remove obsolete code

.python-version

@@ -1 +0,0 @@
-synthetic-data-generator

app.py

@@ -1,4 +1,9 @@
+import os
+
 from distilabel_dataset_generator.app import demo
 
+os.environ["API_KEY"] = "hf_..."
+os.environ["API_KEY"] = "hf_..."
+
 if __name__ == "__main__":
     demo.launch()

src/distilabel_dataset_generator/apps/base.py

@@ -1,6 +1,6 @@
 import io
 import uuid
-from typing import Any, Callable, List, Tuple, Union
+from typing import List, Union
 
 import argilla as rg
 import gradio as gr
@@ -11,161 +11,14 @@ from gradio import OAuthToken
 from huggingface_hub import HfApi, upload_file
 
 from distilabel_dataset_generator.utils import (
-    _LOGGED_OUT_CSS,
     get_argilla_client,
-    get_login_button,
     list_orgs,
-    swap_visibility,
 )
 
 TEXTCAT_TASK = "text_classification"
 SFT_TASK = "supervised_fine_tuning"
 
 
-def get_main_ui(
-    default_dataset_descriptions: List[str],
-    default_system_prompts: List[str],
-    default_datasets: List[pd.DataFrame],
-    fn_generate_system_prompt: Callable,
-    fn_generate_dataset: Callable,
-    task: str,
-):
-    def fn_generate_sample_dataset(system_prompt, progress=gr.Progress()):
-        if system_prompt in default_system_prompts:
-            index = default_system_prompts.index(system_prompt)
-            if index < len(default_datasets):
-                return default_datasets[index]
-        if task == TEXTCAT_TASK:
-            result = fn_generate_dataset(
-                system_prompt=system_prompt,
-                difficulty="high school",
-                clarity="clear",
-                labels=[],
-                num_labels=1,
-                num_rows=1,
-                progress=progress,
-                is_sample=True,
-            )
-        else:
-            result = fn_generate_dataset(
-                system_prompt=system_prompt,
-                num_turns=1,
-                num_rows=1,
-                progress=progress,
-                is_sample=True,
-            )
-        return result
-
-    with gr.Blocks(
-        title="🧬 Synthetic Data Generator",
-        head="🧬 Synthetic Data Generator",
-        css=_LOGGED_OUT_CSS,
-    ) as app:
-        with gr.Row():
-            gr.HTML(
-                """<details style='display: inline-block;'><summary><h2 style='display: inline;'>How does it work?</h2></summary><img src='https://huggingface.co/spaces/argilla/synthetic-data-generator/resolve/main/assets/flow.png' width='100%' style='margin: 0 auto; display: block;'></details>"""
-            )
-        with gr.Row():
-            gr.Markdown(
-                "Want to run this locally or with other LLMs? Take a look at the FAQ tab. distilabel Synthetic Data Generator is free, we use the authentication token to push the dataset to the Hugging Face Hub and not for data generation."
-            )
-        with gr.Row():
-            gr.Column()
-            get_login_button()
-            gr.Column()
-
-        gr.Markdown("## Iterate on a sample dataset")
-        with gr.Column() as main_ui:
-            (
