Upload 7 files

IOHelperUtilities.py

@@ -0,0 +1,85 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/helper_utilities.ipynb.
+
+# %% auto 0
+__all__ = ['check_is_colab', 'MultiFileChooser', 'setup_drives']
+
+# %% ../nbs/helper_utilities.ipynb 3
+import ipywidgets as widgets
+from IPython.display import display, clear_output
+from functools import partial
+from ipyfilechooser import FileChooser
+import os
+
+# %% ../nbs/helper_utilities.ipynb 4
+def check_is_colab():
+    """
+    Check if the current environment is Google Colab.
+    """
+    try:
+        import google.colab
+        return True
+    except:
+        return False
+
+# %% ../nbs/helper_utilities.ipynb 7
+class MultiFileChooser:
+    def __init__(self):
+        self.fc = FileChooser('.')
+        self.fc.title = "Use the following file chooser to add each file individually.\n You can remove files by clicking the remove button."
+        self.fc.use_dir_icons = True
+        self.fc.show_only_dirs = False
+        self.selected_files = []
+        
+        self.fc.register_callback(self.file_selected)
+        
+        self.output = widgets.Output()
+        
+    def file_selected(self, chooser):
+        if self.fc.selected is not None and self.fc.selected not in self.selected_files:
+            self.selected_files.append(self.fc.selected)
+            self.update_display()
+    
+    def update_display(self):
+        with self.output:
+            clear_output()
+            for this_file in self.selected_files:
+                remove_button = widgets.Button(description="Remove", tooltip="Remove this file")
+                remove_button.on_click(partial(self.remove_file, file=this_file))
+                display(widgets.HBox([widgets.Label(value=this_file), remove_button]))
+    
+    def remove_file(self, button, this_file):
+        if this_file in self.selected_files:
+            self.selected_files.remove(this_file)
+            self.update_display()
+    
+    def display(self):
+        display(self.fc, self.output)
+    
+    def get_selected_files(self):
+        return self.selected_files
+
+# %% ../nbs/helper_utilities.ipynb 12
+def setup_drives(upload_set):
+
+    upload_set = upload_set.lower()
+    uploaded = None
+
+    # allow them to mount the drive if they chose Google Colab.
+    if upload_set == 'google drive':
+        if check_is_colab():
+            from google.colab import drive
+            drive.mount('/content/drive')
+        else:
+            raise ValueError("It looks like you're not on Google Colab. Google Drive mounting is currently only implemented for Google Colab.")
+
+    # Everything else means that they'll need to use a file chooser (including Google Drive)
+    if check_is_colab():
+        from google.colab import files
+        uploaded = files.upload()
+    else:
+        # Create file chooser and interact
+        mfc = MultiFileChooser()
+        mfc.display()
+        uploaded = mfc.get_selected_files()
+    
+    return uploaded

MediaVectorStores.py

@@ -0,0 +1,173 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/media_stores.ipynb.
+
+# %% auto 0
+__all__ = ['rawtext_to_doc_split', 'files_to_text', 'youtube_to_text', 'save_text', 'get_youtube_transcript',
+           'website_to_text_web', 'website_to_text_unstructured', 'get_document_segments', 'create_local_vector_store']
+
+# %% ../nbs/media_stores.ipynb 3
+# import libraries here
+import os
+import itertools
+
+from langchain.embeddings import OpenAIEmbeddings
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from langchain.document_loaders.generic import GenericLoader
+from langchain.document_loaders.parsers import OpenAIWhisperParser
+from langchain.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader
+from langchain.document_loaders import WebBaseLoader, UnstructuredURLLoader
+from langchain.docstore.document import Document
+
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQAWithSourcesChain
+
+# %% ../nbs/media_stores.ipynb 8
+def rawtext_to_doc_split(text, chunk_size=1500, chunk_overlap=150):
+  
+  # Quick type checking
+  if not isinstance(text, list):
+    text = [text]
+
+  # Create splitter
+  text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size,
+                                                 chunk_overlap=chunk_overlap,
+                                                 add_start_index = True)
+  
+  #Split into docs segments
+  if isinstance(text[0], Document):
+    doc_segments = text_splitter.split_documents(text)
+  else:
+    doc_segments = text_splitter.split_documents(text_splitter.create_documents(text))
+
+  # Make into one big list
+  doc_segments = list(itertools.chain(*doc_segments)) if isinstance(doc_segments[0], list) else doc_segments
+
+  return doc_segments
+
+# %% ../nbs/media_stores.ipynb 16
+## A single File
+def _file_to_text(single_file, chunk_size = 1000, chunk_overlap=150):
+
+  # Create loader and get segments
+  loader = UnstructuredFileLoader(single_file)
+  doc_segments = loader.load_and_split(RecursiveCharacterTextSplitter(chunk_size=chunk_size,
+                                                                      chunk_overlap=chunk_overlap,
+                                                                      add_start_index=True))
+  return doc_segments
+
+
+## Multiple files
+def files_to_text(files_list, chunk_size=1000, chunk_overlap=150):
+  
+  # Quick type checking
+  if not isinstance(files_list, list):
+    files_list = [files_list]
+
+  # This is currently a fix because the UnstructuredFileLoader expects a list of files yet can't split them correctly yet
+  all_segments = [_file_to_text(single_file, chunk_size=chunk_size, chunk_overlap=chunk_overlap) for single_file in files_list]
+  all_segments = list(itertools.chain(*all_segments)) if isinstance(all_segments[0], list) else all_segments
+
+  return all_segments
+
+# %% ../nbs/media_stores.ipynb 20
+def youtube_to_text(urls, save_dir = "content"):
+  # Transcribe the videos to text
+  # save_dir: directory to save audio files
+
+  if not isinstance(urls, list):
