Reapplying missing title and buttons and clickable URLs (#5)

- Reapplying missing title and buttons and clickable URLs (8c25be179d6e05b0b54577d756bfaeb2b37ed880)

app.py

@@ -1,70 +1,79 @@
 import gradio as gr
-from transformers import pipeline, T5Tokenizer, T5ForConditionalGeneration
+from transformers import T5ForConditionalGeneration, T5Tokenizer
 
 # Load model and tokenizer
 model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small")
 tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
 
-# Summarize Legal Text function
-def summarize_legal_text(input_text, max_new_tokens, temperature):
-    input_ids = tokenizer(input_text, return_tensors="pt").input_ids
-    summary_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, temperature=temperature)
-    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+# Function for Correct Raw HTR
+def correct_htr(text, max_new_tokens, temperature):
+    inputs = tokenizer(text, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# Correct HTR function
-def correct_htr_text(input_text, max_new_tokens, temperature):
-    input_ids = tokenizer(input_text, return_tensors="pt").input_ids
-    output_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, temperature=temperature)
-    return tokenizer.decode(output_ids[0], skip_special_tokens=True)
+# Function for Summarize Legal Text
+def summarize_legal_text(text, max_new_tokens, temperature):
+    prompt = "summarize: " + text
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# Answer Legal Question function
+# Function for Answer Legal Question
 def answer_legal_question(context, question, max_new_tokens, temperature):
-    input_text = f"Answer the following question based on the context: {question}\nContext: {context}"
-    input_ids = tokenizer(input_text, return_tensors="pt").input_ids
-    output_ids = model.generate(input_ids, max_new_tokens=max_new_tokens, temperature=temperature)
-    return tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    prompt = f"question: {question} context: {context}"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# Gradio Interface
+# Gradio Interface Setup
 with gr.Blocks() as demo:
+    # Title and clickable buttons with URLs
+    gr.Markdown("# Flan-T5 Legal Assistant")
+    
+    with gr.Row():
+        gr.Markdown('[Admiralty Court Legal Glossary](http://www.marinelives.org/wiki/Tools:_Admiralty_court_legal_glossary)')
+        gr.Markdown('[HCA 13/70 Ground Truth](https://github.com/Addaci/HCA/blob/main/HCA_13_70_Full_Volume_Processed_Text_EDITED_Ver.1.2_18062024.txt)')
 
-    with gr.Tab("Summarize Legal Text"):
-        summarize_input = gr.Textbox(label="Input Text", placeholder="Enter legal text here...", lines=10)
-        summarize_output = gr.Textbox(label="Summarized Text", lines=10)
-        max_new_tokens_summarize = gr.Slider(10, 512, value=256, step=1, label="Max New Tokens")
-        temperature_summarize = gr.Slider(0.1, 1, value=0.5, step=0.1, label="Temperature")
-        summarize_button = gr.Button("Summarize Text")
-        
-        summarize_button.click(
-            summarize_legal_text,
-            inputs=[summarize_input, max_new_tokens_summarize, temperature_summarize],
-            outputs=summarize_output,
-        )
-
-    with gr.Tab("Correct Raw HTR Text"):
-        htr_input = gr.Textbox(label="Input HTR Text", placeholder="Enter HTR text here...", lines=5)
-        htr_output = gr.Textbox(label="Corrected HTR Text", lines=5)
-        max_new_tokens_htr = gr.Slider(10, 512, value=128, step=1, label="Max New Tokens")
-        temperature_htr = gr.Slider(0.1, 1, value=0.7, step=0.1, label="Temperature")
-        htr_button = gr.Button("Correct HTR")
+    # Tabs for different functionalities
+    with gr.Tab("Correct Raw HTR"):
+        text_input_htr = gr.Textbox(label="Textbox", placeholder="Enter text to correct")
+        text_output_htr = gr.Textbox(label="Textbox", placeholder="Corrected text will appear here")
+        max_new_tokens_htr = gr.Slider(10, 512, value=128, label="Max New Tokens")
+        temperature_htr = gr.Slider(0.1, 1.0, value=0.7, label="Temperature")
+        gr.Button("Correct HTR").click(correct_htr, inputs=[text_input_htr, max_new_tokens_htr, temperature_htr], outputs=text_output_htr)
+        gr.Button("Clear").click(lambda: "", None, text_input_htr)
 
-        htr_button.click(
-            correct_htr_text,
-            inputs=[htr_input, max_new_tokens_htr, temperature_htr],
-            outputs=htr_output,
-        )
+    with gr.Tab("Summarize Legal Text"):
+        text_input_summarize = gr.Textbox(label="Textbox", placeholder="Enter legal text to summarize")
+        text_output_summarize = gr.Textbox(label="Textbox", placeholder="Summary will appear here")
+        max_new_tokens_summarize = gr.Slider(10, 512, value=256, label="Max New Tokens")
+        temperature_summarize = gr.Slider(0.1, 1.0, value=0.5, label="Temperature")
+        gr.Button("Summarize Text").click(summarize_legal_text, inputs=[text_input_summarize, max_new_tokens_summarize, temperature_summarize], outputs=text_output_summarize)
+        gr.Button("Clear").click(lambda: "", None, text_input_summarize)
 
     with gr.Tab("Answer Legal Question"):
-        question_input_context = gr.Textbox(label="Context Text", placeholder="Enter legal context...", lines=10)
-        question_input = gr.Textbox(label="Enter your question", placeholder="Enter your question here...", lines=2)
-        question_output = gr.Textbox(label="Answer", lines=5)
-        max_new_tokens_question = gr.Slider(10, 512, value=128, step=1, label="Max New Tokens")
-        temperature_question = gr.Slider(0.1, 1, value=0.7, step=0.1, label="Temperature")
-        question_button = gr.Button("Get Answer")
-
-        question_button.click(
-            answer_legal_question,
-            inputs=[question_input_context, question_input, max_new_tokens_question, temperature_question],
-            outputs=question_output,
-        )
+        context_input = gr.Textbox(label="Textbox", placeholder="Enter legal text for context")
+        question_input = gr.Textbox(label="Textbox", placeholder="Enter your question")
+        answer_output = gr.Textbox(label="Textbox", placeholder="Answer will appear here")
+        max_new_tokens_answer = gr.Slider(10, 512, value=128, label="Max New Tokens")
+        temperature_answer = gr.Slider(0.1, 1.0, value=0.7, label="Temperature")
+        gr.Button("Get Answer").click(answer_legal_question, inputs=[context_input, question_input, max_new_tokens_answer, temperature_answer], outputs=answer_output)
+        gr.Button("Clear").click(lambda: "", None, [context_input, question_input])
 
+# Launch the demo
 demo.launch()