adding files

.gitattributes

@@ -33,3 +33,4 @@ 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
+quran_hadith.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+venv/
+*.pyc
+*.pyo
+*.pyd
+*.pyc
+*.pyo
+*.pyd

app.py

@@ -0,0 +1,49 @@
+import pickle
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.neighbors import NearestNeighbors
+import gradio as gr
+
+# Load the embeddings from the file
+with open('embeddings.pkl', 'rb') as f:
+    embeddings = pickle.load(f)
+
+# Initialize the Nearest Neighbors model with cosine similarity
+nbrs = NearestNeighbors(n_neighbors=20, metric='cosine').fit(embeddings)
+
+# Load the dataset
+df = pd.read_csv('quran_hadith.csv')
+
+# Initialize the SentenceTransformer model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def semantic_search(query, model, embeddings, nbrs, k=10):
+    # Encode the query
+    query_embedding = model.encode([query])[0]
+
+    # Find the k nearest neighbors
+    distances, indices = nbrs.kneighbors([query_embedding])
+
+    # Convert distances to percentages and round them to two decimal places
+    # distances = [(1 - dist) * 100 for dist in distances[0]]  # Cosine similarity as percentage
+    # distances = [round(dist, 2) for dist in distances]
+
+    # Return the k most similar sentences and their indices
+    similar_sentences = [(df['text'].iloc[idx], dist) for idx, dist in zip(indices[0], distances)]
+    return similar_sentences
+
+# Gradio function
+def search_interface(query):
+    similar_sentences = semantic_search(query, model, embeddings, nbrs, k=10)
+    results = [{"sentence": sentence, "similarity": f"{distance}%"} for sentence, distance in similar_sentences]
+    return results
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=search_interface,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your query here..."),
+    outputs=gr.JSON(label="Similar Sentences")
+)
+
+# Launch the interface
+iface.launch(share=True)

embeddings.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea0ad0ae5e5cf9a73dad7706c32f651e6596cd5b025a5abd440ca5bde7e006a
+size 40502947

quran_hadith.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6beddedddf73d2e8327e284a0eeed55820a246e6f99e19445c812027b5744cc5
+size 10748559