+    urls = [urls]
+  
+  youtube_loader = GenericLoader(YoutubeAudioLoader(urls, save_dir), OpenAIWhisperParser())
+  youtube_docs = youtube_loader.load()
+  
+  return youtube_docs
+
+# %% ../nbs/media_stores.ipynb 24
+def save_text(text, text_name = None):
+  if not text_name:
+    text_name = text[:20]
+  text_path = os.path.join("/content",text_name+".txt")
+  
+  with open(text_path, "x") as f:
+    f.write(text)
+  # Return the location at which the transcript is saved
+  return text_path
+
+# %% ../nbs/media_stores.ipynb 25
+def get_youtube_transcript(yt_url, save_transcript = False, temp_audio_dir = "sample_data"):
+  # Transcribe the videos to text and save to file in /content
+  # save_dir: directory to save audio files
+
+  youtube_docs = youtube_to_text(yt_url, save_dir = temp_audio_dir)
+  
+  # Combine doc
+  combined_docs = [doc.page_content for doc in youtube_docs]
+  combined_text = " ".join(combined_docs)
+  
+  # Save text to file
+  video_path = youtube_docs[0].metadata["source"]
+  youtube_name = os.path.splitext(os.path.basename(video_path))[0]
+
+  save_path = None
+  if save_transcript:
+    save_path = save_text(combined_text, youtube_name)
+  
+  return youtube_docs, save_path
+
+# %% ../nbs/media_stores.ipynb 27
+def website_to_text_web(url, chunk_size = 1500, chunk_overlap=100):
+  
+    # Url can be a single string or list
+    website_loader = WebBaseLoader(url)
+    website_raw = website_loader.load()
+
+    website_data = rawtext_to_doc_split(website_raw, chunk_size = chunk_size, chunk_overlap=chunk_overlap)
+  
+    # Combine doc
+    return website_data
+
+# %% ../nbs/media_stores.ipynb 33
+def website_to_text_unstructured(web_urls, chunk_size = 1500, chunk_overlap=100):
+
+    # Make sure it's a list
+    if not isinstance(web_urls, list):
+        web_urls = [web_urls]
+  
+    # Url can be a single string or list
+    website_loader = UnstructuredURLLoader(web_urls)
+    website_raw = website_loader.load()
+
+    website_data = rawtext_to_doc_split(website_raw, chunk_size = chunk_size, chunk_overlap=chunk_overlap)
+  
+    # Return individual docs or list
+    return website_data
+
+# %% ../nbs/media_stores.ipynb 45
+def get_document_segments(context_info, data_type, chunk_size = 1500, chunk_overlap=100):
+
+    load_fcn = None
+    addtnl_params = {'chunk_size': chunk_size, 'chunk_overlap': chunk_overlap}
+
+    # Define function use to do the loading
+    if data_type == 'text':
+        load_fcn = rawtext_to_doc_split
+    elif data_type == 'web_page':
+        load_fcn = website_to_text_unstructured
+    elif data_type == 'youtube_video':
+        load_fcn = youtube_to_text
+    else:
+        load_fcn = files_to_text
+    
+    # Get the document segments
+    doc_segments = load_fcn(context_info, **addtnl_params)
+
+    return doc_segments
+
+# %% ../nbs/media_stores.ipynb 47
+def create_local_vector_store(document_segments, **retriever_kwargs):
+    embeddings = OpenAIEmbeddings()
+    db = Chroma.from_documents(document_segments, embeddings)
+    retriever = db.as_retriever(**retriever_kwargs)
+    
+    return db, retriever

PromptInteractionBase.py

@@ -0,0 +1,191 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/prompt_interaction_base.ipynb.
+
+# %% auto 0
+__all__ = ['SYSTEM_TUTOR_TEMPLATE', 'HUMAN_RESPONSE_TEMPLATE', 'HUMAN_RETRIEVER_RESPONSE_TEMPLATE', 'DEFAULT_ASSESSMENT_MSG',
+           'DEFAULT_LEARNING_OBJS_MSG', 'DEFAULT_CONDENSE_PROMPT_TEMPLATE', 'DEFAULT_QUESTION_PROMPT_TEMPLATE',
+           'DEFAULT_COMBINE_PROMPT_TEMPLATE', 'create_model', 'set_openai_key', 'create_base_tutoring_prompt',
+           'get_tutoring_prompt', 'get_tutoring_answer', 'create_tutor_mdl_chain']
+
+# %% ../nbs/prompt_interaction_base.ipynb 3
+from langchain.chat_models import ChatOpenAI
+from langchain.llms import OpenAI
+
+from langchain import PromptTemplate
+from langchain.prompts import ChatPromptTemplate, PromptTemplate
+from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate
+from langchain.chains import LLMChain, ConversationalRetrievalChain, RetrievalQAWithSourcesChain
+from langchain.chains.base import Chain
+
+from getpass import getpass
+
+import os
+
+# %% ../nbs/prompt_interaction_base.ipynb 5
+def create_model(openai_mdl='gpt-3.5-turbo-16k', temperature=0.1, **chatopenai_kwargs):
+    llm = ChatOpenAI(model_name = openai_mdl, temperature=temperature, **chatopenai_kwargs)
+
+    return llm
+
+# %% ../nbs/prompt_interaction_base.ipynb 6
+def set_openai_key():
+    openai_api_key = getpass()
+    os.environ["OPENAI_API_KEY"] = openai_api_key
+
+    return
+
+# %% ../nbs/prompt_interaction_base.ipynb 10
+# Create system prompt template
+SYSTEM_TUTOR_TEMPLATE = ("You are a world-class tutor helping students to perform better on oral and written exams though interactive experiences. " +
+                         "When assessing and evaluating students, you always ask one question at a time, and wait for the student's response before " +
+                         "providing them with feedback. Asking one question at a time, waiting for the student's response, and then commenting " +
+                         "on the strengths and weaknesses of their responses (when appropriate) is what makes you such a sought-after, world-class tutor.")
+
+# Create a human response template
+HUMAN_RESPONSE_TEMPLATE = ("I'm trying to better understand the text provided below. {assessment_request} The learning objectives to be assessed are: " +
+                           "{learning_objectives}. Although I may request more than one assessment question, you should " +
+                           "only provide ONE question in you initial response. Do not include the answer in your response. " +
+                           "If I get an answer wrong, provide me with an explanation of why it was incorrect, and then give me additional " +
+                           "chances to respond until I get the correct choice. Explain why the correct choice is right. " +
+                           "The text that you will base your questions on is as follows: {context}.")
