Spaces:
Sleeping
Sleeping
| from sentence_transformers import SentenceTransformer, util | |
| from transformers import pipeline | |
| import gradio as gr | |
| import nltk | |
| # Load the SentenceTransformer model for sentence similarity | |
| try: | |
| model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2') | |
| except Exception as e: | |
| print(f"Error loading SentenceTransformer model: {e}") | |
| # Load a summarization pipeline | |
| try: | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| except Exception as e: | |
| print(f"Error loading summarization pipeline: {e}") | |
| # Download NLTK punkt tokenizer if not already installed (run this once) | |
| nltk.download('punkt') | |
| def summarize_text(text, max_length=100, min_length=25): | |
| try: | |
| # Summarize the input text | |
| summary = summarizer(text, max_length=max_length, min_length=min_length, do_sample=False) | |
| return summary[0]["summary_text"] | |
| except Exception as e: | |
| return f"Error summarizing text: {e}" | |
| def match_cv_to_jobs(cv_text, job_descriptions): | |
| debug_info = "Debug Info:\n" | |
| results = [] | |
| # Summarize the CV text | |
| try: | |
| summarized_cv = summarize_text(cv_text, max_length=150) | |
| debug_info += f"Summarized CV Text: {summarized_cv}\n" | |
| except Exception as e: | |
| debug_info += f"Error summarizing CV text: {e}\n" | |
| return [], debug_info | |
| # Summarize the job description | |
| try: | |
| summarized_job_desc = summarize_text(job_descriptions, max_length=150) | |
| debug_info += f"Summarized Job Description Text: {summarized_job_desc}\n" | |
| except Exception as e: | |
| debug_info += f"Error summarizing job descriptions: {e}\n" | |
| return [], debug_info | |
| # Encode the summarized CV text | |
| try: | |
| cv_embedding = model.encode(summarized_cv, convert_to_tensor=True) | |
| debug_info += f"CV Embedding: {cv_embedding}\n" | |
| except Exception as e: | |
| debug_info += f"Error encoding CV text: {e}\n" | |
| return [], debug_info | |
| # Split summarized job description into sentences | |
| try: | |
| description_sentences = nltk.tokenize.sent_tokenize(summarized_job_desc) | |
| except Exception as e: | |
| debug_info += f"Error tokenizing job description: {e}\n" | |
| return [], debug_info | |
| for sentence in description_sentences: | |
| try: | |
| # Encode each sentence from the summarized job description | |
| sentence_embedding = model.encode(sentence, convert_to_tensor=True) | |
| debug_info += f"\nJob Description Sentence Embedding: {sentence_embedding}\n" | |
| # Compute similarity score | |
| similarity_score = util.pytorch_cos_sim(cv_embedding, sentence_embedding).item() | |
| debug_info += f"Similarity Score for sentence: {similarity_score}\n" | |
| results.append({ | |
| "Job Description Sentence": sentence, | |
| "Similarity Score": similarity_score | |
| }) | |
| except Exception as e: | |
| debug_info += f"Error processing sentence '{sentence}': {e}\n" | |
| continue | |
| # Sort results by similarity score in descending order | |
| try: | |
| results = sorted(results, key=lambda x: x["Similarity Score"], reverse=True) | |
| except Exception as e: | |
| debug_info += f"Error sorting results: {e}\n" | |
| return results, debug_info | |
| # Gradio interface | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# CV and Job Description Matcher with Summarization and Sentence Similarity") | |
| # Input fields for CV and job descriptions | |
| cv_text = gr.Textbox(label="CV Text", placeholder="Enter the CV text here", lines=10) | |
| job_descriptions = gr.Textbox(label="Job Descriptions", placeholder="Enter the entire job description text here", lines=10) | |
| # Button and output area | |
| match_button = gr.Button("Match CV to Job Descriptions") | |
| output = gr.JSON(label="Match Results") | |
| debug_output = gr.Textbox(label="Debug Info", lines=10) # Add a debug box to display debug info | |
| # Set button click to run the function | |
| match_button.click(fn=match_cv_to_jobs, inputs=[cv_text, job_descriptions], outputs=[output, debug_output]) | |
| demo.launch() | |