init

.gitignore

@@ -0,0 +1,3 @@
+audios/**/*
+.env
+__pycache__

.python-version

@@ -0,0 +1 @@
+3.10

app.py

@@ -0,0 +1,826 @@
+import io
+import os
+import ssl
+from contextlib import closing
+from typing import Optional, Tuple
+import datetime
+
+import boto3
+import gradio as gr
+import requests
+
+# UNCOMMENT TO USE WHISPER
+import warnings
+import whisper
+
+from langchain import ConversationChain, LLMChain
+
+from langchain.agents import load_tools, initialize_agent
+from langchain.chains.conversation.memory import ConversationBufferMemory
+from langchain.llms import OpenAI, OpenAIChat
+from threading import Lock
+
+# Console to variable
+from io import StringIO
+import sys
+import re
+
+from openai.error import AuthenticationError, InvalidRequestError, RateLimitError
+
+# Pertains to Express-inator functionality
+from langchain.prompts import PromptTemplate
+
+from polly_utils import PollyVoiceData, NEURAL_ENGINE
+from azure_utils import AzureVoiceData
+
+# Pertains to question answering functionality
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores.faiss import FAISS
+from langchain.docstore.document import Document
+from langchain.chains.question_answering import load_qa_chain
+
+# https://python.langchain.com/en/latest/ecosystem/google_search.html
+# from langchain.utilities import GoogleSearchAPIWrapper
+
+
+# news_api_key = os.environ["NEWS_API_KEY"]
+# tmdb_bearer_token = os.environ["TMDB_BEARER_TOKEN"]
+
+TOOLS_LIST = ['serpapi', 'google-search', 'wolfram-alpha', 'pal-math',
+              'pal-colored-objects']  # 'google-search','news-api','tmdb-api','open-meteo-api'
+TOOLS_DEFAULT_LIST = ['wolfram-alpha', 'pal-math', 'google-search']
+BUG_FOUND_MSG = "Congratulations, you've found a bug in this application!"
+# AUTH_ERR_MSG = "Please paste your OpenAI key from openai.com to use this application. It is not necessary to hit a button or key after pasting it."
+AUTH_ERR_MSG = "Please paste your OpenAI key from openai.com to use this application. "
+MAX_TOKENS = 512
+
+TALKING_HEAD_WIDTH = "192"
+MAX_TALKING_HEAD_TEXT_LENGTH = 155
+
+# Pertains to Express-inator functionality
+NUM_WORDS_DEFAULT = 0
+MAX_WORDS = 400
+FORMALITY_DEFAULT = "N/A"
+TEMPERATURE_DEFAULT = 0.5
+EMOTION_DEFAULT = "N/A"
+LANG_LEVEL_DEFAULT = "N/A"
+TRANSLATE_TO_DEFAULT = "N/A"
+LITERARY_STYLE_DEFAULT = "N/A"
+PROMPT_TEMPLATE = PromptTemplate(
+    input_variables=["original_words", "num_words", "formality", "emotions", "lang_level", "translate_to",
+                     "literary_style"],
+    template="Restate {num_words}{formality}{emotions}{lang_level}{translate_to}{literary_style}the following: \n{original_words}\n",
+)
+
+FORCE_TRANSLATE_DEFAULT = True
+USE_GPT4_DEFAULT = False
+
+POLLY_VOICE_DATA = PollyVoiceData()
+AZURE_VOICE_DATA = AzureVoiceData()
+
+# Pertains to WHISPER functionality
+WHISPER_DETECT_LANG = "Detect language"
+
+# UNCOMMENT TO USE WHISPER
+warnings.filterwarnings("ignore")
+WHISPER_MODEL = whisper.load_model("tiny")
+print("WHISPER_MODEL", WHISPER_MODEL)
+
+
+# UNCOMMENT TO USE WHISPER
+def transcribe(aud_inp, whisper_lang):
+    if aud_inp is None:
+        return ""
+    aud = whisper.load_audio(aud_inp)
+    aud = whisper.pad_or_trim(aud)
+    mel = whisper.log_mel_spectrogram(aud).to(WHISPER_MODEL.device)
+    _, probs = WHISPER_MODEL.detect_language(mel)
+    options = whisper.DecodingOptions(fp16 = False)
+    if whisper_lang != WHISPER_DETECT_LANG:
+        whisper_lang_code = POLLY_VOICE_DATA.get_whisper_lang_code(whisper_lang)
+        options = whisper.DecodingOptions(fp16 = False, language=whisper_lang_code)
+    result = whisper.decode(WHISPER_MODEL, mel, options)
+    print("result.text", result.text)
+    result_text = ""
+    if result and result.text:
+        result_text = result.text
+    return result_text
+
+
+# Temporarily address Wolfram Alpha SSL certificate issue
+ssl._create_default_https_context = ssl._create_unverified_context
+
+
+# TEMPORARY FOR TESTING
+def transcribe_dummy(aud_inp_tb, whisper_lang):
