Update README.md after linting

llama-index-integrations/llms/llama-index-llms-ipex-llm/examples/README.md

@@ -64,36 +64,40 @@ python more_data_type.py -m <path_to_model> -t <path_to_tokenizer> -l <low_bit_f
 > <=4.34.
 
 ### Text2SQL Example
-This example [text2sql](./text2sql.py) demonstrates how to use LlamaIndex with `ipex-llm` to run a text-to-SQL model on Intel hardware. This example shows how to create a database, define a schema, and run SQL queries using low-bit model optimized with `ipex-llm`. 
+
+This example [text2sql](./text2sql.py) demonstrates how to use LlamaIndex with `ipex-llm` to run a text-to-SQL model on Intel hardware. This example shows how to create a database, define a schema, and run SQL queries using low-bit model optimized with `ipex-llm`.
 ### Setup
+
 It requires `llama-index-embeddings-ipex-llm` package as it uses `ipex-llm` embedding.
->
+
 > ```bash
 > pip install llama-index-embeddings-ipex-llm
 > ```
 
 #### Runtime Configurations
+
 For optimal performance, it is recommended to set several environment variables based on your device:
 
 - For Windows Users with Intel Core Ultra integrated GPU
-In Anaconda Prompt: 
->>```
->>set SYCL_CACHE_PERSISTENT=1
->>set BIGDL_LLM_XMX_DISABLED=1
->>```
+  In Anaconda Prompt:
+
+  > >```
+  > >set SYCL_CACHE_PERSISTENT=1
+  > >set BIGDL_LLM_XMX_DISABLED=1
+  > >```
 
 
 - For Linux Users with Intel Arc A-Series GPU:
->>```
->># Configure oneAPI environment variables. Required step for APT or offline installed oneAPI.
->># Skip this step for PIP-installed oneAPI since the environment has already been configured in LD_LIBRARY_PATH.
->>source /opt/intel/oneapi/setvars.sh
->>
->># Recommended Environment Variables for optimal performance
->>export USE_XETLA=OFF
->>export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
->>export SYCL_CACHE_PERSISTENT=1
->>```
+  > >```
+  > ># Configure oneAPI environment variables. Required step for APT or offline installed oneAPI.
+  > ># Skip this step for PIP-installed oneAPI since the environment has already been configured in LD_LIBRARY_PATH.
+  > >source /opt/intel/oneapi/setvars.sh
+  > >
+  > ># Recommended Environment Variables for optimal performance
+  > >export USE_XETLA=OFF
+  > >export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
+  > >export SYCL_CACHE_PERSISTENT=1
+  > >```
 
 >**NOTE** For the first time that each model runs on Intel iGPU/Intel Arc A300-Series or Pro A60, it may take several minutes to compile.
 
@@ -105,6 +109,6 @@ Then, run the example as following:
 python text2sql.py -m <path_to_model> -d <device> -e <path_to_embedding_model> -q <query_to_LLM> -n <num_predict>
 ```
 
->Please note that in this example we'll use [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) model for demonstration, as well as [bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) for our embedding model. It requires updating transformers and tokenizers packages. But you are also welcomed to use other models.
+> Please note that in this example we'll use [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) model for demonstration, as well as [bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) for our embedding model. It requires updating transformers and tokenizers packages. But you are also welcomed to use other models.
 
->If you use other LLMs and encounter output issues, please try changing it. 
+> If you use other LLMs and encounter output issues, please try changing it.