Replacing px.Client() in LlamaTrace Code for Remote Connection

from phoenix.evals import (
    HallucinationEvaluator,
    OpenAIModel,
    QAEvaluator,
    RelevanceEvaluator,
    run_evals,
)
from phoenix.session.evaluation import get_qa_with_reference, get_retrieved_documents
from phoenix.trace import DocumentEvaluations, SpanEvaluations
from tqdm import tqdm
import phoenix as px

# Define the evaluation model
eval_model = OpenAIModel(
    azure_endpoint=AZURE_OPENAI_ENDPOINT,
    azure_deployment="gpt-4o",  # I'm using gpt-4o for evaluation
    model=AZURE_OPENAI_CHAT_COMPLETION_DEPLOYED_MODEL_NAME,
    api_key=AZURE_OPENAI_API_KEY,
    api_version="2024-02-01"
)

# Define evaluators
hallucination_evaluator = HallucinationEvaluator(eval_model)
qa_correctness_evaluator = QAEvaluator(eval_model)
relevance_evaluator = RelevanceEvaluator(eval_model)

# List of project names
projects = ["Baseline", "Contextual"]

# Create DataFrames for queries and retrieved documents for each project
queries_dfs = {}
retrieved_documents_dfs = {}

for project in projects:
    queries_dfs[project] = get_qa_with_reference(px.Client(), project_name=project)
    retrieved_documents_dfs[project] = get_retrieved_documents(px.Client(), project_name=project)

# Loop through each project and perform evaluations
for project in projects:
    queries_df = queries_dfs[project]
    retrieved_documents_df = retrieved_documents_dfs[project]
    
    # Run evaluations
    hallucination_eval_df, qa_correctness_eval_df = run_evals(
        dataframe=queries_df,
        evaluators=[hallucination_evaluator, qa_correctness_evaluator],
        provide_explanation=True,
    )
    relevance_eval_df = run_evals(
        dataframe=retrieved_documents_df,
        evaluators=[relevance_evaluator],
        provide_explanation=True,
    )[0]
    
    # Log evaluations
    px.Client().log_evaluations(
        SpanEvaluations(eval_name=f"Hallucination_{project}", dataframe=hallucination_eval_df),
        SpanEvaluations(eval_name=f"QA Correctness_{project}", dataframe=qa_correctness_eval_df),
        DocumentEvaluations(eval_name=f"Relevance_{project}", dataframe=relevance_eval_df),
    )