Update app.py

app.py

@@ -1,7 +1,47 @@
-import gradio as gr
+import os
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
 
-def greet(name):
-    return "Hello " + name + "!!"
+def find_closest(query):
+    files_contents = []
+    files_names = []
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+    for file in os.listdir():
+        if file.endswith(".txt"):
+            with open(file, 'r') as f:
+                content = f.read()
+                files_contents.append(content)
+                files_names.append(file)
+
+    # Append query to the end
+    files_contents.append(query)
+
+    # Initialize the TfidfVectorizer
+    tfidf_vectorizer = TfidfVectorizer()
+
+    # Fit and transform the texts
+    tfidf_matrix = tfidf_vectorizer.fit_transform(files_contents)
+
+    # Compute the cosine similarity between the query and all files
+    similarity_scores = cosine_similarity(tfidf_matrix[-1:], tfidf_matrix[:-1])
+
+    # Get the index of the file with the highest similarity score
+    max_similarity_idx = similarity_scores.argmax()
+
+    # Return the name of the file with the highest similarity score
+    return files_names[max_similarity_idx]
+
+def find_closest_mp3(query):
+    closest_txt_file = find_closest(query)
+    file_name_without_extension, _ = os.path.splitext(closest_txt_file)
+    return file_name_without_extension + '.mp3'
+my_theme = gr.Theme.from_hub("ysharma/llamas")
+with gr.Blocks(theme=my_theme) as demo:
+  gr.Markdown("# BeatLlama Dreambooth!")
+  # video=gr.PlayableVideo("final_video.mp4")
+  inp=gr.Textbox(placeholder="Describe your dream!",label="Your dream")
+  out=gr.Audio(label="Llamas singing your dream")
+  inp.change(find_closest_mp3,inp,out,scroll_to_output=True)
+  out.play(None)
+demo.queue(1)
+demo.launch(show_api=False,debug=True)