import gradio as gr from huggingface_hub import InferenceClient import PyPDF2 import docx import io client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") def extract_text_from_pdf(pdf_file): pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_file)) text = "" for page in pdf_reader.pages: text += page.extract_text() + "\n" return text def extract_text_from_docx(docx_file): doc = docx.Document(io.BytesIO(docx_file)) return "\n".join([para.text for para in doc.paragraphs]) def parse_cv(file): if file is None: return "Please upload a CV file." file_ext = file.name.split(".")[-1].lower() file_bytes = file.read() if file_ext == "pdf": text = extract_text_from_pdf(file_bytes) elif file_ext == "docx": text = extract_text_from_docx(file_bytes) else: return "Unsupported file format. Please upload a PDF or DOCX file." prompt = f"Analyze the following CV and generate a professional summary and improvement suggestions:\n\n{text}" response = client.text_generation(prompt, max_tokens=512) return response def respond( message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p, ): messages = [{"role": "system", "content": system_message}] for val in history: if val[0]: messages.append({"role": "user", "content": val[0]}) if val[1]: messages.append({"role": "assistant", "content": val[1]}) messages.append({"role": "user", "content": message}) response = "" for message in client.chat_completion( messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p, ): token = message.choices[0].delta.content response += token yield response demo = gr.Blocks() with demo: gr.Markdown("## AI-powered CV Analyzer and Chatbot") with gr.Tab("Chatbot"): chat_interface = gr.ChatInterface( respond, additional_inputs=[ gr.Textbox(value="You are a friendly Chatbot.", label="System message"), gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), gr.Slider( minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)", ), ], ) with gr.Tab("CV Analyzer"): gr.Markdown("### Upload your CV (PDF or DOCX) to receive a professional analysis.") file_input = gr.File(label="Upload CV", type="file") output_text = gr.Textbox(label="CV Analysis Report", lines=10) analyze_button = gr.Button("Analyze CV") analyze_button.click(parse_cv, inputs=file_input, outputs=output_text) if __name__ == "__main__": demo.launch()