Reorganize structure for even less code clutter; `app.py` is greatly slimmed down

app.py

@@ -1,14 +1,12 @@
 from dotenv import load_dotenv
-from functools import partial
 import gradio as gr
 from huggingface_hub import InferenceClient
-from automatic_speech_recognition import automatic_speech_recognition
-from chatbot import chat
-from image_classification import image_classification
-from image_to_text import image_to_text
-from text_to_image import text_to_image
-from text_to_speech import text_to_speech
-from utils import request_image, request_audio
+from automatic_speech_recognition import create_asr_tab
+from chatbot import create_chatbot_tab
+from image_classification import create_image_classification_tab
+from image_to_text import create_image_to_text_tab
+from text_to_image import create_text_to_image_tab
+from text_to_speech import create_text_to_speech_tab
 
 
 class App:
@@ -22,103 +20,17 @@ class App:
             gr.Markdown("A gallery of building blocks for building AI applications")
             with gr.Tabs():
                 with gr.Tab("Text-to-image Generation"):
-                    gr.Markdown("Generate an image from a text prompt.")
-                    text_to_image_prompt = gr.Textbox(label="Prompt")
-                    text_to_image_generate_button = gr.Button("Generate")
-                    text_to_image_output = gr.Image(label="Image", type="pil")
-                    text_to_image_generate_button.click(
-                        fn=partial(text_to_image, self.client),
-                        inputs=text_to_image_prompt,
-                        outputs=text_to_image_output
-                    )
+                    create_text_to_image_tab(self.client)
                 with gr.Tab("Image-to-text or Image Captioning"):
-                    gr.Markdown("Generate a text description of an image.")
-                    image_to_text_url_input = gr.Textbox(label="Image URL")
-                    image_to_text_image_request_button = gr.Button("Get Image")
-                    image_to_text_image_input = gr.Image(label="Image", type="pil")
-                    image_to_text_image_request_button.click(
-                        fn=request_image,
-                        inputs=image_to_text_url_input,
-                        outputs=image_to_text_image_input
-                    )
-                    image_to_text_button = gr.Button("Caption")
-                    image_to_text_output = gr.List(label="Captions", headers=["Caption"])
-                    image_to_text_button.click(
-                        fn=image_to_text,
-                        inputs=image_to_text_image_input,
-                        outputs=image_to_text_output
-                    )
+                    create_image_to_text_tab()
                 with gr.Tab("Image Classification"):
-                    gr.Markdown("Classify a recyclable item as one of: cardboard, glass, metal, paper, plastic, or other using [Trash-Net](https://huggingface.co/prithivMLmods/Trash-Net).")
-                    image_classification_url_input = gr.Textbox(label="Image URL")
-                    image_classification_image_request_button = gr.Button("Get Image")
-                    image_classification_image_input = gr.Image(label="Image",type="pil")
-                    image_classification_image_request_button.click(
-                        fn=request_image,
-                        inputs=image_classification_url_input,
-                        outputs=image_classification_image_input
-                    )
-                    image_classification_button = gr.Button("Classify")
-                    image_classification_output = gr.Dataframe(label="Classification", headers=["Label", "Probability"], interactive=False)
-                    image_classification_button.click(
-                        fn=partial(image_classification, self.client),
-                        inputs=image_classification_image_input,
-                        outputs=image_classification_output
-                    )
+                    create_image_classification_tab(self.client)
                 with gr.Tab("Text-to-speech (TTS)"):
-                    gr.Markdown("Generate speech from text.")
-                    text_to_speech_text = gr.Textbox(label="Text")
-                    text_to_speech_generate_button = gr.Button("Generate")
-                    text_to_speech_output = gr.Audio(label="Speech")
-                    text_to_speech_generate_button.click(
-                        fn=text_to_speech,
-                        inputs=text_to_speech_text,
-                        outputs=text_to_speech_output
-                    )
+                    create_text_to_speech_tab()
                 with gr.Tab("Automatic Speech Recognition (ASR)"):
-                    gr.Markdown("Transcribe audio to text.")
-                    audio_transcription_url_input = gr.Textbox(label="Audio URL")
-                    audio_transcription_audio_request_button = gr.Button("Get Audio")
-                    audio_transcription_audio_input = gr.Audio(label="Audio")
-                    audio_transcription_audio_request_button.click(
-                        fn=request_audio,
-                        inputs=audio_transcription_url_input,
-                        outputs=audio_transcription_audio_input
-                    )
-                    audio_transcription_generate_button = gr.Button("Transcribe")
-                    audio_transcription_output = gr.Textbox(label="Text")
-                    audio_transcription_generate_button.click(
-                        fn=partial(automatic_speech_recognition, self.client),
-                        inputs=audio_transcription_audio_input,
-                        outputs=audio_transcription_output
-                    )
+                    create_asr_tab(self.client)
                 with gr.Tab("Chat"):
-                    gr.Markdown("Have a conversation with an AI chatbot.")
-                    chatbot_history = gr.State(value=None) # Store the conversation history.
-                    chatbot_output = gr.Chatbot(label="Conversation")
-                    chatbot_input = gr.Textbox(label="Your message")
-                    chatbot_send_button = gr.Button("Send")
-                    
-                    def chat_interface(message: str, history: list | None, conversation_state: list[dict] | None):
-                        """Handle chatbot interaction with Gradio chat format."""
-                        if not message.strip():
-                            return history, conversation_state, ""
-                        response, updated_conversation = chat(message, conversation_state) # Get response from chatbot.
-                        if history is None: # Update Gradio chat history format: list of [user_message, bot_message] pairs.
-                            history = []
-                        history.append([message, response])
-                        return history, updated_conversation, "" # Clear input field for the next message from the user.
-                    
-                    chatbot_send_button.click(
-                        fn=chat_interface,
-                        inputs=[chatbot_input, chatbot_output, chatbot_history],
-                        outputs=[chatbot_output, chatbot_history, chatbot_input]
-                    )
-                    chatbot_input.submit(
-                        fn=chat_interface,
-                        inputs=[chatbot_input, chatbot_output, chatbot_history],
-                        outputs=[chatbot_output, chatbot_history, chatbot_input]
-                    )
+                    create_chatbot_tab()
 