+    if aud_inp_tb is None:
+        return ""
+    # aud = whisper.load_audio(aud_inp)
+    # aud = whisper.pad_or_trim(aud)
+    # mel = whisper.log_mel_spectrogram(aud).to(WHISPER_MODEL.device)
+    # _, probs = WHISPER_MODEL.detect_language(mel)
+    # options = whisper.DecodingOptions()
+    # options = whisper.DecodingOptions(language="ja")
+    # result = whisper.decode(WHISPER_MODEL, mel, options)
+    result_text = "Whisper will detect language"
+    if whisper_lang != WHISPER_DETECT_LANG:
+        whisper_lang_code = POLLY_VOICE_DATA.get_whisper_lang_code(whisper_lang)
+        result_text = f"Whisper will use lang code: {whisper_lang_code}"
+    print("result_text", result_text)
+    return aud_inp_tb
+
+
+# Pertains to Express-inator functionality
+def transform_text(desc, express_chain, num_words, formality,
+                   anticipation_level, joy_level, trust_level,
+                   fear_level, surprise_level, sadness_level, disgust_level, anger_level,
+                   lang_level, translate_to, literary_style, force_translate):
+    num_words_prompt = ""
+    if num_words and int(num_words) != 0:
+        num_words_prompt = "using up to " + str(num_words) + " words, "
+
+    # Change some arguments to lower case
+    formality = formality.lower()
+    anticipation_level = anticipation_level.lower()
+    joy_level = joy_level.lower()
+    trust_level = trust_level.lower()
+    fear_level = fear_level.lower()
+    surprise_level = surprise_level.lower()
+    sadness_level = sadness_level.lower()
+    disgust_level = disgust_level.lower()
+    anger_level = anger_level.lower()
+
+    formality_str = ""
+    if formality != "n/a":
+        formality_str = "in a " + formality + " manner, "
+
+    # put all emotions into a list
+    emotions = []
+    if anticipation_level != "n/a":
+        emotions.append(anticipation_level)
+    if joy_level != "n/a":
+        emotions.append(joy_level)
+    if trust_level != "n/a":
+        emotions.append(trust_level)
+    if fear_level != "n/a":
+        emotions.append(fear_level)
+    if surprise_level != "n/a":
+        emotions.append(surprise_level)
+    if sadness_level != "n/a":
+        emotions.append(sadness_level)
+    if disgust_level != "n/a":
+        emotions.append(disgust_level)
+    if anger_level != "n/a":
+        emotions.append(anger_level)
+
+    emotions_str = ""
+    if len(emotions) > 0:
+        if len(emotions) == 1:
+            emotions_str = "with emotion of " + emotions[0] + ", "
+        else:
+            emotions_str = "with emotions of " + ", ".join(emotions[:-1]) + " and " + emotions[-1] + ", "
+
+    lang_level_str = ""
+    if lang_level != LANG_LEVEL_DEFAULT:
+        lang_level_str = "at a level that a person in " + lang_level + " can easily comprehend, " if translate_to == TRANSLATE_TO_DEFAULT else ""
+
+    translate_to_str = ""
+    if translate_to != TRANSLATE_TO_DEFAULT and (force_translate or lang_level != LANG_LEVEL_DEFAULT):
+        translate_to_str = "translated to " + translate_to + (
+            "" if lang_level == LANG_LEVEL_DEFAULT else " at a level that a person in " + lang_level + " can easily comprehend") + ", "
+
+    literary_style_str = ""
+    if literary_style != LITERARY_STYLE_DEFAULT:
+        if literary_style == "Prose":
+            literary_style_str = "as prose, "
+        if literary_style == "Story":
+            literary_style_str = "as a story, "
+        elif literary_style == "Summary":
+            literary_style_str = "as a summary, "
+        elif literary_style == "Outline":
+            literary_style_str = "as an outline numbers and lower case letters, "
+        elif literary_style == "Bullets":
+            literary_style_str = "as bullet points using bullets, "
+        elif literary_style == "Poetry":
+            literary_style_str = "as a poem, "
+        elif literary_style == "Haiku":
+            literary_style_str = "as a haiku, "
+        elif literary_style == "Limerick":
