notebook tweaks

Author: johnnygreco

docs/notebook_source/1-the-basics.py

@@ -314,7 +314,7 @@
 #
 
 # %%
-results = data_designer.create(config_builder, num_records=10)
+results = data_designer.create(config_builder, num_records=10, dataset_name="tutorial-1")
 
 # %%
 # Load the generated dataset as a pandas DataFrame.

docs/notebook_source/2-structured-outputs-and-jinja-expressions.py

@@ -52,7 +52,7 @@
 #
 
 # %%
-data_designer_client = DataDesigner()
+data_designer = DataDesigner()
 
 # %% [markdown]
 # ### 🎛️ Define model configurations
@@ -327,7 +327,7 @@ class ProductReview(BaseModel):
 #
 
 # %%
-preview = data_designer_client.preview(config_builder, num_records=2)
+preview = data_designer.preview(config_builder, num_records=2)
 
 # %%
 # Run this cell multiple times to cycle through the 2 preview records.
@@ -358,17 +358,17 @@ class ProductReview(BaseModel):
 #
 
 # %%
-job_results = data_designer_client.create(config_builder, num_records=10)
+results = data_designer.create(config_builder, num_records=10, dataset_name="tutorial-2")
 
 # %%
 # Load the generated dataset as a pandas DataFrame.
-dataset = job_results.load_dataset()
+dataset = results.load_dataset()
 
 dataset.head()
 
 # %%
 # Load the analysis results into memory.
-analysis = job_results.load_analysis()
+analysis = results.load_analysis()
 
 analysis.to_report()
 

docs/notebook_source/3-seeding-with-a-dataset.py

@@ -34,7 +34,6 @@
     DataDesigner,
     DataDesignerConfigBuilder,
     ModelConfig,
-    SeedConfig,
 )
 
 # %% [markdown]
@@ -46,7 +45,7 @@
 #
 
 # %%
-data_designer_client = DataDesigner()
+data_designer = DataDesigner()
 
 # %% [markdown]
 # ### 🎛️ Define model configurations
@@ -122,12 +121,12 @@
 import urllib.request
 
 url = "https://raw.githubusercontent.com/NVIDIA/GenerativeAIExamples/refs/heads/main/nemo/NeMo-Data-Designer/data/gretelai_symptom_to_diagnosis.csv"
-local_filename, headers = urllib.request.urlretrieve(url, "gretelai_symptom_to_diagnosis.csv")
+local_filename, _ = urllib.request.urlretrieve(url, "gretelai_symptom_to_diagnosis.csv")
 
-seed_dataset = SeedConfig(dataset=local_filename)
+# Seed datasets are passed as reference objects to the config builder.
+seed_dataset_reference = data_designer.make_seed_reference_from_file(local_filename)
 
-# Pass the reference to the config builder for use during generation.
-config_builder.with_seed_dataset(seed_dataset)
+config_builder.with_seed_dataset(seed_dataset_reference)
 
 # %% [markdown]
 # ## 🎨 Designing our synthetic patient notes dataset
@@ -238,7 +237,7 @@
 #
 
 # %%
-preview = data_designer_client.preview(config_builder, num_records=2)
+preview = data_designer.preview(config_builder, num_records=2)
 
 # %%
 # Run this cell multiple times to cycle through the 2 preview records.
@@ -269,17 +268,17 @@
 #
 
 # %%
-job_results = data_designer_client.create(config_builder, num_records=10)
+results = data_designer.create(config_builder, num_records=10, dataset_name="tutorial-3")
 
 # %%
 # Load the generated dataset as a pandas DataFrame.
-dataset = job_results.load_dataset()
+dataset = results.load_dataset()
 
 dataset.head()
 
 # %%
 # Load the analysis results into memory.
-analysis = job_results.load_analysis()
+analysis = results.load_analysis()
 
 analysis.to_report()
 

docs/notebook_source/4-providing-images-as-context.py

@@ -286,7 +286,7 @@ def convert_image_to_chat_format(record, height: int) -> dict:
 #
 
 # %%
-results = data_designer.create(config_builder, num_records=10)
+results = data_designer.create(config_builder, num_records=10, dataset_name="tutorial-4")
 
 # %%
 # Load the generated dataset as a pandas DataFrame.