             demo.launch()
 

automatic_speech_recognition.py

@@ -1,6 +1,8 @@
+from functools import partial
 from huggingface_hub import InferenceClient
 from os import getenv, path, unlink
-from utils import save_audio_to_temp_file, get_model_sample_rate
+import gradio as gr
+from utils import save_audio_to_temp_file, get_model_sample_rate, request_audio
 
 def automatic_speech_recognition(client: InferenceClient, audio: tuple[int, bytes]) -> str:
     temp_file_path = None
@@ -16,3 +18,23 @@ def automatic_speech_recognition(client: InferenceClient, audio: tuple[int, byte
                 unlink(temp_file_path)
             except Exception:
                 pass # Ignore clean-up errors.
+
+
+def create_asr_tab(client: InferenceClient):
+    """Create the automatic speech recognition tab."""
+    gr.Markdown("Transcribe audio to text.")
+    audio_transcription_url_input = gr.Textbox(label="Audio URL")
+    audio_transcription_audio_request_button = gr.Button("Get Audio")
+    audio_transcription_audio_input = gr.Audio(label="Audio")
+    audio_transcription_audio_request_button.click(
+        fn=request_audio,
+        inputs=audio_transcription_url_input,
+        outputs=audio_transcription_audio_input
+    )
+    audio_transcription_generate_button = gr.Button("Transcribe")
+    audio_transcription_output = gr.Textbox(label="Text")
+    audio_transcription_generate_button.click(
+        fn=partial(automatic_speech_recognition, client),
+        inputs=audio_transcription_audio_input,
+        outputs=audio_transcription_output
+    )

chatbot.py

@@ -1,4 +1,5 @@
 from os import getenv
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoModelForSeq2SeqLM, AutoTokenizer
 from utils import get_pytorch_device, spaces_gpu
 
@@ -125,3 +126,33 @@ def chat(message: str, conversation_history: list[dict] | None) -> tuple[str, li
     conversation_history.append({"role": "assistant", "content": response})
     
     return response, conversation_history
+
+
+def create_chatbot_tab():
+    """Create the chatbot tab."""
+    gr.Markdown("Have a conversation with an AI chatbot.")
+    chatbot_history = gr.State(value=None)  # Store the conversation history.
+    chatbot_output = gr.Chatbot(label="Conversation")
+    chatbot_input = gr.Textbox(label="Your message")
+    chatbot_send_button = gr.Button("Send")
+    
+    def chat_interface(message: str, history: list | None, conversation_state: list[dict] | None):
+        """Handle chatbot interaction with Gradio chat format."""
+        if not message.strip():
+            return history, conversation_state, ""
+        response, updated_conversation = chat(message, conversation_state)  # Get response from chatbot.
+        if history is None:  # Update Gradio chat history format: list of [user_message, bot_message] pairs.
+            history = []
+        history.append([message, response])
+        return history, updated_conversation, ""  # Clear input field for the next message from the user.
+    
+    chatbot_send_button.click(
+        fn=chat_interface,
+        inputs=[chatbot_input, chatbot_output, chatbot_history],
+        outputs=[chatbot_output, chatbot_history, chatbot_input]
+    )
+    chatbot_input.submit(
+        fn=chat_interface,
+        inputs=[chatbot_input, chatbot_output, chatbot_history],
+        outputs=[chatbot_output, chatbot_history, chatbot_input]
+    )