+
+HUMAN_RETRIEVER_RESPONSE_TEMPLATE = ("I want to master the topics based on the excerpts of the text below. Given the following extracted text from long documents, {assessment_request} The learning objectives to be assessed are: " +
+                           "{learning_objectives}. Although I may request more than one assessment question, you should " +
+                           "only provide ONE question in you initial response. Do not include the answer in your response. " +
+                           "If I get an answer wrong, provide me with an explanation of why it was incorrect, and then give me additional " +
+                           "chances to respond until I get the correct choice. Explain why the correct choice is right. " +
+                           "The extracted text from long documents are as follows: {summaries}.")
+
+def create_base_tutoring_prompt(system_prompt=None, human_prompt=None):
+
+    #setup defaults using defined values
+    if system_prompt == None:
+        system_prompt = PromptTemplate(template = SYSTEM_TUTOR_TEMPLATE,
+                          input_variables = [])
+    
+    if human_prompt==None:
+        human_prompt = PromptTemplate(template = HUMAN_RESPONSE_TEMPLATE,
+                           input_variables=['assessment_request', 'learning_objectives', 'context'])
+
+    # Create prompt messages
+    system_tutor_msg = SystemMessagePromptTemplate(prompt=system_prompt)
+    human_tutor_msg = HumanMessagePromptTemplate(prompt= human_prompt)
+
+    # Create ChatPromptTemplate
+    chat_prompt = ChatPromptTemplate.from_messages([system_tutor_msg, human_tutor_msg])
+
+    return chat_prompt
+
+# %% ../nbs/prompt_interaction_base.ipynb 14
+DEFAULT_ASSESSMENT_MSG = 'Please design a 5 question short answer quiz about the provided text.'
+DEFAULT_LEARNING_OBJS_MSG = 'Identify and comprehend the important topics and underlying messages and connections within the text'
+
+def get_tutoring_prompt(context, chat_template=None, assessment_request = None, learning_objectives = None, **kwargs):
+
+    # set defaults
+    if chat_template is None:
+        chat_template = create_base_tutoring_prompt()
+    else:
+        if not all([prompt_var in chat_template.input_variables
+                    for prompt_var in ['context', 'assessment_request', 'learning_objectives']]):
+            raise KeyError('''It looks like you may have a custom chat_template. Either include context, assessment_request, and learning objectives
+                           as input variables or create your own tutoring prompt.''')
+
+    if assessment_request is None and 'assessment_request':
+        assessment_request = DEFAULT_ASSESSMENT_MSG
+    
+    if learning_objectives is None:
+        learning_objectives = DEFAULT_LEARNING_OBJS_MSG
+    
+    # compose final prompt
+    tutoring_prompt = chat_template.format_prompt(context=context,
+                                                assessment_request = assessment_request,
+                                                learning_objectives = learning_objectives,
+                                                **kwargs)
+    
+    return tutoring_prompt
+
+
+# %% ../nbs/prompt_interaction_base.ipynb 18
+def get_tutoring_answer(context, tutor_mdl, chat_template=None, assessment_request=None, learning_objectives=None, return_dict=False, call_kwargs={}, input_kwargs={}):
+    
+ # Get answer from chat
+    
+    # set defaults
+    if assessment_request is None:
+            assessment_request = DEFAULT_ASSESSMENT_MSG
+    if learning_objectives is None:
+        learning_objectives = DEFAULT_LEARNING_OBJS_MSG
+    
+    common_inputs = {'assessment_request':assessment_request, 'learning_objectives':learning_objectives}
+    
+    # get answer based on interaction type
+    if isinstance(tutor_mdl, ChatOpenAI):
+        human_ask_prompt = get_tutoring_prompt(context, chat_template, assessment_request, learning_objectives)
+        tutor_answer = tutor_mdl(human_ask_prompt.to_messages())
+
+        if not return_dict:
+            final_answer = tutor_answer.content
+    
+    elif isinstance(tutor_mdl, Chain):
+        if isinstance(tutor_mdl, RetrievalQAWithSourcesChain):
+            if 'question' not in input_kwargs.keys():
+                common_inputs['question'] = assessment_request
+            final_inputs = {**common_inputs, **input_kwargs}
+        else:
+            common_inputs['context'] = context
+            final_inputs = {**common_inputs, **input_kwargs}
+         
+        # get answer
+        tutor_answer = tutor_mdl(final_inputs, **call_kwargs)
+        final_answer = tutor_answer
+
+        if not return_dict:
+            final_answer = final_answer['answer']
+    
+    else:
+        raise NotImplementedError(f"tutor_mdl of type {type(tutor_mdl)} is not supported.")
+
+    return final_answer
+
+# %% ../nbs/prompt_interaction_base.ipynb 19
+DEFAULT_CONDENSE_PROMPT_TEMPLATE = ("Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, " + 
+                                    "in its original language.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:")
+
+DEFAULT_QUESTION_PROMPT_TEMPLATE  = ("Use the following portion of a long document to see if any of the text is relevant to creating a response to the question." +
+                                     "\nReturn any relevant text verbatim.\n{context}\nQuestion: {question}\nRelevant text, if any:")
+
+DEFAULT_COMBINE_PROMPT_TEMPLATE = ("Given the following extracted parts of a long document and the given prompt, create a final answer with references ('SOURCES'). "+
+                                   "If you don't have a response, just say that you are unable to come up with a response. "+
+                                   "\nSOURCES:\n\nQUESTION: {question}\n=========\n{summaries}\n=========\nFINAL ANSWER:'")
+
+def create_tutor_mdl_chain(kind='llm', mdl=None, prompt_template = None, **kwargs):
+    
+    #Validate parameters
+    if mdl is None:
+        mdl = create_model()
+    kind = kind.lower()
+    
+    #Create model chain
+    if kind == 'llm':
+        if prompt_template is None:
+            prompt_template = create_base_tutoring_prompt()
+        mdl_chain = LLMChain(llm=mdl, prompt=prompt_template, **kwargs)
+    elif kind == 'conversational':
+        if prompt_template is None:
+            prompt_template = PromptTemplate.from_template(DEFAULT_CONDENSE_PROMPT_TEMPLATE)
+        mdl_chain = ConversationalRetrieverChain.from_llm(mdl, condense_question_prompt = prompt_template, **kwargs)
+    elif kind == 'retrieval_qa':
+        if prompt_template is None:
+
+            #Create custom human prompt to take in summaries
+            human_prompt = PromptTemplate(template = HUMAN_RETRIEVER_RESPONSE_TEMPLATE,
+                           input_variables=['assessment_request', 'learning_objectives', 'summaries'])
+            prompt_template = create_base_tutoring_prompt(human_prompt=human_prompt)
+            
+        #Create the combination prompt and model
+        question_template = PromptTemplate.from_template(DEFAULT_QUESTION_PROMPT_TEMPLATE)
+        mdl_chain = RetrievalQAWithSourcesChain.from_llm(llm=mdl, question_prompt=question_template, combine_prompt = prompt_template, **kwargs)
+    else:
+        raise NotImplementedError(f"Model kind {kind} not implemented")
+    
+    return mdl_chain

SelfStudyPrompts.py

@@ -0,0 +1,75 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/self_study_prompts.ipynb.