+            literary_style_str = "as a limerick, "
+        elif literary_style == "Rap":
+            literary_style_str = "as a rap, "
+        elif literary_style == "Joke":
+            literary_style_str = "as a very funny joke with a setup and punchline, "
+        elif literary_style == "Knock-knock":
+            literary_style_str = "as a very funny knock-knock joke, "
+        elif literary_style == "FAQ":
+            literary_style_str = "as a FAQ with several questions and answers, "
+
+    formatted_prompt = PROMPT_TEMPLATE.format(
+        original_words=desc,
+        num_words=num_words_prompt,
+        formality=formality_str,
+        emotions=emotions_str,
+        lang_level=lang_level_str,
+        translate_to=translate_to_str,
+        literary_style=literary_style_str
+    )
+
+    trans_instr = num_words_prompt + formality_str + emotions_str + lang_level_str + translate_to_str + literary_style_str
+    if express_chain and len(trans_instr.strip()) > 0:
+        generated_text = express_chain.run(
+            {'original_words': desc, 'num_words': num_words_prompt, 'formality': formality_str,
+             'emotions': emotions_str, 'lang_level': lang_level_str, 'translate_to': translate_to_str,
+             'literary_style': literary_style_str}).strip()
+    else:
+        print("Not transforming text")
+        generated_text = desc
+
+    # replace all newlines with <br> in generated_text
+    generated_text = generated_text.replace("\n", "\n\n")
+
+    prompt_plus_generated = "GPT prompt: " + formatted_prompt + "\n\n" + generated_text
+
+    print("\n==== date/time: " + str(datetime.datetime.now() - datetime.timedelta(hours=5)) + " ====")
+    print("prompt_plus_generated: " + prompt_plus_generated)
+
+    return generated_text
+
+
+def load_chain(tools_list, llm):
+    chain = None
+    express_chain = None
+    memory = None
+    if llm:
+        print("\ntools_list", tools_list)
+        tool_names = tools_list
+        tools = load_tools(tool_names, llm=llm) #, news_api_key=news_api_key, tmdb_bearer_token=tmdb_bearer_token)
+
+        memory = ConversationBufferMemory(memory_key="chat_history")
+
+        chain = initialize_agent(tools, llm, agent="conversational-react-description", verbose=True, memory=memory)
+        express_chain = LLMChain(llm=llm, prompt=PROMPT_TEMPLATE, verbose=True)
+    return chain, express_chain, memory
+
+
+def set_openai_api_key(api_key, use_gpt4):
+    """Set the api key and return chain.
+    If no api_key, then None is returned.
+    """
+    if api_key and api_key.startswith("sk-") and len(api_key) > 50:
+        os.environ["OPENAI_API_KEY"] = api_key
+        print("\n\n ++++++++++++++ Setting OpenAI API key ++++++++++++++ \n\n")
+        print(str(datetime.datetime.now()) + ": Before OpenAI, OPENAI_API_KEY length: " + str(
+            len(os.environ["OPENAI_API_KEY"])))
+
+        if use_gpt4:
+            llm = OpenAIChat(temperature=0.0, max_tokens=MAX_TOKENS, model_name="gpt-4")
+            print("Trying to use llm OpenAIChat with gpt-4")
+        else:
+            print("Trying to use llm OpenAIChat with text-davinci-003")
+            llm = OpenAI(temperature=0.0, max_tokens=MAX_TOKENS, model_name="text-davinci-003")
+
+        print(str(datetime.datetime.now()) + ": After OpenAI, OPENAI_API_KEY length: " + str(
+            len(os.environ["OPENAI_API_KEY"])))
+        chain, express_chain, memory = load_chain(TOOLS_DEFAULT_LIST, llm)
+
+        # Pertains to question answering functionality
+        embeddings = OpenAIEmbeddings()
+
+        if use_gpt4:
+            qa_chain = load_qa_chain(OpenAIChat(temperature=0, model_name="gpt-4"), chain_type="stuff")
+            print("Trying to use qa_chain OpenAIChat with gpt-4")
+        else:
+            print("Trying to use qa_chain OpenAI with text-davinci-003")
+            qa_chain = OpenAI(temperature=0, max_tokens=MAX_TOKENS, model_name="text-davinci-003")
+
