Create app.py

app.py

@@ -0,0 +1,80 @@
+import gradio as gr
+import numpy as np
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import euclidean_distances
+
+# Load DataFrame
+text_embeddings = pd.read_parquet('text_embeddings_abstract_all.parquet')
+
+# Initialize models
+model_all_Mini = SentenceTransformer('all-MiniLM-L6-v2')
+model_e5_large_v2 = SentenceTransformer('intfloat/e5-large-v2')
+model_e5_small_v2 = SentenceTransformer('intfloat/e5-small-v2')
+model_gte_large = SentenceTransformer('thenlper/gte-large')
+model_GIST_large = SentenceTransformer('avsolatorio/GIST-large-Embedding-v0')
+
+# Model selection drop-down list
+model_options = {
+    'all-MiniLM-L6-v2': model_all_Mini,
+    'intfloat/e5-large-v2': model_e5_large_v2,
+    'intfloat/e5-small-v2': model_e5_small_v2,
+    'thenlper/gte-large': model_gte_large,
+    'avsolatorio/GIST-large-Embedding-v0': model_GIST_large
+}
+
+# Main function for the Gradio interface
+def find_similar_texts(model_name, input_text):
+    # Check whether there are abstracts matching the text input
+    input_embedding_mini = model_all_Mini.encode(input_text).reshape(1, -1)
+    embedding_matrix_mini = np.vstack(text_embeddings['embedding_all-MiniLM-L6-v2'])
+    distances_mini = euclidean_distances(embedding_matrix_mini, input_embedding_mini).flatten()
+
+    # Only continue if similar abstract found
+    if any(distances_mini < 1.05):
+        selected_model = model_options[model_name]
+        embedding_column = 'embedding_' + model_name
+        input_embedding = selected_model.encode(input_text).reshape(1, -1)
+        embedding_matrix = np.vstack(text_embeddings[embedding_column])
+        distances = euclidean_distances(embedding_matrix, input_embedding).flatten()
+        text_embeddings['euclidean_distance'] = distances
+        sorted_embeddings = text_embeddings.sort_values(by='euclidean_distance', ascending=True)
+        top_five = sorted_embeddings.head(5)[['abstract', 'patent no']]
+        formatted_output = '\n\n'.join([f"Patent No: {row['patent no']}\nAbstract: {row['abstract']}\n" for index, row in top_five.iterrows()])
+        return formatted_output
+    else:
+        return "It seems there is no patent abstract close to your description."
+
+# Create Gradio interface using Blocks
+with gr.Blocks() as demo:
+    gr.Markdown("## Sentence-Transformer based Patent-Abstract Search")
+    with gr.Row():
+        with gr.Column():
+            model_selector = gr.Dropdown(choices=list(model_options.keys()), label="Chose Sentence-Transformer")
+            text_input = gr.Textbox(lines=2, placeholder="input_text", label="input_text (your description)")
+            submit_button = gr.Button("search")
+            
+        with gr.Column():
+            output = gr.Textbox(label="top 5 patent abstracts if available)")
+    
+    submit_button.click(find_similar_texts, inputs=[model_selector, text_input], outputs=output)
+
+
+    gr.Markdown("""
+    ### Description
+    This demo app leverages several Sentence Transformer models to compute the semantic distance between user input and a small number of patent abstracts in the field of machine learning and AI.
+
+- 'all-MiniLM-L6-v2': embedding size is 384. [More info](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) and [here](https://sbert.net/).
+- 'intfloat/e5-large-v2'. Text Embeddings by Weakly-Supervised Contrastive Pre-training, embedding size is 1024. [More info](https://huggingface.co/intfloat/e5-large-v2).
+- 'intfloat/e5-small-v2': Text Embeddings by Weakly-Supervised Contrastive Pre-training, embedding size is 384. [More info](https://huggingface.co/intfloat/e5-small-v2).
+- 'thenlper/gte-large': General Text Embeddings (GTE) model, embedding size is 1024. [More info](https://huggingface.co/thenlper/gte-large) and [here](https://arxiv.org/abs/2308.03281).
+- 'avsolatorio/GIST-large-Embedding-v0': Fine-tuned on top of the BAAI/bge-large-en-v1.5 using the MEDI dataset augmented with mined triplets from the MTEB Classification training dataset, embedding size is 1024. [More info](https://huggingface.co/avsolatorio/GIST-large-Embedding-v0) and [here](https://arxiv.org/abs/2402.16829).
+
+The patents can be viewed at [Espacenet](https://worldwide.espacenet.com/?locale=en_EP), the free onine service by the European Patent Office.
+
+Please note: The data used in this demo contains only a very limited subset of patent abstracts and is intended only for demonstration purposes. It does by far not cover all patents or their complete data.
+    """)
+    model_selector.change(find_similar_texts, inputs=[model_selector, text_input], outputs=output)
+    text_input.submit(find_similar_texts, inputs=[model_selector, text_input], outputs=output)
+
+demo.launch()