Update app.py

app.py

@@ -1,123 +1,21 @@
 import gradio as gr
-import os
-import time
-from haystack.document_stores import InMemoryDocumentStore
-from haystack.nodes import EmbeddingRetriever
-import pandas as pd
-from deep_translator import GoogleTranslator
 
 
-def load_qa_model():
-  document_store = InMemoryDocumentStore()
-  retriever = EmbeddingRetriever(
-    document_store=document_store,
-    embedding_model="sentence-transformers/all-MiniLM-L6-v2",
-    use_gpu=False,
-    scale_score=False,
-  )
-  # Get dataframe with columns "question", "answer" and some custom metadata
-  df = pd.read_csv('social-faq.csv', on_bad_lines='skip', delimiter=';')
-  # Minimal cleaning
-  df.fillna(value="", inplace=True)
-  df["question"] = df["question"].apply(lambda x: x.strip())
-
-  questions = list(df["question"].values)
-  df["embedding"] = retriever.embed_queries(queries=questions).tolist()
-  df = df.rename(columns={"question": "content"})
-
-  # Convert Dataframe to list of dicts and index them in our DocumentStore
-  docs_to_index = df.to_dict(orient="records")
-  document_store.write_documents(docs_to_index)
-
-  return retriever
-
-def add_text(chat_history, text):
-    chat_history = chat_history + [(text, None)]
-    return chat_history, gr.Textbox(value="", interactive=False)
-
-
-def add_file(chat_history, file):
-    chat_history = chat_history + [((file.name,), None)]
-    return chat_history
-
-
-def chatbot_response(chat_history, language):
-    
-    chat_history[-1][1] = ""
-
-    global retriever
-    global last_answer
-
-    if language == 'pt-br':
-      response = get_answers(retriever, GoogleTranslator(source='pt', target='en').translate(chat_history[-1][0]))
-      response = GoogleTranslator(source='en', target='pt').translate(response)
+def change_textbox(choice):
+    if choice == "short":
+        return gr.Textbox(lines=2, visible=True)
+    elif choice == "long":
+        return gr.Textbox(lines=8, visible=True, value="Lorem ipsum dolor sit amet")
     else:
-      response = get_answers(retriever, chat_history[-1][0])
-
-    last_answer = response
-
-    for character in response:
-      chat_history[-1][1] += character
-      time.sleep(0.01)
-      yield chat_history
-
-
-
-def get_answers(retriever, query):
-  from haystack.pipelines import FAQPipeline
-
-  pipe = FAQPipeline(retriever=retriever)
-
-  from haystack.utils import print_answers
-
-  # Run any question and change top_k to see more or less answers
-  prediction = pipe.run(query=query, params={"Retriever": {"top_k": 1}})
-
-  answers = prediction['answers']
-
-  if answers:
-    return answers[0].answer
-  else:
-    return "I don't have an answer to that question"
-
-
-
-
-retriever = load_qa_model()
-
-last_answer = ""
+        return gr.Textbox(visible=False)
 
 
 with gr.Blocks() as demo:
-    with gr.Accordion("Settings", open=False):
-      language = gr.Radio(["en-us", "pt-br"], label="Language", info="Choose the language to display the classification result and audio", value='en-us', interactive=True)
-
-
-    with gr.Tab("Help"):
-      chatbot = gr.Chatbot(
-        [],
-        elem_id="chatbot",
-        bubble_full_width=False,
-        # avatar_images=(None, "content/avatar-socialear.png"),
-      )
-
-      with gr.Row():
-        txt = gr.Textbox(
-            scale=4,
-            show_label=False,
-            placeholder="Enter text and press enter",
-            container=False,
-        )
-        inputRecord = gr.Audio(label="Record a question", source="microphone", type="filepath")
-        with gr.Column():
-          btn = gr.Button(value="Listen the answer")
-          audioOutput = gr.Audio(interactive=False)
+    radio = gr.Radio(
+        ["short", "long", "none"], label="What kind of essay would you like to write?"
+    )
+    text = gr.Textbox(lines=2, interactive=True, show_copy_button=True)
+    radio.change(fn=change_textbox, inputs=radio, outputs=text)
 
-      txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
-          chatbot_response, [chatbot, language], chatbot
-      )
-      txt_msg.then(lambda: gr.Textbox(interactive=True), None, [txt], queue=False)
-     
 
-demo.queue()
-demo.launch()
+demo.launch()