+
+# %% auto 0
+__all__ = ['MC_QUIZ_DEFAULT', 'SHORT_ANSWER_DEFAULT', 'FILL_BLANK_DEFAULT', 'SEQUENCING_DEFAULT', 'RELATIONSHIP_DEFAULT',
+           'CONCEPTS_DEFAULT', 'REAL_WORLD_EXAMPLE_DEFAULT', 'RANDOMIZED_QUESTIONS_DEFAULT', 'SELF_STUDY_PROMPT_NAMES',
+           'SELF_STUDY_DEFAULTS', 'list_all_self_study_prompt_keys', 'list_all_self_study_prompts',
+           'list_default_self_prompt_varnames', 'print_all_self_study_prompts']
+
+# %% ../nbs/self_study_prompts.ipynb 4
+# used for pretty display
+import pandas as pd
+
+# %% ../nbs/self_study_prompts.ipynb 5
+MC_QUIZ_DEFAULT = "Please design a 5 question multiple choice quiz about the provided text."
+
+SHORT_ANSWER_DEFAULT = ("Please design a 5 question short answer quiz about the provided text. "
+                        "The question types should be short answer. Expect the correct answers to be a few sentences long.")
+
+FILL_BLANK_DEFAULT = """Create a 5 question fill in the blank quiz referencing parts of the provided text.
+The "blank" part of the question should appear as "________". The answers should reflect what word(s) should go in the blank an accurate statement.
+An example is as follows: "The author of the book is ______." The question should be a statement.
+"""
+
+SEQUENCING_DEFAULT = """Create a 5 question questionnaire that will ask me to recall the steps or sequence of events
+in the provided text."""
+
+RELATIONSHIP_DEFAULT = ("Create a 5 question quiz for the student that asks the student to identify relationships between"
+                        "topics or concepts that are important to understanding this text.")
+
+CONCEPTS_DEFAULT = """ Design a 5 question quiz that asks me about definitions or concepts of importance in the provided text."""
+
+REAL_WORLD_EXAMPLE_DEFAULT = """Demonstrate how the provided context can be applied to solve a real world problem.
+Ask me questions about how the demonstration you provided relates to solving a real world problem."""
+
+RANDOMIZED_QUESTIONS_DEFAULT = """Generate a high-quality assessment consisting of 5 varied questions,
+each of different types (open-ended, multiple choice, short answer, analogies, etc.)"""
+
+SELF_STUDY_PROMPT_NAMES = ['MC_QUIZ_DEFAULT',
+'SHORT_ANSWER_DEFAULT',
+'FILL_BLANK_DEFAULT',
+'SEQUENCING_DEFAULT',
+'RELATIONSHIP_DEFAULT',
+'CONCEPTS_DEFAULT',
+'REAL_WORLD_EXAMPLE_DEFAULT',
+'RANDOMIZED_QUESTIONS_DEFAULT']
+
+# %% ../nbs/self_study_prompts.ipynb 7
+# Define self study dictionary for lookup
+SELF_STUDY_DEFAULTS = {'mc': MC_QUIZ_DEFAULT,
+'short_answer': SHORT_ANSWER_DEFAULT,
+'fill_blank': FILL_BLANK_DEFAULT,
+'sequencing': SEQUENCING_DEFAULT,
+'relationships': RELATIONSHIP_DEFAULT,
+'concepts': CONCEPTS_DEFAULT,
+'real_world_example': REAL_WORLD_EXAMPLE_DEFAULT,
+'randomized_questions': RANDOMIZED_QUESTIONS_DEFAULT
+} 
+
+# Return list of all self study prompts
+def list_all_self_study_prompt_keys():
+    return list(SELF_STUDY_DEFAULTS.keys())
+
+def list_all_self_study_prompts():
+    return list(SELF_STUDY_DEFAULTS.values())
+    
+# Return list of all self study variable names
+def list_default_self_prompt_varnames():
+    return SELF_STUDY_PROMPT_NAMES
+
+# Print as a table
+def print_all_self_study_prompts():
+    with pd.option_context('max_colwidth', None):
+        display(pd.DataFrame({'SELF_STUDY_DEFAULTS key': list(SELF_STUDY_DEFAULTS.keys()),
+        'Prompt': list(SELF_STUDY_DEFAULTS.values())}))
+

__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

_modidx.py

@@ -0,0 +1,93 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/lo-achievement',
+                'doc_host': 'https://vanderbilt-data-science.github.io',
+                'git_url': 'https://github.com/vanderbilt-data-science/lo-achievement',
+                'lib_path': 'ai_classroom_suite'},
+  'syms': { 'ai_classroom_suite.IOHelperUtilities': { 'ai_classroom_suite.IOHelperUtilities.MultiFileChooser': ( 'helper_utilities.html#multifilechooser',
+                                                                                                                 'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.__init__': ( 'helper_utilities.html#multifilechooser.__init__',
+                                                                                                                          'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.display': ( 'helper_utilities.html#multifilechooser.display',
+                                                                                                                         'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.file_selected': ( 'helper_utilities.html#multifilechooser.file_selected',
+                                                                                                                               'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.get_selected_files': ( 'helper_utilities.html#multifilechooser.get_selected_files',
+                                                                                                                                    'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.remove_file': ( 'helper_utilities.html#multifilechooser.remove_file',
+                                                                                                                             'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.MultiFileChooser.update_display': ( 'helper_utilities.html#multifilechooser.update_display',
+                                                                                                                                'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.check_is_colab': ( 'helper_utilities.html#check_is_colab',
+                                                                                                               'ai_classroom_suite/IOHelperUtilities.py'),
+                                                      'ai_classroom_suite.IOHelperUtilities.setup_drives': ( 'helper_utilities.html#setup_drives',
+                                                                                                             'ai_classroom_suite/IOHelperUtilities.py')},
+            'ai_classroom_suite.MediaVectorStores': { 'ai_classroom_suite.MediaVectorStores._file_to_text': ( 'media_stores.html#_file_to_text',
+                                                                                                              'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.create_local_vector_store': ( 'media_stores.html#create_local_vector_store',
+                                                                                                                          'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.files_to_text': ( 'media_stores.html#files_to_text',
+                                                                                                              'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.get_document_segments': ( 'media_stores.html#get_document_segments',
+                                                                                                                      'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.get_youtube_transcript': ( 'media_stores.html#get_youtube_transcript',
+                                                                                                                       'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.rawtext_to_doc_split': ( 'media_stores.html#rawtext_to_doc_split',
+                                                                                                                     'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.save_text': ( 'media_stores.html#save_text',
+                                                                                                          'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.website_to_text_unstructured': ( 'media_stores.html#website_to_text_unstructured',