+        print(str(datetime.datetime.now()) + ": After load_chain, OPENAI_API_KEY length: " + str(
+            len(os.environ["OPENAI_API_KEY"])))
+        os.environ["OPENAI_API_KEY"] = ""
+        return chain, express_chain, llm, embeddings, qa_chain, memory, use_gpt4
+    return None, None, None, None, None, None, None
+
+
+def run_chain(chain, inp, capture_hidden_text):
+    output = ""
+    hidden_text = None
+    if capture_hidden_text:
+        error_msg = None
+        tmp = sys.stdout
+        hidden_text_io = StringIO()
+        sys.stdout = hidden_text_io
+
+        try:
+            output = chain.run(input=inp)
+        except AuthenticationError as ae:
+            error_msg = AUTH_ERR_MSG + str(datetime.datetime.now()) + ". " + str(ae)
+            print("error_msg", error_msg)
+        except RateLimitError as rle:
+            error_msg = "\n\nRateLimitError: " + str(rle)
+        except ValueError as ve:
+            error_msg = "\n\nValueError: " + str(ve)
+        except InvalidRequestError as ire:
+            error_msg = "\n\nInvalidRequestError: " + str(ire)
+        except Exception as e:
+            error_msg = "\n\n" + BUG_FOUND_MSG + ":\n\n" + str(e)
+
+        sys.stdout = tmp
+        hidden_text = hidden_text_io.getvalue()
+
+        # remove escape characters from hidden_text
+        hidden_text = re.sub(r'\x1b[^m]*m', '', hidden_text)
+
+        # remove "Entering new AgentExecutor chain..." from hidden_text
+        hidden_text = re.sub(r"Entering new AgentExecutor chain...\n", "", hidden_text)
+
+        # remove "Finished chain." from hidden_text
+        hidden_text = re.sub(r"Finished chain.", "", hidden_text)
+
+        # Add newline after "Thought:" "Action:" "Observation:" "Input:" and "AI:"
+        hidden_text = re.sub(r"Thought:", "\n\nThought:", hidden_text)
+        hidden_text = re.sub(r"Action:", "\n\nAction:", hidden_text)
+        hidden_text = re.sub(r"Observation:", "\n\nObservation:", hidden_text)
+        hidden_text = re.sub(r"Input:", "\n\nInput:", hidden_text)
+        hidden_text = re.sub(r"AI:", "\n\nAI:", hidden_text)
+
+        if error_msg:
+            hidden_text += error_msg
+
+        print("hidden_text: ", hidden_text)
+    else:
+        try:
+            output = chain.run(input=inp)
+        except AuthenticationError as ae:
+            output = AUTH_ERR_MSG + str(datetime.datetime.now()) + ". " + str(ae)
+            print("output", output)
+        except RateLimitError as rle:
+            output = "\n\nRateLimitError: " + str(rle)
+        except ValueError as ve:
+            output = "\n\nValueError: " + str(ve)
+        except InvalidRequestError as ire:
+            output = "\n\nInvalidRequestError: " + str(ire)
+        except Exception as e:
+            output = "\n\n" + BUG_FOUND_MSG + ":\n\n" + str(e)
+
+    return output, hidden_text
+
+
+def reset_memory(history, memory):
+    memory.clear()
+    history = []
+    return history, history, memory
+
+
+class ChatWrapper:
+
+    def __init__(self):
+        self.lock = Lock()
+
+    def __call__(
+            self, api_key: str, inp: str, history: Optional[Tuple[str, str]], chain: Optional[ConversationChain],
+            trace_chain: bool, speak_text: bool, monologue: bool, express_chain: Optional[LLMChain],
+            num_words, formality, anticipation_level, joy_level, trust_level,
+            fear_level, surprise_level, sadness_level, disgust_level, anger_level,
+            lang_level, translate_to, literary_style, qa_chain, docsearch, use_embeddings, force_translate
+    ):
+        """Execute the chat functionality."""
+        self.lock.acquire()
+        try:
+            print("\n==== date/time: " + str(datetime.datetime.now()) + " ====")
+            print("inp: " + inp)
+            print("trace_chain: ", trace_chain)
+            print("speak_text: ", speak_text)
+            print("monologue: ", monologue)
+            history = history or []
+            # If chain is None, that is because no API key was provided.
