Upload 5 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+all_hadiths_clean[[:space:]](1).csv filter=lfs diff=lfs merge=lfs -text
+all_hadiths_clean[[:space:]](2).csv filter=lfs diff=lfs merge=lfs -text
+encoded_hadiths_multilingual-e5-large-instruct[[:space:]](1)[[:space:]](1).sav filter=lfs diff=lfs merge=lfs -text

all_hadiths_clean (1).csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6800edb54d45a6e6c5228cf0342c0c72d90eca62a857bcbb5c61684e550db15
+size 41069994

all_hadiths_clean (2).csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6800edb54d45a6e6c5228cf0342c0c72d90eca62a857bcbb5c61684e550db15
+size 41069994

app (1).py

@@ -0,0 +1,80 @@
+import gradio as gr
+from sentence_transformers import SentenceTransformer
+import pandas as pd
+#import pickle
+import torch
+from pathlib import Path  
+
+# Define the function to categorize ages
+def categorize_source(source):
+    if "Nasa'i" in source:
+        return 'nasai'
+    elif "Majah" in source:
+        return 'ibnmajah'
+    elif "Da'ud" in source:
+        return 'abudawud'
+    elif "Muslim" in source:
+        return 'muslim'
+    elif "Bukhari" in source:
+        return 'bukhari'
+    elif "Tirmidhi" in source:
+        return 'tirmidhi'
+    else:
+        return ''
+
+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")
+    
+    hadiths = pd.read_csv('all_hadiths_clean.csv', delimiter=",")
+    
+    model = SentenceTransformer('intfloat/multilingual-e5-large-instruct')
+
+    document_embeddings = torch.load('encoded_hadiths_multilingual-e5-large-instruct (1).sav',map_location ='cpu')
+    #file = open('encoded_hadiths_multilingual-e5-large-instruct (1).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
+    hadiths['similarity'] = scores.tolist()[0]
+    sorted_hadiths = hadiths.sort_values(by='similarity', ascending=False)
+    print("cekpoin3\n")
+    
+    results = sorted_hadiths.head(20).drop(columns=['id', 'hadith_id', 'chain_indx'])
+    results['source_cat'] = results['source'].apply(categorize_source)
+    results['hadith_no'] = results['hadith_no'].str.strip()
+
+    url = 'https://sunnah.com/'+results['source_cat'].astype(str)+':'+results['hadith_no'].astype(str)
+    results['text_ar'] = '<a href="'+url+'">'+results['text_ar']+'</a>'
+    results = results.drop(columns=['source_cat'])
+    
+    #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=['source', 'chapter_no', 'hadith_no', 'chapter', 'text_ar', 'text_en'],datatype=["str", "str", "str", "str", "markdown", "str"],wrap=True),gr.DownloadButton()], 
+    examples=[
+                ["law of inheritance in islam"],
+                ["tunjukilah jalan yang lurus"],
+                ["سليمان"],
+            ],
+    title="Hadiths Finder")
+#demo = gr.Interface(fn=find, inputs="textbox", outputs="textbox")
+    
+if __name__ == "__main__":
+    demo.launch()   

encoded_hadiths_multilingual-e5-large-instruct (1) (1).sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2821e7b77e91294ab6385974537e653ef5be43bd59a30df6db9276483c93999c
+size 141071516

requirements.txt

@@ -0,0 +1,3 @@
+sentence_transformers
+pandas
+gradio