refactor package folders

app.py

@@ -1,4 +1,4 @@
-from distilabel_dataset_generator.app import demo
+from synthetic_dataset_generator.app import demo
 
 if __name__ == "__main__":
     demo.launch()

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "distilabel-dataset-generator"
+name = "synthetic-dataset-generator"
 version = "0.1.0"
 description = "Build datasets using natural language"
 authors = [

src/{distilabel_dataset_generator → synthetic_dataset_generator}/app.py

@@ -1,8 +1,8 @@
-from distilabel_dataset_generator._tabbedinterface import TabbedInterface
-from distilabel_dataset_generator.apps.eval import app as eval_app
-from distilabel_dataset_generator.apps.faq import app as faq_app
-from distilabel_dataset_generator.apps.sft import app as sft_app
-from distilabel_dataset_generator.apps.textcat import app as textcat_app
+from synthetic_dataset_generator._tabbedinterface import TabbedInterface
+from synthetic_dataset_generator.apps.eval import app as eval_app
+from synthetic_dataset_generator.apps.faq import app as faq_app
+from synthetic_dataset_generator.apps.sft import app as sft_app
+from synthetic_dataset_generator.apps.textcat import app as textcat_app
 
 theme = "argilla/argilla-theme"
 

src/{distilabel_dataset_generator → synthetic_dataset_generator}/apps/base.py

@@ -10,8 +10,8 @@ from distilabel.distiset import Distiset
 from gradio import OAuthToken
 from huggingface_hub import HfApi, upload_file
 
-from distilabel_dataset_generator.constants import TEXTCAT_TASK
-from distilabel_dataset_generator.utils import (
+from synthetic_dataset_generator.constants import TEXTCAT_TASK
+from synthetic_dataset_generator.utils import (
     get_argilla_client,
 )
 

src/{distilabel_dataset_generator → synthetic_dataset_generator}/apps/eval.py

@@ -16,23 +16,23 @@ from distilabel.distiset import Distiset
 from gradio_huggingfacehub_search import HuggingfaceHubSearch
 from huggingface_hub import HfApi
 
-from distilabel_dataset_generator.apps.base import (
+from synthetic_dataset_generator.apps.base import (
     hide_success_message,
     show_success_message,
     validate_argilla_user_workspace_dataset,
     validate_push_to_hub,
 )
-from distilabel_dataset_generator.constants import DEFAULT_BATCH_SIZE
-from distilabel_dataset_generator.pipelines.embeddings import (
+from synthetic_dataset_generator.constants import DEFAULT_BATCH_SIZE
+from synthetic_dataset_generator.pipelines.embeddings import (
     get_embeddings,
     get_sentence_embedding_dimensions,
 )
-from distilabel_dataset_generator.pipelines.eval import (
+from synthetic_dataset_generator.pipelines.eval import (
     generate_pipeline_code,
     get_custom_evaluator,
     get_ultrafeedback_evaluator,
 )
-from distilabel_dataset_generator.utils import (
+from synthetic_dataset_generator.utils import (
     column_to_list,
     extract_column_names,
     get_argilla_client,

src/{distilabel_dataset_generator → synthetic_dataset_generator}/apps/sft.py

@@ -9,25 +9,25 @@ from datasets import Dataset
 from distilabel.distiset import Distiset
 from huggingface_hub import HfApi
 
-from distilabel_dataset_generator.apps.base import (
+from synthetic_dataset_generator.apps.base import (
     hide_success_message,
     show_success_message,
     validate_argilla_user_workspace_dataset,
     validate_push_to_hub,
 )
-from distilabel_dataset_generator.constants import DEFAULT_BATCH_SIZE, SFT_AVAILABLE
-from distilabel_dataset_generator.pipelines.embeddings import (
+from synthetic_dataset_generator.constants import DEFAULT_BATCH_SIZE, SFT_AVAILABLE
+from synthetic_dataset_generator.pipelines.embeddings import (
     get_embeddings,
     get_sentence_embedding_dimensions,
 )
-from distilabel_dataset_generator.pipelines.sft import (
+from synthetic_dataset_generator.pipelines.sft import (
     DEFAULT_DATASET_DESCRIPTIONS,
     generate_pipeline_code,
     get_magpie_generator,
     get_prompt_generator,
     get_response_generator,
 )
-from distilabel_dataset_generator.utils import (
+from synthetic_dataset_generator.utils import (
     get_argilla_client,
     get_org_dropdown,
     swap_visibility,

src/{distilabel_dataset_generator → synthetic_dataset_generator}/apps/textcat.py

@@ -9,30 +9,30 @@ from datasets import ClassLabel, Dataset, Features, Sequence, Value
 from distilabel.distiset import Distiset
 from huggingface_hub import HfApi
 