+            output = "Please paste your OpenAI key from openai.com to use this app. " + str(datetime.datetime.now())
+            hidden_text = output
+
+            if chain:
+                # Set OpenAI key
+                import openai
+                openai.api_key = api_key
+                if not monologue:
+                    if use_embeddings:
+                        if inp and inp.strip() != "":
+                            if docsearch:
+                                docs = docsearch.similarity_search(inp)
+                                output = str(qa_chain.run(input_documents=docs, question=inp))
+                            else:
+                                output, hidden_text = "Please supply some text in the the Embeddings tab.", None
+                        else:
+                            output, hidden_text = "What's on your mind?", None
+                    else:
+                        output, hidden_text = run_chain(chain, inp, capture_hidden_text=trace_chain)
+                else:
+                    output, hidden_text = inp, None
+
+            output = transform_text(output, express_chain, num_words, formality, anticipation_level, joy_level,
+                                    trust_level,
+                                    fear_level, surprise_level, sadness_level, disgust_level, anger_level,
+                                    lang_level, translate_to, literary_style, force_translate)
+
+            text_to_display = output
+            if trace_chain:
+                text_to_display = hidden_text + "\n\n" + output
+            history.append((inp, text_to_display))
+
+            temp_file, html_audio, temp_aud_file = None, None, None
+            if speak_text:
+                    html_audio, temp_aud_file = do_html_audio_speak(output, translate_to)
+
+        except Exception as e:
+            raise e
+        finally:
+            self.lock.release()
+        return history, history, temp_file, html_audio, temp_aud_file, ""
+        # return history, history, html_audio, temp_aud_file, ""
+
+
+chat = ChatWrapper()
+
+
+def do_html_audio_speak(words_to_speak, polly_language):
+    polly_client = boto3.Session(
+        aws_access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
+        aws_secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
+        region_name=os.environ["AWS_DEFAULT_REGION"]
+    ).client('polly')
+
+    voice_id, language_code, engine = POLLY_VOICE_DATA.get_voice(polly_language, "Female")
+    # voice_id, language_code, engine = POLLY_VOICE_DATA.get_voice(polly_language, "Male")
+    if not voice_id:
+        voice_id = "Joanna"
+        # voice_id = "Matthew"
+        language_code = "en-US"
+        engine = NEURAL_ENGINE
+    response = polly_client.synthesize_speech(
+        Text=words_to_speak,
+        OutputFormat='mp3',
+        VoiceId=voice_id,
+        LanguageCode=language_code,
+        Engine=engine
+    )
+
+    html_audio = '<pre>no audio</pre>'
+
+    # Save the audio stream returned by Amazon Polly on Lambda's temp directory
+    if "AudioStream" in response:
+        with closing(response["AudioStream"]) as stream:
+            # output = os.path.join("/tmp/", "speech.mp3")
+
+            try:
+                with open('audios/tempfile.mp3', 'wb') as f:
+                    f.write(stream.read())
+                temp_aud_file = gr.File("audios/tempfile.mp3")
+                temp_aud_file_url = "/file=" + temp_aud_file.value['name']
+                html_audio = f'<audio autoplay><source src={temp_aud_file_url} type="audio/mp3"></audio>'
+            except IOError as error:
+                # Could not write to file, exit gracefully
+                print(error)
+                return None, None
+    else:
+        # The response didn't contain audio data, exit gracefully
+        print("Could not stream audio")
+        return None, None
+
+    return html_audio, "audios/tempfile.mp3"
+
+def update_selected_tools(widget, state, llm):
+    if widget:
+        state = widget
+        chain, express_chain, memory = load_chain(state, llm)
+        return state, llm, chain, express_chain
+
+
+def update_foo(widget, state):
+    if widget:
+        state = widget
+        return state
+
+
+# Pertains to question answering functionality
+def update_embeddings(embeddings_text, embeddings, qa_chain):
+    if embeddings_text:
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+        texts = text_splitter.split_text(embeddings_text)
+
+        docsearch = FAISS.from_texts(texts, embeddings)
+        print("Embeddings updated")
+        return docsearch
+
+
+# Pertains to question answering functionality
+def update_use_embeddings(widget, state):
+    if widget:
+        state = widget
+        return state
+
+
+with gr.Blocks(css=".gradio-container {background-color: lightgray}") as block:
+    llm_state = gr.State()
+    history_state = gr.State()
+    chain_state = gr.State()
+    express_chain_state = gr.State()
+    tools_list_state = gr.State(TOOLS_DEFAULT_LIST)
+    trace_chain_state = gr.State(False)
+    speak_text_state = gr.State(True)
+    monologue_state = gr.State(False)  # Takes the input and repeats it back to the user, optionally transforming it.
