import gradio as gr
from gradio_huggingfacehub_search import HuggingfaceHubSearch
import nbformat as nbf
from huggingface_hub import HfApi
from httpx import Client
import logging
from huggingface_hub import InferenceClient
import json
import re
import pandas as pd
from gradio.data_classes import FileData
from utils.prompts import (
generate_mapping_prompt,
generate_eda_prompt,
generate_embedding_prompt,
)
"""
TODOs:
- Need feedback on the output commands to validate if operations are appropiate to data types
- Refactor
- Make the notebook generation more dynamic, add loading components to do not freeze the UI
- Fix errors:
- When generating output
- When parsing output
- When pushing notebook
- Add target tasks to choose for the notebook:
- Exploratory data analysis
- Auto training
- RAG
- etc.
- Enable 'generate notebook' button only if dataset is available and supports library
- First get compatible-libraries and let user choose the library
"""
# Configuration
BASE_DATASETS_SERVER_URL = "https://datasets-server.huggingface.co"
HEADERS = {"Accept": "application/json", "Content-Type": "application/json"}
client = Client(headers=HEADERS)
inference_client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
logging.basicConfig(level=logging.INFO)
def get_compatible_libraries(dataset: str):
resp = client.get(
f"{BASE_DATASETS_SERVER_URL}/compatible-libraries?dataset={dataset}"
)
resp.raise_for_status()
return resp.json()
def create_notebook_file(cell_commands, notebook_name):
nb = nbf.v4.new_notebook()
nb["cells"] = [
nbf.v4.new_code_cell(command["source"])
if command["cell_type"] == "code"
else nbf.v4.new_markdown_cell(command["source"])
for command in cell_commands
]
with open(notebook_name, "w") as f:
nbf.write(nb, f)
logging.info(f"Notebook {notebook_name} created successfully")
def push_notebook(file_path, dataset_id, token):
notebook_name = "dataset_analysis.ipynb"
api = HfApi(token=token)
try:
api.upload_file(
path_or_fileobj=file_path,
path_in_repo=notebook_name,
repo_id=dataset_id,
repo_type="dataset",
)
link = f"https://huggingface.co/datasets/{dataset_id}/blob/main/{notebook_name}"
return gr.HTML(
value=f'See notebook',
visible=True,
)
except Exception as err:
logging.error(f"Failed to push notebook: {err}")
return gr.HTML(value="Failed to push notebook", visible=True)
def get_first_rows_as_df(dataset: str, config: str, split: str, limit: int):
resp = client.get(
f"{BASE_DATASETS_SERVER_URL}/first-rows?dataset={dataset}&config={config}&split={split}"
)
resp.raise_for_status()
content = resp.json()
rows = content["rows"]
rows = [row["row"] for row in rows]
first_rows_df = pd.DataFrame.from_dict(rows).sample(frac=1).head(limit)
features = content["features"]
features_dict = {feature["name"]: feature["type"] for feature in features}
return features_dict, first_rows_df
def get_txt_from_output(output):
extracted_text = content_from_output(output)
content = json.loads(extracted_text)
logging.info(content)
return content
def content_from_output(output):
pattern = r"`json(.*?)`"
match = re.search(pattern, output, re.DOTALL)
if not match:
pattern = r"```(.*?)```"
match = re.search(pattern, output, re.DOTALL)
if not match:
try:
index = output.index("```json")
logging.info(f"Index: {index}")
return output[index + 7 :]
except:
pass
raise Exception("Unable to generate jupyter notebook.")
return match.group(1)
def generate_eda_cells(dataset_id):
for messages in generate_cells(dataset_id, generate_eda_prompt):
yield messages, gr.update(visible=False), None # Keep button hidden
yield messages, gr.update(visible=True), f"{dataset_id.replace('/', '-')}.ipynb"
def generate_embedding_cells(dataset_id):
for messages in generate_cells(dataset_id, generate_embedding_prompt):
yield messages, gr.update(visible=False), None # Keep button hidden
yield messages, gr.update(visible=True), f"{dataset_id.replace('/', '-')}.ipynb"
def push_to_hub(
history,
dataset_id,
notebook_file,
profile: gr.OAuthProfile | None,
oauth_token: gr.OAuthToken | None,
):
logging.info(f"Pushing notebook to hub: {dataset_id} on file {notebook_file}")
if not profile or not oauth_token:
yield history + [
gr.ChatMessage(role="assistant", content="⏳ _Login to push to hub..._")
]
logging.info(f"Profile: {profile}, token: {oauth_token.token}")
notebook_name = "dataset_analysis.ipynb"
api = HfApi(token=oauth_token.token)
try:
logging.info(f"About to push {notebook_file} - {notebook_name} - {dataset_id}")
api.upload_file(
path_or_fileobj=notebook_file,
path_in_repo=notebook_name,
repo_id=dataset_id,
repo_type="dataset",
)
link = f"https://huggingface.co/datasets/{dataset_id}/blob/main/{notebook_name}"
logging.info(f"Notebook pushed to hub: {link}")
yield history + [
gr.ChatMessage(
role="assistant", content=f"[Here is the generated notebook]({link})"
)
]
except Exception as err:
logging.info("Failed to push notebook", err)
yield history + [gr.ChatMessage(role="assistant", content=err)]
def generate_cells(dataset_id, prompt_fn):
try:
libraries = get_compatible_libraries(dataset_id)
except Exception as err:
gr.Error("Unable to retrieve dataset info from HF Hub.")
