working

app.py

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 import os
 from openai import OpenAI
 import spacy
+import random
 
 # Load environment variables from .env file
 load_dotenv()
@@ -33,45 +34,26 @@ headers = {"Authorization": f"Bearer {HF_TOKEN}"}
 # Global variable to control debug printing
 DEBUG_MODE = True
 
-def debug_print(*args, **kwargs):
-    if DEBUG_MODE:
-        print(*args, **kwargs)
-
-def split_sentences_ginza(input_text):
-    nlp = spacy.load("ja_core_news_sm")
-    doc = nlp(input_text)
-    sentences = [sent.text for sent in doc.sents]
-    return sentences
 
-def query_hf(payload, model_name):
-    # HTTP POST Request
-    response = requests.post(API_URL+model_name, headers=headers, json=payload)
-    return response.json()
 
-def translate_hf(input_text):
-    debug_print("Translating... ", input_text)
+try:
+    file_path = "momotaro.txt"
+    # Open the file in read mode ('r')
+    with open(file_path, 'r') as file:
+        # Read the entire content of the file into a string
+        file_content = file.read()
 
-    sentences = split_sentences_ginza(input_text)  # split into sentences
-    translated_sentences = []
 
-    debug_print("Split sentences... ", sentences)
+except Exception as e:
+    print( "Error loading short story file.", str(e))
+   
+learning_content = file_content
 
-    for sentence in sentences:
-        if sentence.strip():  # Ensure sentence is not empty
-            # API Request for each sentence:
-            response = query_hf({
-                "inputs": sentence.strip(),
-                "options": {"wait_for_model": True}
-            }, "Helsinki-NLP/opus-mt-ja-en")
 
-            debug_print("response: ", response)
-            translated_sentence = response[0]["translation_text"]
-            translated_sentences.append(translated_sentence)
+def debug_print(*args, **kwargs):
+    if DEBUG_MODE:
+        print(*args, **kwargs)
 
-    # Join the translated sentences
-    translation = ' '.join(translated_sentences)
-
-    return translation
 
 
 def translate_openai(input_text):
@@ -134,8 +116,8 @@ def assess(original_japanese, student_translation):
 
 assessor = gr.Interface(fn=assess,
                           inputs=[
-                              gr.Textbox(label="Japanese Sentence Input", placeholder="Input text to be translated", lines=1, value="これは例です"),#example_Japanese),#"
-                              gr.Textbox(label="Student's Translation Attempt", placeholder="Input your English translation", lines=1, value="This is an example")#"This is an example")
+                              gr.Textbox(label="Learning Content", placeholder="Enter content to focus on here", lines=4, value=learning_content),#example_Japanese),#"
+                              gr.Textbox(label="Student Data", placeholder="Enter student data here", lines=4, value="EFL Learner")#"This is an example")
                           ],
                           outputs=[
                               gr.Textbox(label="Machine Generated Translation"),
@@ -145,4 +127,69 @@ assessor = gr.Interface(fn=assess,
                           description="Enter a Japanese sentence and your English translation attempt to receive evaluation feedback."
                           )
 
-assessor.launch(debug=True, share=True)
+
+def respond(learner_data, learning_content, teacher_prompt, message, chat_history):
+  
+    prompt = (
+        f"Teacher prompt: {teacher_prompt}\n"
+        f"Learner data: {learner_data}\n"
+        f"Learning content: {learning_content}\n"
+        
+        f"Student: {message}\n"
+        "Chatbot:"
+    )
+    
+    # Call the OpenAI API
+    response = client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": prompt,
+            }
+        ],
+        model="gpt-3.5-turbo",
+        temperature=0.7,
+        max_tokens=150,
+        stop=["\n", " Student:", " Chatbot:"],  # Stop generating if these patterns are found
+      )
+
+
+    
+    # Extract the text from the response
+    bot_message = response.choices[0].message.content
+
+    chat_history.append((message, bot_message))
+    debug_print(chat_history)
+    return chat_history
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        learner_data = gr.Textbox(label="Learner Data", placeholder="Enter learner data here...", lines=4, value="Honoka is a Japanese EFL student.")
+        learning_content = gr.Textbox(label="Learning Content", placeholder="Enter learning content here...", lines=4, value=learning_content)
+        teacher_prompt = gr.Textbox(label="Teacher Prompt", placeholder="Enter chat guidance here...", lines=4, 
+                                    value="You are a professional EFL teacher. Guide the conversation to discuss the learning content below.")
+    
+
+    chatbot = gr.Chatbot()
+
+    
+
+    with gr.Row():
+        msg = gr.Textbox(label="Your Message", placeholder="Type your message here...")
+        submit_button = gr.Button("Send")
+
+    submit_button.click(
+        respond,
+        inputs=[learner_data, learning_content, teacher_prompt, msg, chatbot],
+        outputs=chatbot,
+    )
+
+
+    #msg = gr.Textbox(placeholder="Type your message here...")
+    clear = gr.ClearButton([msg])
+    
+    #msg.submit(respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
+
+
+if __name__ == "__main__":
+    demo.launch(debug=True)