+    force_translate_state = gr.State(FORCE_TRANSLATE_DEFAULT)  #
+    memory_state = gr.State()
+
+    # Pertains to Express-inator functionality
+    num_words_state = gr.State(NUM_WORDS_DEFAULT)
+    formality_state = gr.State(FORMALITY_DEFAULT)
+    anticipation_level_state = gr.State(EMOTION_DEFAULT)
+    joy_level_state = gr.State(EMOTION_DEFAULT)
+    trust_level_state = gr.State(EMOTION_DEFAULT)
+    fear_level_state = gr.State(EMOTION_DEFAULT)
+    surprise_level_state = gr.State(EMOTION_DEFAULT)
+    sadness_level_state = gr.State(EMOTION_DEFAULT)
+    disgust_level_state = gr.State(EMOTION_DEFAULT)
+    anger_level_state = gr.State(EMOTION_DEFAULT)
+    lang_level_state = gr.State(LANG_LEVEL_DEFAULT)
+    translate_to_state = gr.State(TRANSLATE_TO_DEFAULT)
+    literary_style_state = gr.State(LITERARY_STYLE_DEFAULT)
+
+    # Pertains to WHISPER functionality
+    whisper_lang_state = gr.State(WHISPER_DETECT_LANG)
+
+    # Pertains to question answering functionality
+    embeddings_state = gr.State()
+    qa_chain_state = gr.State()
+    docsearch_state = gr.State()
+    use_embeddings_state = gr.State(False)
+
+    use_gpt4_state = gr.State(USE_GPT4_DEFAULT)
+
+    with gr.Tab("Chat"):
+        with gr.Row():
+            with gr.Column():
+                gr.HTML(
+                    """<b><center>GPT + WolframAlpha + Whisper</center></b>
+                    <p><center>Hit Enter after pasting your OpenAI API key.</center></p>
+                    <i><center>If you have GPT-4 access, optionally select it in Settings tab.</center></i>""")
+
+            openai_api_key_textbox = gr.Textbox(placeholder="Paste your OpenAI API key (sk-...) and hit Enter",
+                                                show_label=False, lines=1, type='password')
+
+        with gr.Row():
+            with gr.Column(scale=1, min_width=TALKING_HEAD_WIDTH, visible=True):
+                speak_text_cb = gr.Checkbox(label="Enable speech", value=True)
+                speak_text_cb.change(update_foo, inputs=[speak_text_cb, speak_text_state],
+                                     outputs=[speak_text_state])
+
+                my_file = gr.File(label="Upload a file", type="file", visible=False)
+                # tmp_file = gr.File(LOOPING_TALKING_HEAD, visible=False)
+                # tmp_file_url = "/file=" + tmp_file.value['name']
+
+                # my_aud_file = gr.File(label="Audio file", type="file", visible=True)
+                tmp_aud_file = gr.File("audios/tempfile.mp3", visible=False)
+                tmp_aud_file_url = "/file=" + tmp_aud_file.value['name']
+                htm_audio = f'<audio><source src={tmp_aud_file_url} type="audio/mp3"></audio>'
+                audio_html = gr.HTML(htm_audio)
+
+            with gr.Column(scale=7):
+                chatbot = gr.Chatbot()
+
+        with gr.Row():
+            message = gr.Textbox(label="What's on your mind??",
+                                 placeholder="What's the answer to life, the universe, and everything?",
+                                 lines=1)
+            submit = gr.Button(value="Send", variant="secondary").style(full_width=False)
+
+        # UNCOMMENT TO USE WHISPER
+        with gr.Row():
+            audio_comp = gr.Microphone(source="microphone", type="filepath", label="Just say it!",
+                                       interactive=True, streaming=False)
+            audio_comp.change(transcribe, inputs=[audio_comp, whisper_lang_state], outputs=[message])
+
+        # TEMPORARY FOR TESTING
+        # with gr.Row():
+        #     audio_comp_tb = gr.Textbox(label="Just say it!", lines=1)
+        #     audio_comp_tb.submit(transcribe_dummy, inputs=[audio_comp_tb, whisper_lang_state], outputs=[message])
+
+        gr.Examples(
+            examples=["What is the current population of Denmark?",
+                      "What is 2 to the 30th power?",
+                      "If x+y=10 and x-y=4, what are x and y?",
+                      "What is x when: 2x+5 = -3x + 7?",
+                      "How much did it rain in Copenhagen today? Please respond in Celsium and Millimeter units.",
+                      "Get me information about the movie 'The Fountain'",
+                      "What are the top headlines today on Bleeping Computer? The date is 2023-03-31",
+                      "On the desk, you see two blue booklets, two purple booklets, and two yellow pairs of sunglasses - "
+                      "if I remove all the pairs of sunglasses from the desk, how many purple items remain on it?"],
+            inputs=message
+        )
+
+    with gr.Tab("Settings"):
+        tools_cb_group = gr.CheckboxGroup(label="Tools:", choices=TOOLS_LIST,
