update-layout-add-evaluation (#17)

- add comment to divide functions/ui (c2fbbc311616f60f3dbc1e546d20517329b41486)
- fix typo (3ef1fed40b702eb482f9017241a2d3641cde3946)
- move sign in button to another column (ea29202ac74e3b567f8bbc83f2dd01edeb7e00b5)
- make sign in button smaller (3b5e775206b9e2276d8d5afd14d5a2ae6eb0f852)
- remove repeated import (9c1769a069aa5cadade2e120ebbfbb3524b4a71c)
- move sign in button to the right (5d91425bc46bbed12e76279e32eed828738f2e78)
- modify column width and typos (2b5c2e3fa953fcd1e7bbc5d50fa1eaa18cf51a7f)
- update successful message and pipeline code (4234ad816ad254da4dc0a2bdf4f6ee901f3ab647)
- update dataframe visualizations (7350fc6b3cdabd3c88562f7ebea772ea936b293b)
- update text and order parameter layout (45693e1d9d5340197d0a5298329a1b176836e5e9)
- typo (2673ebc69f8b3ee53ca0bea400abe8b18dcec6c7)
- add temperature for system prompt (857f1ba71f10ddb10f045923601746daed130b19)
- update textcat (separate prompt and labels) and use input parameters (4e193106207eda3f59650448038a680c25075972)
- update sft and use input parameters (dea11022bc5c78e08481e4e90bbb73b0402cdadc)
- update push dataset (49d5948eb076fc8b3354a9d4acdaac477fc0c398)
- add evaluation task (34371d30aa99cdb709c9def84739ab3b8b7fa611)
- hide pipeline ui each time it generates (c26510fcff621c6a144917e1a56d5f87dd41fd41)
- move order hide pipeline ui (1b00519115b913bff86a6f2ba061f97eb860e78a)
- merge remote tracking branch (1c412e2113c3889b13572af931a3be19fc93df5a)

app.py

@@ -3,6 +3,7 @@
 from src.distilabel_dataset_generator._tabbedinterface import TabbedInterface
 from src.distilabel_dataset_generator.apps.faq import app as faq_app
 from src.distilabel_dataset_generator.apps.sft import app as sft_app
+from src.distilabel_dataset_generator.apps.eval import app as eval_app
 from src.distilabel_dataset_generator.apps.textcat import app as textcat_app
 
 theme ='argilla/argilla-theme'
@@ -25,12 +26,11 @@
 """
 
 demo = TabbedInterface(
-    [textcat_app, sft_app, faq_app],
-    ["Text Classification", "Supervised Fine-Tuning", "FAQ"],
+    [textcat_app, sft_app, eval_app, faq_app],
+    ["Text Classification", "Supervised Fine-Tuning", "Evaluation", "FAQ"],
     css=css,
     title="""
     <h1>Synthetic Data Generator</h1>
-    <h3>Build datasets using natural language</h3>
     """,
     head="Synthetic Data Generator",
     theme=theme,

pyproject.toml

@@ -6,7 +6,7 @@ authors = [
     {name = "davidberenstein1957", email = "[email protected]"},
 ]
 dependencies = [
-    "distilabel[hf-inference-endpoints,argilla,outlines]>=1.4.1",
+    "distilabel[hf-inference-endpoints,argilla,outlines,instructor]>=1.4.1",
     "gradio[oauth]<5.0.0",
     "transformers>=4.44.2",
     "sentence-transformers>=3.2.0",

src/distilabel_dataset_generator/_tabbedinterface.py

@@ -63,10 +63,12 @@ def __init__(
             if title:
                 HTML(value=title)
                 with gr.Row():
-                    with gr.Column(scale=1):
-                        gr.LoginButton(value="Sign in!", variant="hf-login", size="sm", scale=2)
+                    with gr.Column(scale=2):
+                        gr.Markdown("### Build datasets using natural language")
                     with gr.Column(scale=3):
                         pass
+                    with gr.Column(scale=2):
+                        gr.LoginButton(value="Sign in!", variant="hf-login", size="sm", scale=2)
             with Tabs():
                 for interface, tab_name in zip(interface_list, tab_names, strict=False):
                     with Tab(label=tab_name):

src/distilabel_dataset_generator/apps/base.py

@@ -15,7 +15,7 @@
     get_argilla_client,
     get_login_button,
     list_orgs,
-    swap_visibilty,
+    swap_visibility,
 )
 
