rename to chatvertexai and fix hyphenation

Author: dylanbouchard

paper/paper.md

@@ -46,7 +46,7 @@ Furthermore, LangFair is designed for real-world LLM-based systems that require
 
 
 # Generation of Evaluation Datasets
-The `langfair.generator` module offers two classes, `ResponseGenerator` and `CounterfactualGenerator`, which aim to enable user-friendly construction of evaluation datasets for text generation use cases.
+The `langfair.generator` module offers two classes, `ResponseGenerator` and \hyphenateddigits[\unknown]{`CounterfactualGenerator`}, which aim to enable user-friendly construction of evaluation datasets for text generation use cases.
 
 
 ### `ResponseGenerator` class
@@ -90,14 +90,14 @@ When LLMs are used to solve classification problems, traditional machine learnin
 # Semi-Automated Evaluation
 
 ### `AutoEval` class
-To streamline assessments for text generation use cases, the `AutoEval` class conducts a multi-step process (each step is described in detail above) for a comprehensive fairness assessment. Specifically, these steps include metric selection (based on whether FTU is satsified), evaluation dataset generation from user-provided prompts with a user-provided LLM, and computation of applicable fairness metrics. To implement, the user is required to supply a list of prompts and an instance of `langchain` LLM. Below we provide a basic example demonstrating the execution of `AutoEval.evaluate` with a `gemini-pro` instance.^[Note that this example assumes the user has already set up their VertexAI credentials and sampled a list of prompts from their use case prompts.]
+To streamline assessments for text generation use cases, the `AutoEval` class conducts a multi-step process (each step is described in detail above) for a comprehensive fairness assessment. Specifically, these steps include metric selection (based on whether FTU is satsified), evaluation dataset generation from user-provided prompts with a user-provided LLM, and computation of applicable fairness metrics. To implement, the user is required to supply a list of prompts and an instance of a `langchain` LLM. Below we provide a basic example demonstrating the execution of `AutoEval.evaluate` with a `gemini-pro` instance.^[Note that this example assumes the user has already set up their VertexAI credentials and sampled a list of prompts from their use case prompts.]
 
 
 ```python
-from langchain_google_vertexai import VertexAI
+from langchain_google_vertexai import ChatVertexAI
 from langfair.auto import AutoEval
 
-llm = VertexAI(model_name='gemini-pro')
+llm = ChatVertexAI(model_name='gemini-pro')
 auto_object = AutoEval(prompts=prompts, langchain_llm=llm)
 results = await auto_object.evaluate()
 ```