+                                          value=TOOLS_DEFAULT_LIST)
+        tools_cb_group.change(update_selected_tools,
+                              inputs=[tools_cb_group, tools_list_state, llm_state],
+                              outputs=[tools_list_state, llm_state, chain_state, express_chain_state])
+
+        trace_chain_cb = gr.Checkbox(label="Show reasoning chain in chat bubble", value=False)
+        trace_chain_cb.change(update_foo, inputs=[trace_chain_cb, trace_chain_state],
+                              outputs=[trace_chain_state])
+
+        force_translate_cb = gr.Checkbox(label="Force translation to selected Output Language",
+                                         value=FORCE_TRANSLATE_DEFAULT)
+        force_translate_cb.change(update_foo, inputs=[force_translate_cb, force_translate_state],
+                                  outputs=[force_translate_state])
+
+        # speak_text_cb = gr.Checkbox(label="Speak text from agent", value=False)
+        # speak_text_cb.change(update_foo, inputs=[speak_text_cb, speak_text_state],
+        #                      outputs=[speak_text_state])
+
+        monologue_cb = gr.Checkbox(label="Babel fish mode (translate/restate what you enter, no conversational agent)",
+                                   value=False)
+        monologue_cb.change(update_foo, inputs=[monologue_cb, monologue_state],
+                            outputs=[monologue_state])
+
+        use_gpt4_cb = gr.Checkbox(label="Use GPT-4 (experimental) if your OpenAI API has access to it",
+                                  value=USE_GPT4_DEFAULT)
+        use_gpt4_cb.change(set_openai_api_key,
+                           inputs=[openai_api_key_textbox, use_gpt4_cb],
+                           outputs=[chain_state, express_chain_state, llm_state, embeddings_state,
+                                    qa_chain_state, memory_state, use_gpt4_state])
+
+        reset_btn = gr.Button(value="Reset chat", variant="secondary").style(full_width=False)
+        reset_btn.click(reset_memory, inputs=[history_state, memory_state],
+                        outputs=[chatbot, history_state, memory_state])
+
+    with gr.Tab("Whisper STT"):
+        whisper_lang_radio = gr.Radio(label="Whisper speech-to-text language:", choices=[
+            WHISPER_DETECT_LANG, "Arabic", "Arabic (Gulf)", "Catalan", "Chinese (Cantonese)", "Chinese (Mandarin)",
+            "Danish", "Dutch", "English (Australian)", "English (British)", "English (Indian)", "English (New Zealand)",
+            "English (South African)", "English (US)", "English (Welsh)", "Finnish", "French", "French (Canadian)",
+            "German", "German (Austrian)", "Georgian", "Hindi", "Icelandic", "Indonesian", "Italian", "Japanese",
+            "Korean", "Norwegian", "Polish",
+            "Portuguese (Brazilian)", "Portuguese (European)", "Romanian", "Russian", "Spanish (European)",
+            "Spanish (Mexican)", "Spanish (US)", "Swedish", "Turkish", "Ukrainian", "Welsh"],
+                                      value=WHISPER_DETECT_LANG)
+
+        whisper_lang_radio.change(update_foo,
+                                  inputs=[whisper_lang_radio, whisper_lang_state],
+                                  outputs=[whisper_lang_state])
+
+    with gr.Tab("Output Language"):
+        lang_level_radio = gr.Radio(label="Language level:", choices=[
+            LANG_LEVEL_DEFAULT, "1st grade", "2nd grade", "3rd grade", "4th grade", "5th grade", "6th grade",
+            "7th grade", "8th grade", "9th grade", "10th grade", "11th grade", "12th grade", "University"],
+                                    value=LANG_LEVEL_DEFAULT)
+        lang_level_radio.change(update_foo, inputs=[lang_level_radio, lang_level_state],
+                                outputs=[lang_level_state])
+
+        translate_to_radio = gr.Radio(label="Language:", choices=[
+            TRANSLATE_TO_DEFAULT, "Arabic", "Arabic (Gulf)", "Catalan", "Chinese (Cantonese)", "Chinese (Mandarin)",
+            "Danish", "Dutch", "English (Australian)", "English (British)", "English (Indian)", "English (New Zealand)",
+            "English (South African)", "English (US)", "English (Welsh)", "Finnish", "French", "French (Canadian)",
+            "German", "German (Austrian)", "Georgian", "Hindi", "Icelandic", "Indonesian", "Italian", "Japanese",
+            "Korean", "Norwegian", "Polish",
+            "Portuguese (Brazilian)", "Portuguese (European)", "Romanian", "Russian", "Spanish (European)",
+            "Spanish (Mexican)", "Spanish (US)", "Swedish", "Turkish", "Ukrainian", "Welsh",
