Update app.py

app.py

@@ -1,9 +1,6 @@
 import gradio as gr
 from transformers import pipeline
 from langchain import PromptTemplate
-from langchain.document_loaders import WebBaseLoader
-from langchain.schema import StrOutputParser
-from langchain.schema.prompt_template import format_document
 from langchain.chains import LLMChain
 from langchain_google_genai import ChatGoogleGenerativeAI
 import os
@@ -45,15 +42,23 @@ prompt = PromptTemplate(input_variables=['task_type', 'task_number', 'question',
 # Define the LLM chain
 chain = LLMChain(llm=llm_model, prompt=prompt)
 
-def evaluate(task_type, task_number, question, image):
-    # Ensure the image is in the correct format
-    if isinstance(image, str):
-        # Load the image if it's a URL or path
-        image = Image.open(image)
-    
-    # Process the image to extract text
-    text_content = ocr_pipe(image)
-    content = text_content[0]['generated_text']
+def evaluate(task_type, task_number, question, input_type, image=None, text=None):
+    if input_type == "Image" and image is not None:
+        # Ensure the image is in the correct format
+        if isinstance(image, str):
+            # Load the image if it's a URL or path
+            image = Image.open(image)
+        
+        # Process the image to extract text
+        text_content = ocr_pipe(image)
+        content = text_content[0]['generated_text']
+    elif input_type == "Text" and text is not None:
+        content = text
+    else:
+        return "Please provide the required input based on your selection."
+
+    # Retrieve the description for the given task type and number, or use a default value
+    task_description = description.get((task_type, task_number), "No description available for this task.")
 
     # Run the chain
     result = chain.run({
@@ -61,7 +66,7 @@ def evaluate(task_type, task_number, question, image):
         'task_number': task_number,
         'question': question,
         'content': content,
-        'description': description[(task_type, task_number)]
+        'description': task_description
     })
 
     return result
@@ -71,9 +76,17 @@ inputs = [
     gr.Dropdown(choices=["Academic", "General"], label="Test Type", value="Academic"),
     gr.Dropdown(choices=["Task 1", "Task 2"], label="Task Number", value="Task 1"),
     gr.Textbox(label="Question", value=""),
-    gr.Image(type="pil", label="Upload Image")
+    gr.Radio(choices=["Image", "Text"], label="Input Type", value="Image", id="input_type"),
+    gr.Image(type="pil", label="Upload Image", id="image_input", visible=True),
+    gr.Textbox(label="Enter Text", id="text_input", visible=False)
 ]
 
+def toggle_input(input_type):
+    if input_type == "Image":
+        return gr.update(visible=True), gr.update(visible=False)
+    else:
+        return gr.update(visible=False), gr.update(visible=True)
+
 footer_html_with_analytics = f"""
 <script async src="https://www.googletagmanager.com/gtag/js?id={tracking_id}"></script>
 <script>
@@ -106,6 +119,12 @@ outputs = gr.Markdown(label="Result")
 # Define the Gradio Blocks and Interface
 with gr.Blocks() as demo:
     gr.Markdown("# IELTS Writing Evaluation")
+    with gr.Row():
+        with gr.Column():
+            input_type_radio = gr.Radio(choices=["Image", "Text"], label="Input Type", value="Image")
+            image_input = gr.Image(type="pil", label="Upload Image", visible=True)
+            text_input = gr.Textbox(label="Enter Text", visible=False)
+        input_type_radio.change(toggle_input, input_type_radio, [image_input, text_input])
     gr.Interface(fn=evaluate, inputs=inputs, outputs=outputs)
     gr.HTML(footer_html_with_analytics)