Default Values

app.py

@@ -28,8 +28,6 @@ def generate_synthetic_dataset(
     temperature,
     top_p,
     max_tokens,
-    api_base,
-    api_key,
     dataset_type,
     topic,
     domains,
@@ -48,8 +46,6 @@ def generate_synthetic_dataset(
         temperature (float): The temperature for the LLM.
         top_p (float): The top_p value for the LLM.
         max_tokens (int): The maximum number of tokens for the LLM.
-        api_base (str): The API base URL.
-        api_key (str): The API key.
         dataset_type (str): The type of dataset to generate.
         topic (str): The topic of the dataset.
         domains (str): The domains for the dataset.
@@ -86,22 +82,13 @@ def generate_synthetic_dataset(
     ):
         return "All fields except API Base and API Key must be filled."
 
-    if api_base and api_key:
-        llm_config = LLMConfig(
-            model=llm_model,
-            temperature=temperature,
-            top_p=top_p,
-            max_tokens=max_tokens,
-            api_base=api_base,
-            api_key=api_key,
-        )
-    else:
-        llm_config = LLMConfig(
-            model=llm_model,
-            temperature=temperature,
-            top_p=top_p,
-            max_tokens=max_tokens,
-        )
+
+    llm_config = LLMConfig(
+        model=llm_model,
+        temperature=temperature,
+        top_p=top_p,
+        max_tokens=max_tokens,
+    )
 
     dataset_config = DatasetConfig(
         topic=topic,
@@ -168,7 +155,7 @@ def ui_main():
 
         with gr.Row():
             llm_model = gr.Textbox(
-                label="LLM Model", placeholder="model_provider/model_name"
+                label="LLM Model", placeholder="model_provider/model_name", value="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct"
             )
             temperature = gr.Slider(
                 label="Temperature", minimum=0.0, maximum=1.0, step=0.1, value=0.5
@@ -177,10 +164,6 @@ def ui_main():
                 label="Top P", minimum=0.0, maximum=1.0, step=0.1, value=0.9
             )
             max_tokens = gr.Number(label="Max Tokens", value=2048)
-            api_base = gr.Textbox(label="API Base", placeholder="API Base - Optional")
-            api_key = gr.Textbox(
-                label="API Key", placeholder="Your API Key - Optional", type="password"
-            )
 
         with gr.Row():
             dataset_type = gr.Dropdown(
@@ -194,15 +177,15 @@ def ui_main():
                     "Text Classification",
                 ],
             )
-            topic = gr.Textbox(label="Topic", placeholder="Dataset topic")
-            domains = gr.Textbox(label="Domains", placeholder="Comma-separated domains")
+            topic = gr.Textbox(label="Topic", placeholder="Dataset topic", value="Artificial Intelligence")
+            domains = gr.Textbox(label="Domains", placeholder="Comma-separated domains", value="Machine Learning, Deep Learning")
             language = gr.Textbox(
                 label="Language", placeholder="Language", value="English"
             )
             additional_description = gr.Textbox(
                 label="Additional Description",
                 placeholder="Additional description",
-                value="",
+                value="This dataset must be more focused on healthcare implementations of AI, Machine Learning, and Deep Learning.",
             )
             num_entries = gr.Number(label="Number of Entries", value=1000)
 
@@ -211,17 +194,17 @@ def ui_main():
                 label="Hugging Face Token",
                 placeholder="Your HF Token",
                 type="password",
-                value=None,
+                value="hf_1234566789912345677889",
             )
             hf_repo_name = gr.Textbox(
                 label="Hugging Face Repo Name",
                 placeholder="organization_or_user_name/dataset_name",
-                value=None,
+                value="shekswess/synthgenai-dataset",
             )
             llm_env_vars = gr.Textbox(
                 label="LLM Environment Variables",
                 placeholder="Comma-separated environment variables (e.g., KEY1=VALUE1, KEY2=VALUE2)",
-                value=None,
+                value="HUGGINGFACE_API_KEY=hf_1234566789912345677889",
             )
 
         generate_button = gr.Button("Generate Dataset")
@@ -234,8 +217,6 @@ def ui_main():
                 temperature,
                 top_p,
                 max_tokens,
-                api_base,
-                api_key,
                 dataset_type,
                 topic,
                 domains,