+                                                                                                                             'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.website_to_text_web': ( 'media_stores.html#website_to_text_web',
+                                                                                                                    'ai_classroom_suite/MediaVectorStores.py'),
+                                                      'ai_classroom_suite.MediaVectorStores.youtube_to_text': ( 'media_stores.html#youtube_to_text',
+                                                                                                                'ai_classroom_suite/MediaVectorStores.py')},
+            'ai_classroom_suite.PromptInteractionBase': { 'ai_classroom_suite.PromptInteractionBase.create_base_tutoring_prompt': ( 'prompt_interaction_base.html#create_base_tutoring_prompt',
+                                                                                                                                    'ai_classroom_suite/PromptInteractionBase.py'),
+                                                          'ai_classroom_suite.PromptInteractionBase.create_model': ( 'prompt_interaction_base.html#create_model',
+                                                                                                                     'ai_classroom_suite/PromptInteractionBase.py'),
+                                                          'ai_classroom_suite.PromptInteractionBase.create_tutor_mdl_chain': ( 'prompt_interaction_base.html#create_tutor_mdl_chain',
+                                                                                                                               'ai_classroom_suite/PromptInteractionBase.py'),
+                                                          'ai_classroom_suite.PromptInteractionBase.get_tutoring_answer': ( 'prompt_interaction_base.html#get_tutoring_answer',
+                                                                                                                            'ai_classroom_suite/PromptInteractionBase.py'),
+                                                          'ai_classroom_suite.PromptInteractionBase.get_tutoring_prompt': ( 'prompt_interaction_base.html#get_tutoring_prompt',
+                                                                                                                            'ai_classroom_suite/PromptInteractionBase.py'),
+                                                          'ai_classroom_suite.PromptInteractionBase.set_openai_key': ( 'prompt_interaction_base.html#set_openai_key',
+                                                                                                                       'ai_classroom_suite/PromptInteractionBase.py')},
+            'ai_classroom_suite.SelfStudyPrompts': { 'ai_classroom_suite.SelfStudyPrompts.list_all_self_study_prompt_keys': ( 'self_study_prompts.html#list_all_self_study_prompt_keys',
+                                                                                                                              'ai_classroom_suite/SelfStudyPrompts.py'),
+                                                     'ai_classroom_suite.SelfStudyPrompts.list_all_self_study_prompts': ( 'self_study_prompts.html#list_all_self_study_prompts',
+                                                                                                                          'ai_classroom_suite/SelfStudyPrompts.py'),
+                                                     'ai_classroom_suite.SelfStudyPrompts.list_default_self_prompt_varnames': ( 'self_study_prompts.html#list_default_self_prompt_varnames',
+                                                                                                                                'ai_classroom_suite/SelfStudyPrompts.py'),
+                                                     'ai_classroom_suite.SelfStudyPrompts.print_all_self_study_prompts': ( 'self_study_prompts.html#print_all_self_study_prompts',
+                                                                                                                           'ai_classroom_suite/SelfStudyPrompts.py')},
+            'ai_classroom_suite.self_study_app': { 'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor': ( 'gradio_application.html#slightlydelusionaltutor',
+                                                                                                                  'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.__init__': ( 'gradio_application.html#slightlydelusionaltutor.__init__',
+                                                                                                                           'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.add_user_message': ( 'gradio_application.html#slightlydelusionaltutor.add_user_message',
+                                                                                                                                   'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.forget_conversation': ( 'gradio_application.html#slightlydelusionaltutor.forget_conversation',
+                                                                                                                                      'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.get_sources_memory': ( 'gradio_application.html#slightlydelusionaltutor.get_sources_memory',
+                                                                                                                                     'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.get_tutor_reply': ( 'gradio_application.html#slightlydelusionaltutor.get_tutor_reply',
+                                                                                                                                  'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.SlightlyDelusionalTutor.initialize_llm': ( 'gradio_application.html#slightlydelusionaltutor.initialize_llm',
+                                                                                                                                 'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.add_user_message': ( 'gradio_application.html#add_user_message',
+                                                                                                           'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.create_reference_store': ( 'gradio_application.html#create_reference_store',
+                                                                                                                 'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.disable_until_done': ( 'gradio_application.html#disable_until_done',
+                                                                                                             'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.embed_key': ( 'gradio_application.html#embed_key',
+                                                                                                    'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.get_tutor_reply': ( 'gradio_application.html#get_tutor_reply',
+                                                                                                          'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.prompt_select': ( 'gradio_application.html#prompt_select',
+                                                                                                        'ai_classroom_suite/self_study_app.py'),
+                                                   'ai_classroom_suite.self_study_app.save_chatbot_dialogue': ( 'gradio_application.html#save_chatbot_dialogue',
+                                                                                                                'ai_classroom_suite/self_study_app.py')}}}

self_study_app.py

@@ -0,0 +1,358 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/gradio_application.ipynb.