-from distilabel_dataset_generator.constants import DEFAULT_BATCH_SIZE
-from src.distilabel_dataset_generator.apps.base import (
+from src.synthetic_dataset_generator.apps.base import (
     hide_success_message,
     show_success_message,
     validate_argilla_user_workspace_dataset,
     validate_push_to_hub,
 )
-from src.distilabel_dataset_generator.pipelines.embeddings import (
+from src.synthetic_dataset_generator.pipelines.embeddings import (
     get_embeddings,
     get_sentence_embedding_dimensions,
 )
-from src.distilabel_dataset_generator.pipelines.textcat import (
+from src.synthetic_dataset_generator.pipelines.textcat import (
     DEFAULT_DATASET_DESCRIPTIONS,
     generate_pipeline_code,
     get_labeller_generator,
     get_prompt_generator,
     get_textcat_generator,
 )
-from src.distilabel_dataset_generator.utils import (
+from src.synthetic_dataset_generator.utils import (
     get_argilla_client,
     get_org_dropdown,
     get_preprocess_labels,
     swap_visibility,
 )
+from synthetic_dataset_generator.constants import DEFAULT_BATCH_SIZE
 
 
 def generate_system_prompt(dataset_description, temperature, progress=gr.Progress()):

src/{distilabel_dataset_generator → synthetic_dataset_generator}/pipelines/base.py

@@ -1,4 +1,4 @@
-from distilabel_dataset_generator.constants import API_KEYS
+from synthetic_dataset_generator.constants import API_KEYS
 
 TOKEN_INDEX = 0
 

src/{distilabel_dataset_generator → synthetic_dataset_generator}/pipelines/embeddings.py

@@ -3,7 +3,7 @@ from typing import List
 from sentence_transformers import SentenceTransformer
 from sentence_transformers.models import StaticEmbedding
 
-from distilabel_dataset_generator.constants import STATIC_EMBEDDING_MODEL
+from synthetic_dataset_generator.constants import STATIC_EMBEDDING_MODEL
 
 static_embedding = StaticEmbedding.from_model2vec(STATIC_EMBEDDING_MODEL)
 model = SentenceTransformer(modules=[static_embedding])

src/{distilabel_dataset_generator → synthetic_dataset_generator}/pipelines/eval.py

@@ -5,9 +5,9 @@ from distilabel.steps.tasks import (
     UltraFeedback,
 )
 
-from distilabel_dataset_generator.constants import BASE_URL, MODEL
-from distilabel_dataset_generator.pipelines.base import _get_next_api_key
-from distilabel_dataset_generator.utils import extract_column_names
+from synthetic_dataset_generator.constants import BASE_URL, MODEL
+from synthetic_dataset_generator.pipelines.base import _get_next_api_key
+from synthetic_dataset_generator.utils import extract_column_names
 
 
 def get_ultrafeedback_evaluator(aspect, is_sample):

src/{distilabel_dataset_generator → synthetic_dataset_generator}/pipelines/sft.py

@@ -1,12 +1,12 @@
 from distilabel.llms import InferenceEndpointsLLM
 from distilabel.steps.tasks import ChatGeneration, Magpie, TextGeneration
 
-from distilabel_dataset_generator.constants import (
+from synthetic_dataset_generator.constants import (
     BASE_URL,
     MAGPIE_PRE_QUERY_TEMPLATE,
     MODEL,
 )
-from distilabel_dataset_generator.pipelines.base import _get_next_api_key
+from synthetic_dataset_generator.pipelines.base import _get_next_api_key
 
 INFORMATION_SEEKING_PROMPT = (
     "You are an AI assistant designed to provide accurate and concise information on a wide"

src/{distilabel_dataset_generator → synthetic_dataset_generator}/pipelines/textcat.py

@@ -9,9 +9,9 @@ from distilabel.steps.tasks import (
 )
 from pydantic import BaseModel, Field
 
-from distilabel_dataset_generator.constants import BASE_URL, MODEL
-from distilabel_dataset_generator.pipelines.base import _get_next_api_key
-from distilabel_dataset_generator.utils import get_preprocess_labels
+from synthetic_dataset_generator.constants import BASE_URL, MODEL
+from synthetic_dataset_generator.pipelines.base import _get_next_api_key
+from synthetic_dataset_generator.utils import get_preprocess_labels
 
 PROMPT_CREATION_PROMPT = """You are an AI assistant specialized in generating very precise text classification tasks for dataset creation.
 

src/{distilabel_dataset_generator → synthetic_dataset_generator}/utils.py

@@ -12,7 +12,7 @@ from gradio.oauth import (
 from huggingface_hub import whoami
 from jinja2 import Environment, meta
 
-from distilabel_dataset_generator.constants import argilla_client
+from synthetic_dataset_generator.constants import argilla_client
 
 
 def get_duplicate_button():