logging.error(f"Failed to fetch compatible libraries: {err}")
return []
if not libraries:
gr.Error("Dataset not compatible with pandas library.")
logging.error(f"Dataset not compatible with pandas library")
return gr.File(visible=False), gr.Row.update(visible=False)
pandas_library = next(
(lib for lib in libraries.get("libraries", []) if lib["library"] == "pandas"),
None,
)
if not pandas_library:
gr.Error("Dataset not compatible with pandas library.")
return []
first_config_loading_code = pandas_library["loading_codes"][0]
first_code = first_config_loading_code["code"]
first_config = first_config_loading_code["config_name"]
first_split = list(first_config_loading_code["arguments"]["splits"].keys())[0]
logging.info(f"First config: {first_config} - first split: {first_split}")
first_file = f"hf://datasets/{dataset_id}/{first_config_loading_code['arguments']['splits'][first_split]}"
logging.info(f"First split file: {first_file}")
features, df = get_first_rows_as_df(dataset_id, first_config, first_split, 3)
sample_data = df.head(5).to_dict(orient="records")
prompt = prompt_fn(features, sample_data, first_code)
messages = [gr.ChatMessage(role="user", content=prompt)]
yield messages + [gr.ChatMessage(role="assistant", content="⏳ _Starting task..._")]
prompt_messages = [{"role": "user", "content": prompt}]
output = inference_client.chat_completion(
messages=prompt_messages, stream=True, max_tokens=2500
)
generated_text = ""
current_line = ""
for chunk in output:
current_line += chunk.choices[0].delta.content
if current_line.endswith("\n"):
generated_text += current_line
messages.append(gr.ChatMessage(role="assistant", content=current_line))
current_line = ""
yield messages
yield messages
logging.info("---> Formated prompt")
formatted_prompt = generate_mapping_prompt(generated_text)
logging.info(formatted_prompt)
prompt_messages = [{"role": "user", "content": formatted_prompt}]
yield messages + [
gr.ChatMessage(role="assistant", content="⏳ _Generating notebook..._")
]
output = inference_client.chat_completion(
messages=prompt_messages, stream=False, max_tokens=2500
)
cells_txt = output.choices[0].message.content
logging.info("---> Model output")
logging.info(cells_txt)
commands = get_txt_from_output(cells_txt)
html_code = f""
# Adding dataset viewer on the first part
commands.insert(
0,
{
"cell_type": "code",
"source": f'from IPython.display import HTML\n\ndisplay(HTML("{html_code}"))',
},
)
commands.insert(0, {"cell_type": "markdown", "source": "# Dataset Viewer"})
notebook_name = f"{dataset_id.replace('/', '-')}.ipynb"
create_notebook_file(commands, notebook_name=notebook_name)
messages.append(
gr.ChatMessage(role="user", content="Here is the generated notebook")
)
yield messages
messages.append(
gr.ChatMessage(
role="user",
content=FileData(path=notebook_name, mime_type="application/x-ipynb+json"),
)
)
yield messages
def comming_soon_message():
gr.Info("Comming soon")
with gr.Blocks(fill_height=True) as demo:
gr.Markdown("# 🤖 Dataset notebook creator 🕵️")
with gr.Row():
with gr.Column(scale=1):
dataset_name = HuggingfaceHubSearch(
label="Hub Dataset ID",
placeholder="Search for dataset id on Huggingface",
search_type="dataset",
value="",
)
@gr.render(inputs=dataset_name)
def embed(name):
if not name:
return gr.Markdown("### No dataset provided")
html_code = f"""
"""
return gr.HTML(value=html_code)
with gr.Row():
generate_eda_btn = gr.Button("Generate EDA notebook")
generate_embedding_btn = gr.Button("Generate Embeddings notebook")
generate_training_btn = gr.Button("Generate Training notebook")
with gr.Column():
chatbot = gr.Chatbot(
label="Results",
type="messages",
avatar_images=(
None,
None,
),
)
with gr.Row():
login_btn = gr.LoginButton()
push_btn = gr.Button("Push to hub", visible=False)
notebook_file = gr.File(visible=False)
generate_eda_btn.click(
generate_eda_cells,
inputs=[dataset_name],
outputs=[chatbot, push_btn, notebook_file],
)
generate_embedding_btn.click(
generate_embedding_cells,
inputs=[dataset_name],
outputs=[chatbot, push_btn, notebook_file],
)
generate_training_btn.click(comming_soon_message, inputs=[], outputs=[])
push_btn.click(
push_to_hub,
inputs=[
chatbot,
dataset_name,
notebook_file,
],
outputs=[chatbot],
)
demo.launch()