| import json | |
| from huggingface_hub import InferenceClient | |
| import gradio as gr | |
| import PyPDF2 | |
| import random | |
| import pandas as pd | |
| from io import BytesIO | |
| import csv | |
| import os | |
| import io | |
| import tempfile | |
| import re | |
| client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1") | |
| def extract_sentences_from_excel(file): | |
| df = pd.read_excel(file) | |
| text = ' '.join(df['Unnamed: 1'].astype(str)) | |
| sentences = text.split('.') | |
| sentences = [s.strip() for s in sentences if s.strip() and s.strip() != 'nan'] | |
| return sentences | |
| def save_to_json(data, filename="synthetic_data.json"): | |
| with open(filename, mode='a', encoding='utf-8') as file: | |
| json.dump(data, file, indent=4, ensure_ascii=False) | |
| def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalty): | |
| sentences = extract_sentences_from_excel(file) | |
| data = [] | |
| with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json') as tmp: | |
| for sentence in sentences: | |
| sentence = sentence.strip() | |
| if not sentence: | |
| continue | |
| generate_kwargs = { | |
| "temperature": temperature, | |
| "max_new_tokens": max_new_tokens, | |
| "top_p": top_p, | |
| "repetition_penalty": repetition_penalty, | |
| "do_sample": True, | |
| "seed": 42, | |
| } | |
| try: | |
| stream = client.text_generation(f"{prompt} Output the response in the following JSON format: {{'generated_sentence': 'The generated sentence text', 'confidence_score': 0.9}}", **generate_kwargs, stream=True, details=True, return_full_text=False) | |
| output = "" | |
| for response in stream: | |
| output += response.token.text | |
| try: | |
| json_output = json.loads(output) | |
| data.append({"original_sentence": sentence, "generated_data": json_output}) | |
| except json.JSONDecodeError: | |
| print(f"Error decoding JSON for sentence '{sentence}': {output}") | |
| except Exception as e: | |
| print(f"Error generating data for sentence '{sentence}': {e}") | |
| save_to_json(data, tmp.name) | |
| tmp_path = tmp.name | |
| return tmp_path | |
| gr.Interface( | |
| fn=generate, | |
| inputs=[ | |
| gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx"]), | |
| gr.Textbox(label="Prompt", placeholder="Enter your prompt here"), | |
| gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"), | |
| gr.Slider(label="Max new tokens", value=256, minimum=0, maximum=5120, step=64, interactive=True, info="The maximum numbers of new tokens"), | |
| gr.Slider(label="Top-p (nucleus sampling)", value=0.95, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"), | |
| gr.Slider(label="Repetition penalty", value=1.0, minimum=1.0, maximum=2.0, step=0.1, interactive=True, info="Penalize repeated tokens"), | |
| ], | |
| outputs=gr.File(label="Synthetic Data "), | |
| title="SDG", | |
| description="AYE QABIL.", | |
| allow_flagging="never", | |
| ).launch() |