+
+# %% auto 0
+__all__ = ['save_pdf', 'save_json', 'save_txt', 'save_csv', 'num_sources', 'css', 'save_chatbot_dialogue',
+           'SlightlyDelusionalTutor', 'embed_key', 'create_reference_store', 'prompt_select', 'add_user_message',
+           'get_tutor_reply', 'disable_until_done']
+
+# %% ../nbs/gradio_application.ipynb 9
+import gradio as gr
+from functools import partial
+import pandas as pd
+import os
+
+from .PromptInteractionBase import *
+from .IOHelperUtilities import *
+from .SelfStudyPrompts import *
+from .MediaVectorStores import *
+
+# %% ../nbs/gradio_application.ipynb 13
+def save_chatbot_dialogue(chat_tutor, save_type):
+
+    formatted_convo = pd.DataFrame(chat_tutor.conversation_memory, columns=['user', 'chatbot'])
+
+    output_fname = f'tutoring_conversation.{save_type}'
+
+    if save_type == 'csv':
+        formatted_convo.to_csv(output_fname, index=False)
+    elif save_type == 'json':
+        formatted_convo.to_json(output_fname, orient='records')
+    elif save_type == 'txt':
+        temp = formatted_convo.apply(lambda x: 'User: {0}\nAI: {1}'.format(x[0], x[1]), axis=1)
+        temp = '\n\n'.join(temp.tolist())
+        with open(output_fname, 'w') as f:
+            f.write(temp)
+    else:
+        gr.update(value=None, visible=False)
+    
+    return gr.update(value=output_fname, visible=True)
+
+save_pdf = partial(save_chatbot_dialogue, save_type='pdf')
+save_json = partial(save_chatbot_dialogue, save_type='json')
+save_txt = partial(save_chatbot_dialogue, save_type='txt')
+save_csv = partial(save_chatbot_dialogue, save_type='csv')
+
+
+# %% ../nbs/gradio_application.ipynb 16
+class SlightlyDelusionalTutor:
+    # create basic initialization function
+    def __init__(self, model_name = None):
+
+        # create default model name
+        if model_name is None:
+            self.model_name = 'gpt-3.5-turbo-16k'
+
+        self.chat_llm = None
+        self.tutor_chain = None
+        self.vector_store = None
+        self.vs_retriever = None
+        self.conversation_memory = []
+        self.sources_memory = []
+        self.flattened_conversation = ''
+        self.api_key_valid = False
+        self.learning_objectives = None
+        self.openai_auth = ''
+    
+    def initialize_llm(self):
+
+        if self.openai_auth:
+            try:
+                self.chat_llm = create_model(self.model_name, openai_api_key = self.openai_auth)
+                self.api_key_valid = True
+            except Exception as e:
+                print(e)
+                self.api_key_valid = False
+        else:
+            print("Please provide an OpenAI API key and press Enter.")
+
+    def add_user_message(self, user_message):
+        self.conversation_memory.append([user_message, None])
+        self.flattened_conversation = self.flattened_conversation + '\n\n' + 'User: ' + user_message
+    
+    def get_tutor_reply(self, **input_kwargs):
+
+        if not self.conversation_memory:
+            return "Please type something to start the conversation."
+        
+        # we want to have a different vector comparison for reference lookup after the topic is first used
+        if len(self.conversation_memory) > 1:
+            if 'question' in input_kwargs.keys():
+                if input_kwargs['question']:
+                    input_kwargs['question'] = self.conversation_memory[-1][0] + ' keeping in mind I want to learn about ' + input_kwargs['question']
+                else:
+                    input_kwargs['question'] = self.conversation_memory[-1][0]
+
+        # get tutor message
+        tutor_message = get_tutoring_answer(None,
+                                     self.tutor_chain,
+                                     assessment_request = self.flattened_conversation + 'First, please provide your feedback on my previous answer if I was answering a question, otherwise, respond appropriately to my statement. Then, help me with the following:' + self.conversation_memory[-1][0],
+                                     learning_objectives = self.learning_objectives,
+                                     return_dict=True,
+                                     **input_kwargs)
+
+        # add tutor message to conversation memory
+        self.conversation_memory[-1][1] = tutor_message['answer']
+        self.flattened_conversation = self.flattened_conversation + '\nAI: ' + tutor_message['answer']
+        self.sources_memory.append(tutor_message['source_documents'])
+        #print(self.flattened_conversation, '\n\n')
+        print(tutor_message['source_documents'])
+    
+    def get_sources_memory(self):
+        # retrieve last source
+        last_sources = self.sources_memory[-1]
+
+        # get page_content keyword from last_sources
+        doc_contents = ['Source ' + str(ind+1) + '\n"' + doc.page_content + '"\n\n' for ind, doc in enumerate(last_sources)]
+        doc_contents = ''.join(doc_contents)
+
+        return doc_contents
+    
+    def forget_conversation(self):
+        self.conversation_memory = []
+        self.sources_memory = []
+        self.flattened_conversation = ''
+
+# %% ../nbs/gradio_application.ipynb 18
+def embed_key(openai_api_key, chat_tutor):
+  if not openai_api_key:
+    return chat_tutor
+  
+  # Otherwise, update key
+  os.environ["OPENAI_API_KEY"] = openai_api_key
+  
+  #update tutor
+  chat_tutor.openai_auth = openai_api_key
+
+  if not chat_tutor.api_key_valid:
+    chat_tutor.initialize_llm()
+
+  return chat_tutor
+
+# %% ../nbs/gradio_application.ipynb 20
+def create_reference_store(chat_tutor, vs_button, text_cp, upload_files, reference_vs, openai_auth, learning_objs):
+
+    text_segs = []
+    upload_segs = []
+    
+    if reference_vs:
+        raise NotImplementedError("Reference Vector Stores are not yet implemented")
+    
+    if text_cp.strip():
+        text_segs = get_document_segments(text_cp, 'text', chunk_size=700, chunk_overlap=100)
+        [doc.metadata.update({'source':'text box'}) for doc in text_segs];
+    
+    if upload_files:
+        print(upload_files)
+        upload_fnames = [f.name for f in upload_files]
+        upload_segs = get_document_segments(upload_fnames, 'file', chunk_size=700, chunk_overlap=100)
+    
+    # get the full list of everything
+    all_segs = text_segs + upload_segs
+    print(all_segs)
+
+    # create the vector store and update tutor
+    vs_db, vs_retriever = create_local_vector_store(all_segs, search_kwargs={"k": 2})
+    chat_tutor.vector_store = vs_db
+    chat_tutor.vs_retriever = vs_retriever
+
+    # create the tutor chain
+    if not chat_tutor.api_key_valid or not chat_tutor.openai_auth:
+        chat_tutor = embed_key(openai_auth, chat_tutor)
+    qa_chain = create_tutor_mdl_chain(kind="retrieval_qa", mdl=chat_tutor.chat_llm, retriever = chat_tutor.vs_retriever, return_source_documents=True)
+    chat_tutor.tutor_chain = qa_chain
+
+    # store learning objectives
+    chat_tutor.learning_objectives = learning_objs
+
+    # return the story
+    return chat_tutor, gr.update(interactive=True, value='Tutor Initialized!')