-                dataset_description,
-                examples,
-                btn_generate_system_prompt,
-                system_prompt,
-                sample_dataset,
-                btn_generate_sample_dataset,
-            ) = get_iterate_on_sample_dataset_ui(
-                default_dataset_descriptions=default_dataset_descriptions,
-                default_system_prompts=default_system_prompts,
-                default_datasets=default_datasets,
-                task=task,
-            )
-            gr.Markdown("## Generate full dataset")
-            gr.Markdown(
-                "Once you're satisfied with the sample, generate a larger dataset and push it to Argilla or the Hugging Face Hub."
-            )
-            with gr.Row(variant="panel") as custom_input_ui:
-                pass
-
-            (
-                dataset_name,
-                add_to_existing_dataset,
-                btn_generate_full_dataset_argilla,
-                btn_generate_and_push_to_argilla,
-                btn_push_to_argilla,
-                org_name,
-                repo_name,
-                private,
-                btn_generate_full_dataset,
-                btn_generate_and_push_to_hub,
-                btn_push_to_hub,
-                final_dataset,
-                success_message,
-            ) = get_push_to_ui(default_datasets)
-
-        sample_dataset.change(
-            fn=lambda x: x,
-            inputs=[sample_dataset],
-            outputs=[final_dataset],
-        )
-
-        btn_generate_system_prompt.click(
-            fn=fn_generate_system_prompt,
-            inputs=[dataset_description],
-            outputs=[system_prompt],
-            show_progress=True,
-        ).then(
-            fn=fn_generate_sample_dataset,
-            inputs=[system_prompt],
-            outputs=[sample_dataset],
-            show_progress=True,
-        )
-
-        btn_generate_sample_dataset.click(
-            fn=fn_generate_sample_dataset,
-            inputs=[system_prompt],
-            outputs=[sample_dataset],
-            show_progress=True,
-        )
-
-        app.load(fn=swap_visibility, outputs=main_ui)
-        app.load(get_org_dropdown, outputs=[org_name])
-
-    return (
-        app,
-        main_ui,
-        custom_input_ui,
-        dataset_description,
-        examples,
-        btn_generate_system_prompt,
-        system_prompt,
-        sample_dataset,
-        btn_generate_sample_dataset,
-        dataset_name,
-        add_to_existing_dataset,
-        btn_generate_full_dataset_argilla,
-        btn_generate_and_push_to_argilla,
-        btn_push_to_argilla,
-        org_name,
-        repo_name,
-        private,
-        btn_generate_full_dataset,
-        btn_generate_and_push_to_hub,
-        btn_push_to_hub,
-        final_dataset,
-        success_message,
-    )
-
-
 def validate_argilla_user_workspace_dataset(
     dataset_name: str,
     add_to_existing_dataset: bool = True,
@@ -205,176 +58,6 @@ def get_org_dropdown(oauth_token: Union[OAuthToken, None]):
     )
 
