fix docs

Author: penguine-ip

b.py

@@ -21,7 +21,7 @@ Here's what an unsafe input would look like in the context of a cybersecurity br
 Since `TopicalGuard` is a input guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import CybersecurityGuard
+from deepeval.guardrails import Guardrails, CybersecurityGuard
 from deepeval.guardrails.cybersecurity_guard import (
     CyberattackCategory
 )

d.py

@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of graphic content:
 Since `GraphicContentGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import GraphicContentGuard
+from deepeval.guardrails import Guardrails, GraphicContentGuard
 
 guardrails = Guardrails(guards=[GraphicContentGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-cybersecurity.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of graphic content:
 Since `HallucinationGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import HallucinationGuard
+from deepeval.guardrails import Guardrails, HallucinationGuard
 
 guardrails = Guardrails(guards=[HallucinationGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-graphic-content.mdx

@@ -1,7 +1,7 @@
 ---
 id: confident-ai-guardrails-illegal
-title: Illegal Guard
-sidebar_label: Illegal Guard
+title: Illegal Activity Guard
+sidebar_label: Illegal Activity Guard
 ---
 
 The **Illegal Activity Guard** is an output guard that analyzes the output generated by your LLM application to detect any content that promotes or describes illegal or unethical activities, ensuring all outputs comply with legal and ethical standards.
@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of illegal activity:
 Since `IllegalActivityGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import IllegalActivityGuard
+from deepeval.guardrails import Guardrails, IllegalActivityGuard
 
 guardrails = Guardrails(guards=[IllegalActivityGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-hallucination.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe input would look like in the context of jailbreaking:
 Since `JailbreakingGuardGuard` is a input guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import JailbreakingGuardGuard
+from deepeval.guardrails import Guardrails, JailbreakingGuardGuard
 
 guardrails = Guardrails(guards=[JailbreakingGuardGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-illegal.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of modernization:
 Since `SyntaxGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import SyntaxGuard
+from deepeval.guardrails import Guardrails, SyntaxGuard
 
 guardrails = Guardrails(guards=[SyntaxGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-jailbreaking.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe input would look like in the context of privacy:
 Since `PrivacyGuard` is a input guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import PrivacyGuard
+from deepeval.guardrails import Guardrails, PrivacyGuard
 
 guardrails = Guardrails(guards=[PrivacyGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-modernization.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe input would look like in the context of prompt injection:
 Since `PromptInjectionGuard` is a input guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import PromptInjectionGuard
+from deepeval.guardrails import Guardrails, PromptInjectionGuard
 
 guardrails = Guardrails(guards=[PromptInjectionGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-privacy.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of incorrect syntax:
 Since `SyntaxGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import SyntaxGuard
+from deepeval.guardrails import Guardrails, SyntaxGuard
 
 guardrails = Guardrails(guards=[SyntaxGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-prompt-injection.mdx

@@ -56,7 +56,7 @@ print(guard_result.breached, guard_result.guard_data)
 ## Example
 
 ```python
-from deepeval.guardrails import TopicalGuard
+from deepeval.guardrails import Guardrails, TopicalGuard
 
 allowed_topics = ["technology", "science", "health"]
 user_input = "Can you tell me about the latest advancements in quantum computing?"

docs/confident-ai/confident-ai-guardrails-syntax.mdx

@@ -21,7 +21,7 @@ Here's what an unsafe output would look like in the context of toxicity:
 Since `ToxicityGuard` is an output guard, simply provide it as a guard in the list of `guards` when initializing a `Guardrails` object:
 
 ```python
-from deepeval.guardrails import ToxicityGuard
+from deepeval.guardrails import Guardrails, ToxicityGuard
 
 guardrails = Guardrails(guards=[ToxicityGuard()])
 ```

docs/confident-ai/confident-ai-guardrails-topical.mdx

@@ -25,17 +25,17 @@ To use the `ToolCorrectnessMetric`, you'll have to provide the following argumen
 
 ```python
 from deepeval.metrics import ToolCorrectnessMetric
-from deepeval.test_case import LLMTestCase, ToolCallParams, ToolCall
+from deepeval.test_case import LLMTestCase, ToolCall
 
 test_case = LLMTestCase(
     input="What if these shoes don't fit?",
     actual_output="We offer a 30-day full refund at no extra cost.",
     # Replace this with the tools that was actually used by your LLM agent
     tools_called=[ToolCall(name="WebSearch"), ToolCall(name="ToolQuery")],
-    expected_tools=[ToolCall(name="WebSearch")]
+    expected_tools=[ToolCall(name="WebSearch")],
 )
 
-metric = ToolCorrectnessMetric(evaluation_param=ToolCallParams.TOOL)
+metric = ToolCorrectnessMetric()
 metric.measure(test_case)
 print(metric.score)
 print(metric.reason)
@@ -44,7 +44,7 @@ print(metric.reason)
 There are seven optional parameters when creating a `ToolCorrectnessMetric`:
 
 - [Optional] `threshold`: a float representing the minimum passing threshold, defaulted to 0.5.
-  [Optional] `evaluation_params`: A list of `ToolCallParams` indicating the strictness of the correctness criteria. For example, supplying a list containing `ToolCallParams.NAME` and `ToolCallParams.INPUT_PARAMETERS`, but excluding `ToolCallParams.OUTPUT`, will consider a tool correct if the tool name and input parameters match, even if the output does not. Defaults to a list with one element: `[ToolCallParams.NAME]`.
+  [Optional] `evaluation_params`: A list of `ToolCallParams` indicating the strictness of the correctness criteria, available options are `ToolCallParams.INPUT_PARAMETERS` and `ToolCallParams.OUTPUT`. For example, supplying a list containing `ToolCallParams.INPUT_PARAMETERS` but excluding `ToolCallParams.OUTPUT`, will deem a tool correct if the tool name and input parameters match, even if the output does not. Defaults to a an empty list.
 - [Optional] `include_reason`: a boolean which when set to `True`, will include a reason for its evaluation score. Defaulted to `True`.
 - [Optional] `strict_mode`: a boolean which when set to `True`, enforces a binary metric score: 1 for perfection, 0 otherwise. It also overrides the current threshold and sets it to 1. Defaulted to `False`.
 - [Optional] `verbose_mode`: a boolean which when set to `True`, prints the intermediate steps used to calculate said metric to the console, as outlined in the [How Is It Calculated](#how-is-it-calculated) section. Defaulted to `False`.