+
+# %% ../nbs/gradio_application.ipynb 22
+### Gradio Called Functions ###
+
+def prompt_select(selection, number, length):
+  if selection == "Random":
+    prompt = f"Please design a {number} question quiz based on the context provided and the inputted learning objectives (if applicable). The types of questions should be randomized (including multiple choice, short answer, true/false, short answer, etc.).  Provide one question at a time, and wait for my response before providing me with feedback. Again, while the quiz may ask for multiple questions, you should only provide 1 question in you initial response. Do not include the answer in your response. If I get an answer wrong, provide me with an explanation of why it was incorrect, and then give me additional chances to respond until I get the correct choice. Explain why the correct choice is right."
+  elif selection == "Fill in the Blank":
+    prompt = f"Create a {number} question fill in the blank quiz refrencing the context provided. The quiz should reflect the learning objectives (if inputted). The 'blank' part of the question should appear as '________'. The answers should reflect what word(s) should go in the blank an accurate statement. An example is the follow: 'The author of the article is ______.' The question should be a statement. Provide one question at a time, and wait for my response before providing me with feedback. Again, while the quiz may ask for multiple questions, you should only provide ONE question in you initial response. Do not include the answer in your response. If I get an answer wrong, provide me with an explanation of why it was incorrect,and then give me additional chances to respond until I get the correct choice. Explain why the correct choice is right."
+  elif selection == "Short Answer":
+    prompt = f"Please design a {number} question quiz about which reflects the learning objectives (if inputted).  The questions should be short answer. Expect the correct answers to be {length} sentences long. Provide one question at a time, and wait for my response before providing me with feedback. Again, while the quiz may ask for multiple questions, you should only provide ONE question in you initial response. Do not include the answer in your response. If I get an answer wrong, provide me with an explanation of why it was incorrect, and then give me additional chances to respond until I get the correct choice. Explain why the correct answer is right."
+  else:
+    prompt = f"Please design a {number} question {selection.lower()} quiz based on the context provided and the inputted learning objectives (if applicable). Provide one question at a time, and wait for my response before providing me with feedback. Again, while the quiz may ask for multiple questions, you should only provide 1 question in you initial response. Do not include the answer in your response. If I get an answer wrong, provide me with an explanation of why it was incorrect, and then give me additional chances to respond until I get the correct choice. Explain why the correct choice is right."
+  return prompt, prompt
+    
+
+# %% ../nbs/gradio_application.ipynb 24
+### Chatbot Functions ###
+
+def add_user_message(user_message, chat_tutor):
+  """Display user message and update chat history to include it.
+  Also disables user text input until bot is finished (call to reenable_chat())
+  See https://gradio.app/creating-a-chatbot/"""
+  chat_tutor.add_user_message(user_message)
+  return gr.update(value="", interactive=False), chat_tutor.conversation_memory, chat_tutor
+
+def get_tutor_reply(learning_topic, chat_tutor):
+  chat_tutor.get_tutor_reply(input_kwargs={'question':learning_topic})
+  return gr.update(value="", interactive=True), gr.update(visible=True, value=chat_tutor.get_sources_memory()), chat_tutor.conversation_memory, chat_tutor
+
+num_sources = 2
+
+# %% ../nbs/gradio_application.ipynb 25
+def disable_until_done(obj_in):
+    return gr.update(interactive=False)
+
+# %% ../nbs/gradio_application.ipynb 27
+# See https://gradio.app/custom-CSS-and-JS/
+css="""
+#sources-container {
+  overflow: scroll !important; /* Needs to override default formatting */
+  /*max-height: 20em; */ /* Arbitrary value */
+}
+#sources-container > div { padding-bottom: 1em !important; /* Arbitrary value */ }
+.short-height > * > * { min-height: 0 !important; }
+.translucent { opacity: 0.5; }
+.textbox_label { padding-bottom: .5em; }
+"""
+#srcs = [] # Reset sources (db and qa are kept the same for ease of testing)
+
+with gr.Blocks(css=css, analytics_enabled=False) as demo:
+
+  #initialize tutor (with state)
+  study_tutor = gr.State(SlightlyDelusionalTutor())
+
+  # Title
+  gr.Markdown("# Studying with a Slightly Delusional Tutor")
+
+  # API Authentication functionality
+  with gr.Box():
+    gr.Markdown("### OpenAI API Key ")
+    gr.HTML("""<span>Embed your OpenAI API key below; if you haven't created one already, visit
+      <a href="https://platform.openai.com/account/api-keys">platform.openai.com/account/api-keys</a>
+    to sign up for an account and get your personal API key</span>""",
+            elem_classes="textbox_label")
+    api_input = gr.Textbox(show_label=False, type="password", container=False, autofocus=True,
+                      placeholder="●●●●●●●●●●●●●●●●●", value='')
+    api_input.submit(fn=embed_key, inputs=[api_input, study_tutor], outputs=study_tutor)
+    api_input.blur(fn=embed_key, inputs=[api_input, study_tutor], outputs=study_tutor)
+
+  # Reference document functionality (building vector stores)
+  with gr.Box():
+    gr.Markdown("### Add Reference Documents")
+    # TODO Add entry for path to vector store (should be disabled for now)
+    with gr.Row(equal_height=True):
+      text_input = gr.TextArea(label='Copy and paste your text below',
+                                lines=2)
+
+      file_input = gr.Files(label="Load a .txt or .pdf file",
+                            file_types=['.pdf', '.txt'], type="file",
+                            elem_classes="short-height")
+
+      instructor_input = gr.TextArea(label='Enter vector store URL, if given by instructor (WIP)', value='',
+                                lines=2, interactive=False, elem_classes="translucent")
+    
+    # Adding the learning objectives
+    with gr.Box():
+      gr.Markdown("### Optional: Enter Your Learning Objectives")
+      learning_objectives = gr.Textbox(label='If provided by your instructor, please input your learning objectives for this session', value='')
+    
+    # Adding the button to submit all of the settings and create the Chat Tutor Chain.