 TEXTCAT_TASK = "text_classification"
@@ -137,7 +137,7 @@ def fn_generate_sample_dataset(system_prompt, progress=gr.Progress()):
             show_progress=True,
         )
 
-        app.load(fn=swap_visibilty, outputs=main_ui)
+        app.load(fn=swap_visibility, outputs=main_ui)
         app.load(get_org_dropdown, outputs=[org_name])
 
     return (
@@ -300,25 +300,6 @@ def get_iterate_on_sample_dataset_ui(
     )
 
 
-def get_pipeline_code_ui(pipeline_code: str) -> gr.Code:
-    gr.Markdown("## Customize and run with distilabel")
-    gr.HTML("<hr>")
-
-    with gr.Accordion(
-        "Run this pipeline using distilabel",
-        open=False,
-    ):
-        gr.Markdown(
-            "You can run this pipeline locally with distilabel. For more information, please refer to the [distilabel documentation](https://distilabel.argilla.io/) or go to the FAQ tab at the top of the page for more information."
-        )
-        pipeline_code = gr.Code(
-            value=pipeline_code,
-            language="python",
-            label="Distilabel Pipeline Code",
-        )
-    return pipeline_code
-
-
 def get_argilla_tab() -> Tuple[Any]:
     with gr.Tab(label="Argilla"):
         if get_argilla_client() is not None:
@@ -492,33 +473,35 @@ def get_success_message_row() -> gr.Markdown:
     return success_message
 
 
-def show_success_message_hub(org_name, repo_name) -> gr.Markdown:
+def show_success_message(org_name, repo_name) -> gr.Markdown:
     client = get_argilla_client()
     argilla_api_url = client.api_url
     return gr.Markdown(
         value=f"""
         <div style="padding: 1em; background-color: #e6f3e6; border-radius: 5px; margin-top: 1em;">
             <h3 style="color: #2e7d32; margin: 0;">Dataset Published Successfully!</h3>
             <p style="margin-top: 0.5em;">
-                Your dataset is now available the Hugging Face Hub:
-                <a href="https://huggingface.co/datasets/{org_name}/{repo_name}" target="_blank" style="color: #1565c0; text-decoration: none;">
-                    https://huggingface.co/datasets/{org_name}/{repo_name}
-                </a>
+                <strong>
+                    <a href="{argilla_api_url}" target="_blank" style="color: #1565c0; text-decoration: none;">
+                        Open your dataset in the Argilla space
+                    </a>
+                </strong>
             </p>
             <p style="margin-top: 0.5em;">
-                Your dataset is now available within Argilla:
-                <a href="{argilla_api_url}" target="_blank" style="color: #1565c0; text-decoration: none;">
-                    {argilla_api_url}
+                The generated dataset is in the right format for fine-tuning with TRL, AutoTrain, or other frameworks. Your dataset is now available at: 
+                <a href="https://huggingface.co/datasets/{org_name}/{repo_name}" target="_blank" style="color: #1565c0; text-decoration: none;">
+                    https://huggingface.co/datasets/{org_name}/{repo_name}
                 </a>
-                <br>Unfamiliar with Argilla? Here are some docs to help you get started:
-                <br>• <a href="https://docs.argilla.io/latest/how_to_guides/annotate/" target="_blank">How to curate data in Argilla</a>
-                <br>• <a href="https://docs.argilla.io/latest/how_to_guides/import_export/" target="_blank">How to export data once you have reviewed the dataset</a>
             </p>
         </div>
+        <p style="margin-top: 1em; font-size: 0.9em; color: #333;">
+            Unfamiliar with Argilla? Here are some docs to help you get started:
+            <br>• <a href="https://docs.argilla.io/latest/how_to_guides/annotate/" target="_blank">How to curate data in Argilla</a>
+            <br>• <a href="https://docs.argilla.io/latest/how_to_guides/import_export/" target="_blank">How to export data once you have reviewed the dataset</a>
+        </p>
         """,
         visible=True,
     )
 
-
 def hide_success_message() -> gr.Markdown:
     return gr.Markdown(value="")