Update readme

README.md

@@ -4,7 +4,7 @@
 | --- | --- |
 | Date of development | Feb 15, 2024 |
 | Validator type | Format |
-| Blog |  |
+| Blog | - |
 | License | Apache 2 |
 | Input/Output | Output |
 
@@ -16,10 +16,13 @@ Scans LLM outputs for strings that could cause browser script execution downstre
 
 Use this validator when you are passing the results of your LLM requests directly to a browser or other html-executable environment. It's a good idea to also implement other XSS and code injection prevention techniques.
 
+## Requirements
+* `bleach`
+
 ## Installation
 
 ```bash
-$ guardrails hub install hub://guardrails/web_sanitization
+guardrails hub install hub://guardrails/web_sanitization
 ```
 
 ## Usage Examples
@@ -30,55 +33,30 @@ In this example, we apply the validator to a string output generated by an LLM.
 
 ```python
 # Import Guard and Validator
-from guardrails.hub import WebSanitization
 from guardrails import Guard
-
-# Initialize Validator
-val = WebSanitization(
-		choices=['cat', 'dog', 'bird'],
-		on_fail="fix"
-)
-
-# Setup Guard
-guard = Guard.from_string(
-    validators=[val, ...],
-)
-
-guard.parse("dog")  # Validator passes
-guard.parse("<script>horse()</script>")  # Validator fails
-```
-
-### Validating JSON output via Python
-
-In this example, we apply the validator to a string field of a JSON output generated by an LLM.
-
-```python
-# Import Guard and Validator
-from pydantic import BaseModel
 from guardrails.hub import WebSanitization
-from guardrails import Guard
 
-val = WebSanitization(
-    on_fail="fix"
+# Use the Guard with the validator
+guard = Guard().use(WebSanitization, on_fail="exception")
+
+# Test passing response
+guard.validate(
+    """MetaAI's Llama2 is the latest in their open-source LLM series. 
+    It is a powerful language model."""
 )
 
-# Create Pydantic BaseModel
-class PetInfo(BaseModel):
-    pet_name: str
-    pet_profile_page: str = Field(
-            description="Generated profile page for pet", validators=[val]
+try:
+    # Test failing response
+    guard.validate(
+        """MetaAI's Llama2 is the latest in their open-source LLM series. 
+        It is a powerful language model. <script>alert('XSS')</script>"""
     )
-
-# Create a Guard to check for valid Pydantic output
-guard = Guard.from_pydantic(output_class=PetInfo)
-
-# Run LLM output generating JSON through guard
-guard.parse("""
-{
-		"pet_name": "Caesar",
-		"pet_profile_page": "# Caesar's page!\n<script>zoom-effect()</script><img src='/caesar.png'/>"
-}
-""")
+except Exception as e:
+    print(e)
+```
+Output:
+```console
+Validation failed for field with errors: The output contains a web injection attack.
 ```
 
 # API Reference
@@ -97,7 +75,7 @@ Initializes a new instance of the WebSanitization validator class.
 
 <br>
 
-**`__call__(self, value, metadata={}) → ValidationOutcome`**
+**`__call__(self, value, metadata={}) → ValidationResult`**
 
 <ul>