Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,67 @@
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+from datasets import load_dataset
+import pandas as pd
+import torch
+
+# ------------------------------
+# Cache model & dataset
+# ------------------------------
+def load_model_and_tokenizer():
+    model_ckpt = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+    tokenizer = AutoTokenizer.from_pretrained(model_ckpt)
+    model = AutoModel.from_pretrained(model_ckpt)
+    return tokenizer, model
+
+def load_embeddings_dataset():
+    dataset = load_dataset("ginnigarg/dataset-github-issues-embeddings", split="train")
+    dataset.add_faiss_index(column="embeddings")
+    return dataset
+
+tokenizer, model = load_model_and_tokenizer()
+embeddings_dataset = load_embeddings_dataset()
+
+# ------------------------------
+# Embedding helper
+# ------------------------------
+def cls_pooling(model_output):
+    return model_output.last_hidden_state[:, 0]
+
+def get_embeddings(text_list):
+    encoded_input = tokenizer(text_list, padding=True, truncation=True, return_tensors="pt")
+    with torch.no_grad():
+        model_output = model(**encoded_input)
+    return cls_pooling(model_output)
+
+# ------------------------------
+# Search function for Gradio
+# ------------------------------
+def semantic_search(question):
+    question_embedding = get_embeddings([question]).cpu().detach().numpy()
+    scores, samples = embeddings_dataset.get_nearest_examples(
+        "embeddings", question_embedding, k=5
+    )
+    samples_df = pd.DataFrame.from_dict(samples)
+    samples_df["scores"] = scores
+    samples_df.sort_values("scores", ascending=False, inplace=True)
+    # Convert to displayable format
+    return samples_df[["title", "comments", "html_url", "scores"]]
+
+# ------------------------------
+# Gradio Interface
+# ------------------------------
+with gr.Blocks() as demo:
+    gr.Markdown("# GitHub Issues Semantic Search")
+    question_input = gr.Textbox(label="Enter your question", value="How can I load a dataset offline?")
+    output = gr.Dataframe(headers=["title", "comments", "html_url", "scores"], datatype=["str", "str", "str", "number"])
+    search_button = gr.Button("Search")
+
+    def on_click(question):
+        return semantic_search(question)
+
+    search_button.click(fn=on_click, inputs=[question_input], outputs=[output])
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    demo.launch()