Create app.py

app.py

@@ -0,0 +1,84 @@
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+import pandas as pd
+import pickle
+from pathlib import Path  
+
+def make_clickable_both(val): 
+    name, url = val.split('#')
+    print(name+"\n")
+    print(url+"\n")
+    return f'<a href="{url}">{name}</a>'
+
+def find(query):
+    def get_detailed_instruct(task_description: str, query: str) -> str:
+        return f'Instruct: {task_description}\nQuery: {query}'
+    
+    # Each query must come with a one-sentence instruction that describes the task
+    task = 'Given a web search query, retrieve relevant passages that answer the query'
+    queries = [
+        get_detailed_instruct(task, query)
+    ]
+    print("cekpoin0\n")
+    
+    quran = pd.read_csv('quran-simple-clean.txt', delimiter="|")
+    
+    file = open('quran-splitted.sav','rb')
+    quran_splitted = pickle.load(file)
+    
+    model = SentenceTransformer('intfloat/multilingual-e5-large-instruct')
+    
+    documents = quran_splitted['text'].tolist()
+    # document_embeddings = model.encode(documents, convert_to_tensor=True, normalize_embeddings=True)
+    # filename = 'encoded_quran_text_split_multilingual-e5-large-instruct.sav'
+    # pickle.dump(embeddings, open(filename, 'wb'))
+    file = open('encoded_quran_text_split_multilingual-e5-large-instructs.sav','rb')
+    document_embeddings = pickle.load(file)
+    print("cekpoin1\n")
+    
+    query_embeddings = model.encode(queries, convert_to_tensor=True, normalize_embeddings=True)
+    scores = (query_embeddings @ document_embeddings.T) * 100
+    print("cekpoin2\n")
+
+    # insert the similarity value to dataframe & sort it
+    file = open('quran-splitted.sav','rb')
+    quran_splitted = pickle.load(file)
+    quran_splitted['similarity'] = scores.tolist()[0]
+    sorted_quran = quran_splitted.sort_values(by='similarity', ascending=False)
+    print("cekpoin3\n")
+    
+    #results = ""
+    results = pd.DataFrame()
+    i = 0
+    while i<20:
+        result = sorted_quran.iloc[i]
+        result_quran = quran.loc[(quran['sura']==result['sura']) & (quran['aya']==result['aya'])]
+        results = pd.concat([results, result_quran])
+        #results = results + result_quran['text'].item()+" (Q.S "+str(result['sura']).rstrip('.0')+":"+str(result['aya']).rstrip('.0')+")\n"
+        i=i+1
+
+    url = 'https://quran.com/'+results['sura'].astype(str)+':'+results['aya'].astype(str)+'/tafsirs/en-tafisr-ibn-kathir'
+    results['text'] = '<a href="'+url+'">'+results['text']+'</a>'
+    #results['text'] = results['text'] + '#' + 'https://quran.com/'+results['sura'].astype(str)+':'+results['aya'].astype(str)+'/tafsirs/en-tafisr-ibn-kathir'
+    
+    #results = results.style.format({'text': make_clickable_both})
+    
+    #return sorted_quran
+    filepath = Path(query+'.csv')  
+    results.to_csv(filepath,index=False)  
+    return results, filepath
+    
+demo = gr.Interface(
+    fn=find, 
+    inputs="textbox", 
+    outputs=[gr.Dataframe(headers=['sura', 'aya', 'text'],datatype=["str", "str", "markdown"],wrap=True),gr.DownloadButton()], 
+    examples=[
+                ["law of inheritance in islam"],
+                ["tunjukilah jalan yang lurus"],
+                ["سليمان"],
+            ],
+    title="Quran Finder")
+#demo = gr.Interface(fn=find, inputs="textbox", outputs="textbox")
+    
+if __name__ == "__main__":
+    demo.launch()