Update app.py

app.py

@@ -1,64 +1,51 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
 
+from transformers import pipeline
+import gradio as gr
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# Input language translators (to English)
+input_translators = {
+    "Hindi": pipeline("translation_hi_to_en", model="Helsinki-NLP/opus-mt-hi-en"),
+    "French": pipeline("translation_fr_to_en", model="Helsinki-NLP/opus-mt-fr-en"),
+    "German": pipeline("translation_de_to_en", model="Helsinki-NLP/opus-mt-de-en"),
+    "English": None  # No translation needed
+}
+
+# Summarization model
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+# Output translators (English → target)
+output_translators = {
+    "None": None,
+    "Hindi": pipeline("translation_en_to_hi", model="Helsinki-NLP/opus-mt-en-hi"),
+    "French": pipeline("translation_en_to_fr", model="Helsinki-NLP/opus-mt-en-fr"),
+    "German": pipeline("translation_en_to_de", model="Helsinki-NLP/opus-mt-en-de"),
+}
+
+def summarize_multilang(text, input_lang, output_lang):
+    # Step 1: Translate to English (if needed)
+    if input_lang != "English":
+        translator = input_translators[input_lang]
+        text = translator(text)[0]['translation_text']
+    
+    # Step 2: Summarize
+    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
+    
+    # Step 3: Translate summary (if needed)
+    if output_lang != "None":
+        summary = output_translators[output_lang](summary)[0]['translation_text']
+    
+    return summary
+
+# Gradio interface
+gr.Interface(
+    fn=summarize_multilang,
+    inputs=[
+        gr.Textbox(lines=10, label="Input Text"),
+        gr.Dropdown(choices=["English", "Hindi", "French", "German"], label="Input Language"),
+        gr.Dropdown(choices=["None", "Hindi", "French", "German"], label="Translate Summary To")
     ],
-)
-
+    outputs=gr.Textbox(label="Final Summary"),
+    title="SummarAI",
+    description="Supports input in Hindi, French, German, or English. Summarizes and optionally translates the summary."
+).launch()
 
-if __name__ == "__main__":
-    demo.launch()