+    with gr.Row():
+      vs_build_button = gr.Button(value = 'Start Studying with Your Tutor!', scale=1)
+      vs_build_button.click(disable_until_done, vs_build_button, vs_build_button) \
+        .then(create_reference_store, [study_tutor, vs_build_button, text_input, file_input, instructor_input, api_input, learning_objectives],
+                            [study_tutor, vs_build_button])
+
+  
+
+  # Premade question prompts
+  with gr.Box():
+    gr.Markdown("""
+    ## Generate a Premade Prompt
+    Select your type and number of desired questions. Click "Generate Prompt" to get your premade prompt,
+    and then "Insert Prompt into Chat" to copy the text into the chat interface below. \
+    You can also copy the prompt using the icon in the upper right corner and paste directly into the input box when interacting with the model.
+    """)
+    with gr.Row():
+      with gr.Column():
+        question_type = gr.Dropdown(["Multiple Choice", "True or False", "Short Answer", "Fill in the Blank", "Random"], label="Question Type")
+        number_of_questions = gr.Textbox(label="Enter desired number of questions")
+        sa_desired_length = gr.Dropdown(["1-2", "3-4", "5-6", "6 or more"], label = "For short answer questions only, choose the desired sentence length for answers. The default value is 1-2 sentences.")
+      with gr.Column():
+        prompt_button = gr.Button("Generate Prompt")
+        premade_prompt_output = gr.Textbox(label="Generated prompt (save or copy)", show_copy_button=True)
+
+
+  # Chatbot interface
+  gr.Markdown("## Chat with the Model")
+  topic_input = gr.Textbox(label="What topic or concept are you trying to learn more about?")
+  with gr.Row(equal_height=True):
+    with gr.Column(scale=2):
+      chatbot = gr.Chatbot()
+      with gr.Row():
+        user_chat_input = gr.Textbox(label="User input", scale=9)
+        user_chat_submit = gr.Button("Ask/answer model", scale=1)
+
+    # sources
+    with gr.Box(elem_id="sources-container", scale=1):
+      # TODO: Display document sources in a nicer format?
+      gr.HTML(value="<h3 id='sources'>Referenced Sources</h3>")
+      sources_output = gr.Textbox(value='', interactive=False, visible=False, show_label=False)
+      #sources_output = []
+      #for i in range(num_sources):
+      #  source_elem = gr.HTML(visible=False)
+      #  sources_output.append(source_elem)
+
+  #define the behavior of prompt button later since it depends on user_chat_input
+  prompt_button.click(prompt_select,
+                      inputs=[question_type, number_of_questions, sa_desired_length],
+                      outputs=[premade_prompt_output, user_chat_input])
+
+  # Display input and output in three-ish parts
+  # (using asynchronous functions):
+  # First show user input, then show model output when complete
+  # Then wait until the bot provides response and return the result
+  # Finally, allow the user to ask a new question by reenabling input
+  async_response = user_chat_submit.click(add_user_message,
+            [user_chat_input, study_tutor],
+            [user_chat_input, chatbot, study_tutor], queue=False) \
+  .then(get_tutor_reply, [topic_input, study_tutor], [user_chat_input, sources_output, chatbot, study_tutor], queue=True)
+
+  async_response_b = user_chat_input.submit(add_user_message,
+            [user_chat_input, study_tutor],
+            [user_chat_input, chatbot, study_tutor], queue=False) \
+  .then(get_tutor_reply, [topic_input, study_tutor], [user_chat_input, sources_output, chatbot, study_tutor], queue=True)
+
+  with gr.Blocks():
+    gr.Markdown("""
+    ## Export Your Chat History
+    Export your chat history as a .json, PDF file, .txt, or .csv file
+    """)
+    with gr.Row():
+      export_dialogue_button_json = gr.Button("JSON")
+      export_dialogue_button_pdf = gr.Button("PDF")
+      export_dialogue_button_txt = gr.Button("TXT")
+      export_dialogue_button_csv = gr.Button("CSV")
+    
+    file_download = gr.Files(label="Download here",
+                            file_types=['.pdf', '.txt', '.csv', '.json'], type="file", visible=False)
+    
+    export_dialogue_button_json.click(save_json, study_tutor, file_download, show_progress=True)
+    export_dialogue_button_pdf.click(save_pdf, study_tutor, file_download, show_progress=True)
+    export_dialogue_button_txt.click(save_txt, study_tutor, file_download, show_progress=True)
+    export_dialogue_button_csv.click(save_csv, study_tutor, file_download, show_progress=True)
+
+demo.queue()
+demo.launch(debug=True)
+#demo.launch()
+#gr.close_all()