 
-def get_push_to_ui(default_datasets):
-    with gr.Column() as push_to_ui:
-        (
-            dataset_name,
-            add_to_existing_dataset,
-            btn_generate_full_dataset_argilla,
-            btn_generate_and_push_to_argilla,
-            btn_push_to_argilla,
-        ) = get_argilla_tab()
-        (
-            org_name,
-            repo_name,
-            private,
-            btn_generate_full_dataset,
-            btn_generate_and_push_to_hub,
-            btn_push_to_hub,
-        ) = get_hf_tab()
-        final_dataset = get_final_dataset_row(default_datasets)
-        success_message = get_success_message_row()
-    return (
-        dataset_name,
-        add_to_existing_dataset,
-        btn_generate_full_dataset_argilla,
-        btn_generate_and_push_to_argilla,
-        btn_push_to_argilla,
-        org_name,
-        repo_name,
-        private,
-        btn_generate_full_dataset,
-        btn_generate_and_push_to_hub,
-        btn_push_to_hub,
-        final_dataset,
-        success_message,
-    )
-
-
-def get_iterate_on_sample_dataset_ui(
-    default_dataset_descriptions: List[str],
-    default_system_prompts: List[str],
-    default_datasets: List[pd.DataFrame],
-    task: str,
-):
-    with gr.Column():
-        dataset_description = gr.TextArea(
-            label="Give a precise description of your desired application. Check the examples for inspiration.",
-            value=default_dataset_descriptions[0],
-            lines=2,
-        )
-        examples = gr.Examples(
-            elem_id="system_prompt_examples",
-            examples=[[example] for example in default_dataset_descriptions],
-            inputs=[dataset_description],
-        )
-        with gr.Row():
-            gr.Column(scale=1)
-            btn_generate_system_prompt = gr.Button(
-                value="Generate system prompt and sample dataset", variant="primary"
-            )
-            gr.Column(scale=1)
-
-        system_prompt = gr.TextArea(
-            label="System prompt for dataset generation. You can tune it and regenerate the sample.",
-            value=default_system_prompts[0],
-            lines=2 if task == TEXTCAT_TASK else 5,
-        )
-
-        with gr.Row():
-            sample_dataset = gr.Dataframe(
-                value=default_datasets[0],
-                label=(
-                    "Sample dataset. Text truncated to 256 tokens."
-                    if task == TEXTCAT_TASK
-                    else "Sample dataset. Prompts and completions truncated to 256 tokens."
-                ),
-                interactive=False,
-                wrap=True,
-            )
-
-        with gr.Row():
-            gr.Column(scale=1)
-            btn_generate_sample_dataset = gr.Button(
-                value="Generate sample dataset", variant="primary"
-            )
-            gr.Column(scale=1)
-
-    return (
-        dataset_description,
-        examples,
-        btn_generate_system_prompt,
-        system_prompt,
-        sample_dataset,
-        btn_generate_sample_dataset,
-    )
-
-
-def get_argilla_tab() -> Tuple[Any]:
-    with gr.Tab(label="Argilla"):
-        if get_argilla_client() is not None:
-            with gr.Row(variant="panel"):
-                dataset_name = gr.Textbox(
-                    label="Dataset name",
-                    placeholder="dataset_name",
-                    value="my-distiset",
-                )
-                add_to_existing_dataset = gr.Checkbox(
-                    label="Allow adding records to existing dataset",
-                    info="When selected, you do need to ensure the dataset options are the same as in the existing dataset.",
-                    value=False,
-                    interactive=True,
-                    scale=1,
-                )
-
-            with gr.Row(variant="panel"):
-                btn_generate_full_dataset_argilla = gr.Button(
-                    value="Generate", variant="primary", scale=2
-                )
-                btn_generate_and_push_to_argilla = gr.Button(
-                    value="Generate and Push to Argilla",
-                    variant="primary",
-                    scale=2,
-                )
-                btn_push_to_argilla = gr.Button(
-                    value="Push to Argilla", variant="primary", scale=2
-                )
-        else:
-            gr.Markdown(
-                "Please add `ARGILLA_API_URL` and `ARGILLA_API_KEY` to use Argilla or export the dataset to the Hugging Face Hub."
-            )
-    return (
-        dataset_name,
-        add_to_existing_dataset,
-        btn_generate_full_dataset_argilla,
-        btn_generate_and_push_to_argilla,
-        btn_push_to_argilla,
-    )
-
-
-def get_hf_tab() -> Tuple[Any]:
-    with gr.Tab("Hugging Face Hub"):
-        with gr.Row(variant="panel"):
-            org_name = get_org_dropdown()
-            repo_name = gr.Textbox(
-                label="Repo name",
-                placeholder="dataset_name",
-                value="my-distiset",
-            )
-            private = gr.Checkbox(
-                label="Private dataset",
-                value=True,
-                interactive=True,
-                scale=1,
-            )
-        with gr.Row(variant="panel"):
-            btn_generate_full_dataset = gr.Button(
-                value="Generate", variant="primary", scale=2
-            )
-            btn_generate_and_push_to_hub = gr.Button(
-                value="Generate and Push to Hub", variant="primary", scale=2
-            )
-            btn_push_to_hub = gr.Button(value="Push to Hub", variant="primary", scale=2)
-    return (
-        org_name,
-        repo_name,
-        private,
-        btn_generate_full_dataset,
-        btn_generate_and_push_to_hub,
-        btn_push_to_hub,
-    )
-
-
 def push_pipeline_code_to_hub(
     pipeline_code: str,
     org_name: str,
@@ -455,24 +138,6 @@ def validate_push_to_hub(org_name, repo_name):
     return repo_id
 
