.0](#haystack-20)
+  - [Installation](#installation)
+  - [Usage](#usage)
+- [Haystack 1.x](#haystack-1x)
+  - [Installation (1.x)](#installation-1x)
+  - [Usage (1.x)](#usage-1x)
+
+## Overview
+
+[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
+It is an open-source project that allows serving open models in production, when you have GPU resources available.
+
+For Haystack 1.x, the integration is available as a separate package, while for Haystack 2.x, the integration comes out of the box.
+
+## Haystack 2.x
+
+vLLM can be deployed as a server that implements the OpenAI API protocol.
+This allows vLLM to be used with the `OpenAIGenerator` and `OpenAIChatGenerator` components in Haystack.
+
+For an end-to-end example of [vLLM + Haystack 2.x, see this notebook](https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/vllm_inference_engine.ipynb).
+
+
+### Installation
+vLLM should be installed.
+- you can use `pip`: `pip install vllm` (more information in the [vLLM documentation](https://docs.vllm.ai/en/latest/getting_started/installation.html))
+- for production use cases, there are many other options, including Docker ([docs](https://docs.vllm.ai/en/latest/serving/deploying_with_docker.html))
+
+### Usage
+You first need to run an vLLM OpenAI-compatible server. You can do that using [Python](https://docs.vllm.ai/en/latest/getting_started/quickstart.html#openai-compatible-server) or [Docker](https://docs.vllm.ai/en/latest/serving/deploying_with_docker.html). 
+
+Then, you can use the `OpenAIGenerator` and `OpenAIChatGenerator` components in Haystack to query the vLLM server.
+
+```python
+from haystack.components.generators.chat import OpenAIChatGenerator
+from haystack.dataclasses import ChatMessage
+from haystack.utils import Secret
+
+generator = OpenAIChatGenerator(
+    api_key=Secret.from_token("VLLM-PLACEHOLDER-API-KEY"),  # for compatibility with the OpenAI API, a placeholder api_key is needed
+    model="mistralai/Mistral-7B-Instruct-v0.1",
+    api_base_url="http://localhost:8000/v1",
+    generation_kwargs = {"max_tokens": 512}
+)
+
+response = generator.run(messages=[ChatMessage.from_user("Hi. Can you help me plan my next trip to Italy?")])
+```
+
+## Haystack 1.x
+
+### Installation (1.x)
 Install the wrapper via pip:  `pip install vllm-haystack`
 
-## Usage
+### Usage (1.x)
 This integration provides two invocation layers:
 - `vLLMInvocationLayer`: To use models hosted on a vLLM server
 - `vLLMLocalInvocationLayer`: To use locally hosted vLLM models
 
-### Use a Model Hosted on a vLLM Server
+#### Use a Model Hosted on a vLLM Server
 To utilize the wrapper the `vLLMInvocationLayer` has to be used. 
 
 Here is a simple example of how a `PromptNode` can be created with the wrapper.
@@ -52,12 +104,12 @@ prompt_node = PromptNode(model_name_or_path=model, top_k=1, max_length=256)
 The model will be inferred based on the model served on the vLLM server.
 For more configuration examples, take a look at the unit-tests.
 
-#### Hosting a vLLM Server
+##### Hosting a vLLM Server
 
 To create an *OpenAI-Compatible Server* via vLLM you can follow the steps in the 
 Quickstart section of their [documentation](https://vllm.readthedocs.io/en/latest/getting_started/quickstart.html#openai-compatible-server).
 
-### Use a Model Hosted Locally
+#### Use a Model Hosted Locally
 ⚠️To run `vLLM` locally you need to have `vllm` installed and a supported GPU.
 
 If you don't want to use an API-Server this wrapper also provides a `vLLMLocalInvocationLayer` which executes the vLLM on the same node Haystack is running on.