Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from sentence_transformers import SentenceTransformer, util | |
| import string, re | |
| from cleanco import basename | |
| model = None | |
| def prepare(text): | |
| text = text.translate(str.maketrans('', '', string.punctuation + '”“')) | |
| pattern = r"\b(?=[MDCLXVII])M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})([II]X|[II]V|V?[II]{0,3})\b\.?" | |
| text = re.sub(pattern, '', text) | |
| text = basename(text).upper() | |
| return text | |
| def semantic(company_1, company_2): | |
| global model | |
| # Single list of sentences | |
| sentences = [prepare(company_1), prepare(company_2)] | |
| if model is None: | |
| model = SentenceTransformer('all-mpnet-base-v2') | |
| #Compute embeddings | |
| embeddings = model.encode(sentences, convert_to_tensor=True) | |
| #Compute cosine-similarities for each sentence with each other sentence | |
| cosine_scores = util.cos_sim(embeddings, embeddings) | |
| #Find the pairs with the highest cosine similarity scores | |
| pairs = [] | |
| for i in range(len(cosine_scores)-1): | |
| for j in range(i+1, len(cosine_scores)): | |
| pairs.append({'index': [i, j], 'score': cosine_scores[i][j]}) | |
| #Sort scores in decreasing order | |
| pairs = sorted(pairs, key=lambda x: x['score'], reverse=True) | |
| for pair in pairs: | |
| return "{:.4f}".format(pair['score']) | |
| company_1 = "Growth Capital Acquisition Corp" | |
| company_2 = None # "Growth Capital Acquisition Corp III" | |
| title = 'sentences_semantic' | |
| gr.Interface(semantic,inputs=[gr.inputs.Textbox(lines=1, default=company_1, label="Company_1"), gr.inputs.Textbox(lines=1, default=company_2, label="Company_2")], | |
| outputs=[gr.outputs.Textbox(type="auto",label="Score")],title = title).launch() |