From ff36bd459f5db65a8d3ae6aec377e5efe28894ed Mon Sep 17 00:00:00 2001
From: Roger Yang <roger.yang@arize.com>
Date: Thu, 15 Feb 2024 17:10:47 -0800
Subject: [PATCH] docs: update markdownss for px.Client().log_evaluations()

---
 docs/how-to/define-your-schema/llm-evaluations.md   | 8 ++++----
 docs/llm-evals/quickstart-retrieval-evals/README.md | 4 ++--
 docs/quickstart/evals.md                            | 4 ++--
 docs/use-cases/rag-evaluation.md                    | 4 ++--
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/docs/how-to/define-your-schema/llm-evaluations.md b/docs/how-to/define-your-schema/llm-evaluations.md
index c73d3cd8462..ed281f5bbb4 100644
--- a/docs/how-to/define-your-schema/llm-evaluations.md
+++ b/docs/how-to/define-your-schema/llm-evaluations.md
@@ -24,7 +24,7 @@ The evaluations dataframe can be sent to Phoenix as follows. Note that the name
 ```python
 from phoenix.trace import SpanEvaluations
 
-px.log_evaluations(
+px.Client().log_evaluations(
     SpanEvaluations(
         dataframe=qa_correctness_eval_df,
         eval_name="Q&A Correctness",
@@ -43,7 +43,7 @@ The evaluations dataframe can be sent to Phoenix as follows. Note that the name
 ```python
 from phoenix.trace import DocumentEvaluations
 
-px.log_evaluations(
+px.Client().log_evaluations(
     DocumentEvaluations(
         dataframe=document_relevance_eval_df,
         eval_name="Relevance",
@@ -53,10 +53,10 @@ px.log_evaluations(
 
 ## Logging Multiple Evaluation DataFrames
 
-Multiple evaluation datasets can be logged by the same `px.log_evaluations()` function call.
+Multiple evaluation datasets can be logged by the same `px.Client().log_evaluations()` function call.
 
 ```
-px.log_evaluations(
+px.Client().log_evaluations(
     SpanEvaluations(
         dataframe=qa_correctness_eval_df,
         eval_name="Q&A Correctness",
diff --git a/docs/llm-evals/quickstart-retrieval-evals/README.md b/docs/llm-evals/quickstart-retrieval-evals/README.md
index 89ec4cfb07a..64f027c86ac 100644
--- a/docs/llm-evals/quickstart-retrieval-evals/README.md
+++ b/docs/llm-evals/quickstart-retrieval-evals/README.md
@@ -62,7 +62,7 @@ qa_correctness_eval["score"] = (
 ).astype(int)
 
 # Logs the Evaluations back to the Phoenix User Interface (Optional)
-px.log_evaluations(
+px.Client().log_evaluations(
   SpanEvaluations(eval_name="Hallucination", dataframe=hallucination_eval),
   SpanEvaluations(eval_name="QA Correctness", dataframe=qa_correctness_eval),
 )
@@ -100,7 +100,7 @@ retrieved_documents_eval["score"] = (
     retrieved_documents_eval.label[~retrieved_documents_eval.label.isna()] == "relevant"
 ).astype(int)
 
-px.log_evaluations(DocumentEvaluations(eval_name="Relevance", dataframe=retrieved_documents_eval))
+px.Client().log_evaluations(DocumentEvaluations(eval_name="Relevance", dataframe=retrieved_documents_eval))
 
 ```
 
diff --git a/docs/quickstart/evals.md b/docs/quickstart/evals.md
index 2f8d5a1d77c..4fd74d61984 100644
--- a/docs/quickstart/evals.md
+++ b/docs/quickstart/evals.md
@@ -117,11 +117,11 @@ Log your evaluations to your running Phoenix session.
 ```python
 from phoenix.trace import DocumentEvaluations, SpanEvaluations
 
-px.log_evaluations(
+px.Client().log_evaluations(
     SpanEvaluations(eval_name="Hallucination", dataframe=hallucination_eval_df),
     SpanEvaluations(eval_name="QA Correctness", dataframe=qa_correctness_eval_df),
+    DocumentEvaluations(eval_name="Relevance", dataframe=relevance_eval_df),
 )
-px.log_evaluations(DocumentEvaluations(eval_name="Relevance", dataframe=relevance_eval_df))
 ```
 
 Your evaluations should now appear as annotations on your spans in Phoenix!
diff --git a/docs/use-cases/rag-evaluation.md b/docs/use-cases/rag-evaluation.md
index 3e4b00df23b..80d5243e23c 100644
--- a/docs/use-cases/rag-evaluation.md
+++ b/docs/use-cases/rag-evaluation.md
@@ -500,7 +500,7 @@ We have now evaluated our RAG system's retrieval performance. Let's send these e
 ```python
 from phoenix.trace import DocumentEvaluations, SpanEvaluations
 
-px.log_evaluations(
+px.Client().log_evaluations(
     SpanEvaluations(dataframe=ndcg_at_2, eval_name="ndcg@2"),
     SpanEvaluations(dataframe=precision_at_2, eval_name="precision@2"),
     DocumentEvaluations(dataframe=retrieved_documents_relevance_df, eval_name="relevance"),
@@ -578,7 +578,7 @@ Since we have evaluated our RAG system's QA performance and Hallucinations perfo
 ```python
 from phoenix.trace import SpanEvaluations
 
-px.log_evaluations(
+px.Client().log_evaluations(
     SpanEvaluations(dataframe=qa_correctness_eval_df, eval_name="Q&A Correctness"),
     SpanEvaluations(dataframe=hallucination_eval_df, eval_name="Hallucination"),
 )