 
-def get_final_dataset_row(default_datasets) -> gr.Dataframe:
-    with gr.Row():
-        final_dataset = gr.Dataframe(
-            value=default_datasets[0],
-            label="Generated dataset",
-            interactive=False,
-            wrap=True,
-            min_width=300,
-        )
-    return final_dataset
-
-
-def get_success_message_row() -> gr.Markdown:
-    with gr.Row():
-        success_message = gr.Markdown(visible=False)
-    return success_message
-
-
 def show_success_message(org_name, repo_name) -> gr.Markdown:
     client = get_argilla_client()
     if client is None:

src/distilabel_dataset_generator/apps/sft.py

@@ -28,7 +28,6 @@ from distilabel_dataset_generator.pipelines.sft import (
     get_response_generator,
 )
 from distilabel_dataset_generator.utils import (
-    _LOGGED_OUT_CSS,
     get_argilla_client,
     get_org_dropdown,
     swap_visibility,
@@ -350,7 +349,7 @@ def hide_pipeline_code_visibility():
 ######################
 
 
-with gr.Blocks(css=_LOGGED_OUT_CSS) as app:
+with gr.Blocks() as app:
     with gr.Column() as main_ui:
         if not SFT_AVAILABLE:
             gr.Markdown(

src/distilabel_dataset_generator/apps/textcat.py

@@ -28,7 +28,6 @@ from src.distilabel_dataset_generator.pipelines.textcat import (
     get_textcat_generator,
 )
 from src.distilabel_dataset_generator.utils import (
-    _LOGGED_OUT_CSS,
     get_argilla_client,
     get_org_dropdown,
     get_preprocess_labels,
@@ -332,7 +331,7 @@ def hide_pipeline_code_visibility():
 ######################
 
 
-with gr.Blocks(css=_LOGGED_OUT_CSS) as app:
+with gr.Blocks() as app:
     with gr.Column() as main_ui:
         gr.Markdown("## 1. Describe the dataset you want")
         with gr.Row():

src/distilabel_dataset_generator/utils.py

@@ -6,10 +6,7 @@ import gradio as gr
 import numpy as np
 import pandas as pd
 from gradio.oauth import (
-    OAUTH_CLIENT_ID,
-    OAUTH_CLIENT_SECRET,
-    OAUTH_SCOPES,
-    OPENID_PROVIDER_URL,
+    OAuthToken,
     get_space,
 )
 from huggingface_hub import whoami
@@ -17,30 +14,6 @@ from jinja2 import Environment, meta
 
 from distilabel_dataset_generator.constants import argilla_client
 
-_LOGGED_OUT_CSS = ".main_ui_logged_out{opacity: 0.3; pointer-events: none}"
-
-
-_CHECK_IF_SPACE_IS_SET = (
-    all(
-        [
-            OAUTH_CLIENT_ID,
-            OAUTH_CLIENT_SECRET,
-            OAUTH_SCOPES,
-            OPENID_PROVIDER_URL,
-        ]
-    )
-    or get_space() is None
-)
-
-if _CHECK_IF_SPACE_IS_SET:
-    from gradio.oauth import OAuthToken
-else:
-    OAuthToken = str
-
-
-def get_login_button():
-    return gr.LoginButton(value="Sign in!", size="sm", scale=2).activate()
-
 
 def get_duplicate_button():
     if get_space() is not None:
@@ -85,13 +58,6 @@ def get_org_dropdown(oauth_token: Union[OAuthToken, None] = None):
     )
 
 
-def get_token(oauth_token: Union[OAuthToken, None]):
-    if oauth_token:
-        return oauth_token.token
-    else:
-        return ""
-
-
 def swap_visibility(oauth_token: Union[OAuthToken, None]):
     if oauth_token:
         return gr.update(elem_classes=["main_ui_logged_in"])
@@ -99,28 +65,6 @@ def swap_visibility(oauth_token: Union[OAuthToken, None]):
         return gr.update(elem_classes=["main_ui_logged_out"])
 
 
-def get_base_app():
-    with gr.Blocks(
-        title="🧬 Synthetic Data Generator",
-        head="🧬  Synthetic Data Generator",
-        css=_LOGGED_OUT_CSS,
-    ) as app:
-        with gr.Row():
-            gr.Markdown(
-                "Want to run this locally or with other LLMs? Take a look at the FAQ tab. distilabel Synthetic Data Generator is free, we use the authentication token to push the dataset to the Hugging Face Hub and not for data generation."
-            )
-        with gr.Row():
-            gr.Column()
-            get_login_button()
-            gr.Column()
-
-        gr.Markdown("## Iterate on a sample dataset")
-        with gr.Column() as main_ui:
-            pass
-
-    return app
-
-
 def get_argilla_client() -> Union[rg.Argilla, None]:
     return argilla_client