[Doc] ruff format some Python examples (#26767)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

docs/deployment/frameworks/cerebrium.md

@@ -63,7 +63,7 @@ If successful, you should be returned a CURL command that you can call inference
 
 ??? console "Command"
 
-    ```python
+    ```bash
     curl -X POST https://api.cortex.cerebrium.ai/v4/p-xxxxxx/vllm/run \
     -H 'Content-Type: application/json' \
     -H 'Authorization: <JWT TOKEN>' \
@@ -81,7 +81,7 @@ You should get a response like:
 
 ??? console "Response"
 
-    ```python
+    ```json
     {
         "run_id": "52911756-3066-9ae8-bcc9-d9129d1bd262",
         "result": {

docs/deployment/frameworks/dstack.md

@@ -83,7 +83,7 @@ After the provisioning, you can interact with the model by using the OpenAI SDK:
 
     client = OpenAI(
         base_url="https://gateway.<gateway domain>",
-        api_key="<YOUR-DSTACK-SERVER-ACCESS-TOKEN>"
+        api_key="<YOUR-DSTACK-SERVER-ACCESS-TOKEN>",
     )
 
     completion = client.chat.completions.create(
@@ -93,7 +93,7 @@ After the provisioning, you can interact with the model by using the OpenAI SDK:
                 "role": "user",
                 "content": "Compose a poem that explains the concept of recursion in programming.",
             }
-        ]
+        ],
     )
 
     print(completion.choices[0].message.content)

docs/deployment/frameworks/haystack.md

@@ -34,7 +34,7 @@ pip install vllm haystack-ai
         api_key=Secret.from_token("VLLM-PLACEHOLDER-API-KEY"),
         model="mistralai/Mistral-7B-Instruct-v0.1",
         api_base_url="http://{your-vLLM-host-ip}:{your-vLLM-host-port}/v1",
-        generation_kwargs = {"max_tokens": 512}
+        generation_kwargs={"max_tokens": 512},
     )
 
     response = generator.run(

docs/deployment/frameworks/hf_inference_endpoints.md

@@ -32,28 +32,28 @@ This is the easiest way to get started with vLLM on Hugging Face Inference Endpo
     import os
 
     client = OpenAI(
-        base_url = DEPLOYMENT_URL,
-        api_key = os.environ["HF_TOKEN"] # https://huggingface.co/settings/tokens
+        base_url=DEPLOYMENT_URL,
+        api_key=os.environ["HF_TOKEN"],  # https://huggingface.co/settings/tokens
     )
 
     chat_completion = client.chat.completions.create(
-        model = "HuggingFaceTB/SmolLM3-3B",
-        messages = [
+        model="HuggingFaceTB/SmolLM3-3B",
+        messages=[
             {
                 "role": "user",
                 "content": [
                     {
                         "type": "text",
-                        "text": "Give me a brief explanation of gravity in simple terms."
+                        "text": "Give me a brief explanation of gravity in simple terms.",
                     }
-                ]
+                ],
             }
         ],
-        stream = True
+        stream=True,
     )
 
     for message in chat_completion:
-        print(message.choices[0].delta.content, end = "")
+        print(message.choices[0].delta.content, end="")
     ```
 
 !!! note
@@ -86,34 +86,34 @@ This method applies to models with the [`transformers` library tag](https://hugg
     import os
 
     client = OpenAI(
-        base_url = DEPLOYMENT_URL,
-        api_key = os.environ["HF_TOKEN"] # https://huggingface.co/settings/tokens
+        base_url=DEPLOYMENT_URL,
+        api_key=os.environ["HF_TOKEN"],  # https://huggingface.co/settings/tokens
     )
 
     chat_completion = client.chat.completions.create(
-        model = "ibm-granite/granite-docling-258M",
-        messages = [
+        model="ibm-granite/granite-docling-258M",
+        messages=[
             {
                 "role": "user",
                 "content": [
                     {
                         "type": "image_url",
                         "image_url": {
-                            "url": "https://huggingface.co/ibm-granite/granite-docling-258M/resolve/main/assets/new_arxiv.png"
-                        }
+                            "url": "https://huggingface.co/ibm-granite/granite-docling-258M/resolve/main/assets/new_arxiv.png",
+                        },
                     },
                     {
                         "type": "text",
-                        "text": "Convert this page to docling."
-                    }
+                        "text": "Convert this page to docling.",
+                    },
                 ]
             }
         ],
-        stream = True
+        stream=True,
     )
 
     for message in chat_completion:
-        print(message.choices[0].delta.content, end = "")
+        print(message.choices[0].delta.content, end="")
     ```
 
 !!! note

docs/deployment/frameworks/litellm.md

@@ -36,15 +36,16 @@ pip install vllm litellm
     ```python
     import litellm 
 
-    messages = [{ "content": "Hello, how are you?","role": "user"}]
+    messages = [{"content": "Hello, how are you?", "role": "user"}]
 
     # hosted_vllm is prefix key word and necessary
     response = litellm.completion(
-                model="hosted_vllm/qwen/Qwen1.5-0.5B-Chat", # pass the vllm model name
-                messages=messages,
-                api_base="http://{your-vllm-server-host}:{your-vllm-server-port}/v1",
-                temperature=0.2,
-                max_tokens=80)
+        model="hosted_vllm/qwen/Qwen1.5-0.5B-Chat", # pass the vllm model name
+        messages=messages,
+        api_base="http://{your-vllm-server-host}:{your-vllm-server-port}/v1",
+        temperature=0.2,
+        max_tokens=80,
+    )
 
     print(response)
     ```

docs/deployment/frameworks/retrieval_augmented_generation.md

@@ -40,7 +40,7 @@ pip install -U vllm \
 
 1. Run the script
 
-    ```python
+    ```bash
     python retrieval_augmented_generation_with_langchain.py
     ```
 
@@ -78,6 +78,6 @@ pip install vllm \
 
 1. Run the script:
 
-    ```python
+    ```bash
     python retrieval_augmented_generation_with_llamaindex.py
     ```