image_classification.py

@@ -1,9 +1,11 @@
+from functools import partial
 from huggingface_hub import InferenceClient
 from os import path, unlink, getenv
+import gradio as gr
 from PIL.Image import Image
 import pandas as pd
 from pandas import DataFrame
-from utils import save_image_to_temp_file
+from utils import save_image_to_temp_file, request_image
 
 
 def image_classification(client: InferenceClient, image: Image) -> DataFrame:
@@ -22,3 +24,23 @@ def image_classification(client: InferenceClient, image: Image) -> DataFrame:
                 unlink(temp_file_path)
             except Exception:
                 pass # Ignore clean-up errors.
+
+
+def create_image_classification_tab(client: InferenceClient):
+    """Create the image classification tab."""
+    gr.Markdown("Classify a recyclable item as one of: cardboard, glass, metal, paper, plastic, or other using [Trash-Net](https://huggingface.co/prithivMLmods/Trash-Net).")
+    image_classification_url_input = gr.Textbox(label="Image URL")
+    image_classification_image_request_button = gr.Button("Get Image")
+    image_classification_image_input = gr.Image(label="Image", type="pil")
+    image_classification_image_request_button.click(
+        fn=request_image,
+        inputs=image_classification_url_input,
+        outputs=image_classification_image_input
+    )
+    image_classification_button = gr.Button("Classify")
+    image_classification_output = gr.Dataframe(label="Classification", headers=["Label", "Probability"], interactive=False)
+    image_classification_button.click(
+        fn=partial(image_classification, client),
+        inputs=image_classification_image_input,
+        outputs=image_classification_output
+    )

image_to_text.py

@@ -1,8 +1,9 @@
 import gc
 from os import getenv
+import gradio as gr
 from PIL.Image import Image
 from transformers import AutoProcessor, BlipForConditionalGeneration
-from utils import get_pytorch_device, spaces_gpu
+from utils import get_pytorch_device, spaces_gpu, request_image
 
 
 @spaces_gpu
@@ -20,3 +21,23 @@ def image_to_text(image: Image) -> list[str]:
     del model, inputs
     gc.collect()
     return results
+
+
+def create_image_to_text_tab():
+    """Create the image-to-text captioning tab."""
+    gr.Markdown("Generate a text description of an image.")
+    image_to_text_url_input = gr.Textbox(label="Image URL")
+    image_to_text_image_request_button = gr.Button("Get Image")
+    image_to_text_image_input = gr.Image(label="Image", type="pil")
+    image_to_text_image_request_button.click(
+        fn=request_image,
+        inputs=image_to_text_url_input,
+        outputs=image_to_text_image_input
+    )
+    image_to_text_button = gr.Button("Caption")
+    image_to_text_output = gr.List(label="Captions", headers=["Caption"])
+    image_to_text_button.click(
+        fn=image_to_text,
+        inputs=image_to_text_image_input,
+        outputs=image_to_text_output
+    )

text_to_image.py

@@ -1,7 +1,22 @@
+from functools import partial
 from os import getenv
+import gradio as gr
 from PIL.Image import Image
 from huggingface_hub import InferenceClient
 
 
 def text_to_image(client: InferenceClient, prompt: str) -> Image:
     return client.text_to_image(prompt, model=getenv("TEXT_TO_IMAGE_MODEL"))
+
+
+def create_text_to_image_tab(client: InferenceClient):
+    """Create the text-to-image generation tab."""
+    gr.Markdown("Generate an image from a text prompt.")
+    text_to_image_prompt = gr.Textbox(label="Prompt")
+    text_to_image_generate_button = gr.Button("Generate")
+    text_to_image_output = gr.Image(label="Image", type="pil")
+    text_to_image_generate_button.click(
+        fn=partial(text_to_image, client),
+        inputs=text_to_image_prompt,
+        outputs=text_to_image_output
+    )

text_to_speech.py

@@ -1,5 +1,6 @@
 import gc
 from os import getenv
+import gradio as gr
 from transformers import pipeline
 from utils import spaces_gpu
 
@@ -15,3 +16,16 @@ def text_to_speech(text: str) -> tuple[int, bytes]:
     del narrator
     gc.collect()
     return (result["sampling_rate"], result["audio"][0])
+
+
+def create_text_to_speech_tab():
+    """Create the text-to-speech tab."""
+    gr.Markdown("Generate speech from text.")
+    text_to_speech_text = gr.Textbox(label="Text")
+    text_to_speech_generate_button = gr.Button("Generate")
+    text_to_speech_output = gr.Audio(label="Speech")
+    text_to_speech_generate_button.click(
+        fn=text_to_speech,
+        inputs=text_to_speech_text,
+        outputs=text_to_speech_output
+    )