diff --git a/haystack/utils/auth.py b/haystack/utils/auth.py
index 75c348c7a..c8ba48369 100644
--- a/haystack/utils/auth.py
+++ b/haystack/utils/auth.py
@@ -24,6 +24,15 @@ class SecretType(Enum):
 class Secret(ABC):
     """
     Encapsulates a secret used for authentication.
+
+    Usage example:
+    ```python
+    from haystack.components.generators import OpenAIGenerator
+    from haystack.utils import Secret
+
+    generator = OpenAIGenerator(api_key=Secret.from_token("<here_goes_your_token>"))
+    ...
+    ```
     """
 
     @staticmethod
diff --git a/haystack/utils/hf.py b/haystack/utils/hf.py
index 9b0421ef2..31f2beca9 100644
--- a/haystack/utils/hf.py
+++ b/haystack/utils/hf.py
@@ -30,6 +30,8 @@ def serialize_hf_model_kwargs(kwargs: Dict[str, Any]):
     """
     Recursively serialize HuggingFace specific model keyword arguments
     in-place to make them JSON serializable.
+
+    :param kwargs: The keyword arguments to serialize
     """
     torch_import.check()
 
@@ -46,6 +48,8 @@ def deserialize_hf_model_kwargs(kwargs: Dict[str, Any]):
     """
     Recursively deserialize HuggingFace specific model keyword arguments
     in-place to make them JSON serializable.
+
+    :param kwargs: The keyword arguments to deserialize
     """
     torch_import.check()
 
@@ -99,7 +103,6 @@ def list_inference_deployed_models(headers: Optional[Dict] = None) -> List[str]:
     List all currently deployed models on HF TGI free tier
 
     :param headers: Optional dictionary of headers to include in the request
-    :type headers: Optional[Dict]
     :return: list of all currently deployed models
     :raises Exception: If the request to the TGI API fails
 
@@ -180,7 +183,7 @@ with LazyImport(message="Run 'pip install transformers[torch]'") as torch_and_tr
 
     class StopWordsCriteria(StoppingCriteria):
         """
-        Stops text generation if any one of the stop words is generated.
+        Stops text generation in HuggingFace generators if any one of the stop words is generated.
 
         Note: When a stop word is encountered, the generation of new text is stopped.
         However, if the stop word is in the prompt itself, it can stop generating new text
@@ -226,6 +229,15 @@ with LazyImport(message="Run 'pip install transformers[torch]'") as torch_and_tr
             return result
 
     class HFTokenStreamingHandler(TextStreamer):
+        """
+        Streaming handler for HuggingFaceLocalGenerator and HuggingFaceLocalChatGenerator.
+
+        Note: This is a helper class for HuggingFaceLocalGenerator & HuggingFaceLocalChatGenerator enabling streaming
+        of generated text via Haystack Callable[StreamingChunk, None] callbacks.
+
+        Do not use this class directly.
+        """
+
         def __init__(
             self,
             tokenizer: Union[PreTrainedTokenizer, PreTrainedTokenizerFast],
diff --git a/haystack/utils/requests_utils.py b/haystack/utils/requests_utils.py
index 6d207f45b..7d2248765 100644
--- a/haystack/utils/requests_utils.py
+++ b/haystack/utils/requests_utils.py
@@ -16,8 +16,15 @@ def request_with_retry(
 
     All kwargs will be passed to ``requests.request``, so it accepts the same arguments.
 
-    Example Usage:
-    --------------
+    :param attempts: Maximum number of attempts to retry the request.
+    :param status_codes_to_retry: List of HTTP status codes that will trigger a retry. When param is `None`,  HTTP 408, 418, 429 and 503 will be retried.
+    :param **kwargs: Optional arguments that ``request`` takes.
+    :return: :class:`Response <Response>` object
+
+
+    Usage examples:
+    ```python
+    from haystack.utils import request_with_retry
 
     # Sending an HTTP request with default retry configs
     res = request_with_retry(method="GET", url="https://example.com")
@@ -54,15 +61,7 @@ def request_with_retry(
 
     # Retry all 5xx status codes
     res = request_with_retry(method="GET", url="https://example.com", status_codes_to_retry=list(range(500, 600)))
-
-    :param attempts: Maximum number of attempts to retry the request, defaults to 3
-    :param status_codes_to_retry: List of HTTP status codes that will trigger a retry, defaults to [408, 418, 429, 503]:
-        - `408: Request Timeout`
-        - `418`
-        - `429: Too Many Requests`
-        - `503: Service Unavailable`
-    :param **kwargs: Optional arguments that ``request`` takes.
-    :return: :class:`Response <Response>` object
+    ```
     """
 
     if status_codes_to_retry is None: