Minor clean-up and update readme

README.md

@@ -10,7 +10,7 @@
 
 ## Description
 
-This validator checks if an LLM-generated text is gibberish/non-sensical. It can validate either sentence by sentence or the entire text as a whole.
+This validator validates the "cleanliness" of the text generated by a language model. It uses a pre-trained model to determine if the text is coherent and not gibberish. The validator can be used to filter out text that is not coherent or does not make sense.
 
 ## Requirements
 - Dependencies: `nltk`, `transformers`, `torch`
@@ -32,19 +32,32 @@ In this example, we use the `gibberish_text` validator on any LLM generated text
 from guardrails.hub import GibberishText
 from guardrails import Guard
 
-# Initialize Validator
-val = GibberishText(threshold=0.75, validation_method="sentence", on_fail="fix")
+# Use the Guard with the validator
+guard = Guard().use(
+    GibberishText, threshold=0.5, validation_method="sentence", on_fail="exception"
+)
 
-# Setup Guard
-guard = Guard.from_string(
-    validators=[val, ...],
+# Test passing response
+guard.validate(
+    "Azure is a cloud computing service created by Microsoft. It's a significant competitor to AWS."
 )
 
-# Pass LLM output through guard
-guard.parse("Zoom is a great video conferencing tool. It's very easy to use.")  # Pass
-guard.parse("The quick brown fox jumps over the lazy dog. Fox fox fox fox fox. Floppyland gsdkd%$klsdml")  # Fail
+try:
+    # Test failing response
+    guard.validate(
+        "Floppyland love great coffee okay. Fox fox fox. Move to New York City."
+    )
+except Exception as e:
+    print(e)
+```
+Output:
+```console
+Validation failed for field with errors: The following sentences in your response were found to be gibberish:
 
+- Floppyland love great coffee okay.
+- Fox fox fox.
 ```
+**Note: See how only the first 2 sentences within the failing response are considered gibberish.**
 
 ## API Reference
 

validator/main.py

@@ -105,7 +105,7 @@ def validate_each_sentence(
             return FailResult(
                 metadata=metadata,
                 error_message=(
-                    f"The following sentences in your response"
+                    f"The following sentences in your response "
                     "were found to be gibberish:\n"
                     f"\n{unsupported_sentences}"
                 ),