From 78e362268363b87829731611a1c2644f14175b07 Mon Sep 17 00:00:00 2001
From: Jeffrey Ip <jeffreyip@confident-ai.com>
Date: Sun, 24 Nov 2024 11:51:11 +0800
Subject: [PATCH] Updated docs again

---
 deepeval/dataset/dataset.py       |  6 ++----
 docs/docs/evaluation-datasets.mdx | 19 +++++++++++++------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/deepeval/dataset/dataset.py b/deepeval/dataset/dataset.py
index 284b464d..939d5617 100644
--- a/deepeval/dataset/dataset.py
+++ b/deepeval/dataset/dataset.py
@@ -420,9 +420,7 @@ def get_column_data(df: pd.DataFrame, col_name: str, default=None):
                 else [default] * len(df)
             )
 
-        df = pd.read_csv(file_path)
-        # Convert np.nan (default for missing values in pandas) to None for compatibility with Python and Pydantic
-        df = df.astype(object).where(pd.notna(df), None)
+        df = pd.read_csv(file_path).astype(object).where(pd.notna(pd.read_csv(file_path)), None)
 
         inputs = get_column_data(df, input_col_name)
         actual_outputs = get_column_data(df, actual_output_col_name)
@@ -552,7 +550,7 @@ def add_goldens_from_json_file(
                     retrieval_context=retrieval_context,
                     tools_called=tools_called,
                     expected_tools=expected_tools,
-                    source_file=file_path,
+                    source_file=source_file,
                 )
             )
 
diff --git a/docs/docs/evaluation-datasets.mdx b/docs/docs/evaluation-datasets.mdx
index cce8ee4b..5a8bf36e 100644
--- a/docs/docs/evaluation-datasets.mdx
+++ b/docs/docs/evaluation-datasets.mdx
@@ -70,19 +70,26 @@ A `Golden` and `LLMTestCase` contains almost an identical class signature, so te
 
 ## Generate An Evaluation Dataset
 
+:::caution
+We highly recommend you to checkout the [`Synthesizer`](synthesizer-introduction) page to see the customizations available and how data synthesization work in `deepeval`. All methods in an `EvaluationDataset` that can be used to generate goldens uses the `Synthesizer` under the hood and has exactly the same function signature as corresponding methods in the `Synthesizer`.
+:::
+
 `deepeval` offers anyone the ability to easily generate synthetic datasets from documents locally on your machine. This is especially helpful if you don't have an evaluation dataset prepared beforehand.
 
 ```python
 from deepeval.dataset import EvaluationDataset
 
 dataset = EvaluationDataset()
-dataset.generate_goldens_from_docs(
-    document_paths=['example.txt', 'example.docx', 'example.pdf'],
-    max_goldens_per_document=2
-)
+dataset.generate_goldens_from_docs(document_paths=['example.txt', 'example.docx', 'example.pdf'])
 ```
 
-Under the hood, an `EvaluationDataset` generates goldens using to `deepeval`'s `Synthesizer`. You can customize the `Synthesizer` used to generate goldens within an `EvaluationDataset`.
+In this example, we've used the `generate_goldens_from_docs` method, which one one of the three generation methods offered by `deepeval`'s `Synthesizer`. The three methods include:
+
+- [`generate_goldens_from_docs()`](synthesizer-generate-from-docs): useful for generating goldens to evaluate your LLM application based on contexts extracted from your knowledge base in the form of documents.
+- [`generate_goldens_from_contexts()`](synthesizer-generate-from-contexts): useful for generating goldens to evaluate your LLM application based on a list of prepared context.
+- [`generate_goldens_from_scratch()`](synthesizer-generate-from-scratch): useful for generating goldens to evaluate your LLM application without relying on contexts from a knowledge base.
+
+Under the hood, these 3 methods calls the corresponding methods in `deepeval`'s `Synthesizer` with the exact same parameters, with an addition of a `synthesizer` parameter for you to customize your generation pipeline.
 
 ```python
 from deepeval.dataset import EvaluationDataset
@@ -99,7 +106,7 @@ dataset.generate_goldens_from_docs(
 ```
 
 :::info
-`deepeval`'s `Synthesizer` uses a series of evolution techniques to complicate and make generated goldens more realistic to human prepared data. For more information on how `deepeval`'s `Synthesizer` works, visit the [synthesizer section.](evaluation-datasets-synthetic-data)
+`deepeval`'s `Synthesizer` uses a series of evolution techniques to complicate and make generated goldens more realistic to human prepared data. For more information on how `deepeval`'s `Synthesizer` works, visit the [synthesizer section.](synthesizer-introduction#how-does-it-work)
 :::
 
 ## Load an Existing Dataset