Updated docs

docs/docs/confident-ai-guardrails.mdx

@@ -17,36 +17,47 @@ Before diving into this content, it might be helpful to read the following:
 
 ## Guarding Live Responses
 
-To begin guarding LLM responses, use the `deepeval.guard(...)` method within your LLM application.
+To begin guarding LLM responses, first create an instance of `deepeval`'s `Guardrails`:
 
 ```python
 import deepeval
-from deepeval.guardrails import Guard
+from deepeval.guardrails import Guardrails, Guard
 
-safety_scores = deepeval.guard(
-    input="Tell me more about the effects of global warming.",
-    response="Global warming is a fake phenomenon and just pseudo-science.",
+guardrails = Guardrails(
     guards=[Guard.HALLUCINATION, Guard.BIAS],
     purpose="Environmental education"
 )
 ```
 
-There are two mandatory and four optional parameters when using the `guard()` function:
+There are four mandatory and four optional parameters when creating a `Guardrails` instance:
 
-- `input`: A string that represents the user query to your LLM application.
-- `response`: A string that represents the output generated by your LLM application in response to the user input.
 - `guards`: A list of `Guard` enums specifying the guards to be used. Defaults to using all available Guards.
 - [Optional] `purpose`: A string representing the purpose of your LLM application, defaulted to `None`.
 - [Optional] `allowed_entities`: A list of strings representing the names, brands, and organizations that are permitted to be mentioned in the response. Defaults to `None`.
 - [Optional] `system_prompt`: A string representing your system prompt. Defaults to `None`.
-- [Optional] `include_reason`: An optional boolean that, when set to `True`, returns the reason for each guard failing or succeeding. Defaults to `False`.
 
-Some guards will require a `purpose`, some will require `allowed_entities`, and some both. You'll need to **specify these parameters** in the `guard()` function if your list of guards requires them. Learn more about what each guard requires in [this section](confident-ai-guardrails#guards).
+Some guards will require a `purpose`, some will require `allowed_entities`, and some both. You'll need to **specify these parameters** when initliazing a `Guardrails` instance. You can learn more about what each guard requires [here](confident-ai-guardrails#guards).
 
 :::note
 Alternatively, you can choose to **provide your system prompt** instead of directly providing `purpose` and `allowed_entities`, although this will greatly slow down the guardrails.
 :::
 
+Finally, use `deepeval`'s `Guardrails`s to guard against undesirable LLM responses:
+
+```python
+...
+
+safety_scores = guardrails.guard(
+    input="Tell me more about the effects of global warming.",
+    response="Global warming is a fake phenomenon and just pseudo-science.",
+)
+```
+
+There are two mandatory optional parameters when using the `guard()` method:
+
+- `input`: A string that represents the user query to your LLM application.
+- `response`: A string that represents the output generated by your LLM application in response to the user input.
+
 ## Interpreting Guardrail Results
 
 Each `Guard` scores your model's response from a scale of 1 to 10. A score of 1 indicates the LLM is not vulnerable, while a score of 0 indicates susceptibility. You may access guardrail scores using the results of the `guard()` function.