+            "emojis", "Gen Z slang", "how the stereotypical Karen would say it", "Klingon", "Neanderthal",
+            "Pirate", "Strange Planet expospeak technical talk", "Yoda"],
+                                      value=TRANSLATE_TO_DEFAULT)
+
+        translate_to_radio.change(update_foo,
+                                  inputs=[translate_to_radio, translate_to_state],
+                                  outputs=[translate_to_state])
+
+    with gr.Tab("Formality"):
+        formality_radio = gr.Radio(label="Formality:",
+                                   choices=[FORMALITY_DEFAULT, "Casual", "Polite", "Honorific"],
+                                   value=FORMALITY_DEFAULT)
+        formality_radio.change(update_foo,
+                               inputs=[formality_radio, formality_state],
+                               outputs=[formality_state])
+
+    with gr.Tab("Lit Style"):
+        literary_style_radio = gr.Radio(label="Literary style:", choices=[
+            LITERARY_STYLE_DEFAULT, "Prose", "Story", "Summary", "Outline", "Bullets", "Poetry", "Haiku", "Limerick",
+            "Rap",
+            "Joke", "Knock-knock", "FAQ"],
+                                        value=LITERARY_STYLE_DEFAULT)
+
+        literary_style_radio.change(update_foo,
+                                    inputs=[literary_style_radio, literary_style_state],
+                                    outputs=[literary_style_state])
+
+    with gr.Tab("Emotions"):
+        anticipation_level_radio = gr.Radio(label="Anticipation level:",
+                                            choices=[EMOTION_DEFAULT, "Interest", "Anticipation", "Vigilance"],
+                                            value=EMOTION_DEFAULT)
+        anticipation_level_radio.change(update_foo,
+                                        inputs=[anticipation_level_radio, anticipation_level_state],
+                                        outputs=[anticipation_level_state])
+
+        joy_level_radio = gr.Radio(label="Joy level:",
+                                   choices=[EMOTION_DEFAULT, "Serenity", "Joy", "Ecstasy"],
+                                   value=EMOTION_DEFAULT)
+        joy_level_radio.change(update_foo,
+                               inputs=[joy_level_radio, joy_level_state],
+                               outputs=[joy_level_state])
+
+        trust_level_radio = gr.Radio(label="Trust level:",
+                                     choices=[EMOTION_DEFAULT, "Acceptance", "Trust", "Admiration"],
+                                     value=EMOTION_DEFAULT)
+        trust_level_radio.change(update_foo,
+                                 inputs=[trust_level_radio, trust_level_state],
+                                 outputs=[trust_level_state])
+
+        fear_level_radio = gr.Radio(label="Fear level:",
+                                    choices=[EMOTION_DEFAULT, "Apprehension", "Fear", "Terror"],
+                                    value=EMOTION_DEFAULT)
+        fear_level_radio.change(update_foo,
+                                inputs=[fear_level_radio, fear_level_state],
+                                outputs=[fear_level_state])
+
+        surprise_level_radio = gr.Radio(label="Surprise level:",
+                                        choices=[EMOTION_DEFAULT, "Distraction", "Surprise", "Amazement"],
+                                        value=EMOTION_DEFAULT)
+        surprise_level_radio.change(update_foo,
+                                    inputs=[surprise_level_radio, surprise_level_state],
+                                    outputs=[surprise_level_state])
+
+        sadness_level_radio = gr.Radio(label="Sadness level:",
+                                       choices=[EMOTION_DEFAULT, "Pensiveness", "Sadness", "Grief"],
+                                       value=EMOTION_DEFAULT)
+        sadness_level_radio.change(update_foo,
+                                   inputs=[sadness_level_radio, sadness_level_state],
+                                   outputs=[sadness_level_state])
+
+        disgust_level_radio = gr.Radio(label="Disgust level:",
+                                       choices=[EMOTION_DEFAULT, "Boredom", "Disgust", "Loathing"],
+                                       value=EMOTION_DEFAULT)
+        disgust_level_radio.change(update_foo,
+                                   inputs=[disgust_level_radio, disgust_level_state],
+                                   outputs=[disgust_level_state])
+
+        anger_level_radio = gr.Radio(label="Anger level:",
+                                     choices=[EMOTION_DEFAULT, "Annoyance", "Anger", "Rage"],
+                                     value=EMOTION_DEFAULT)
+        anger_level_radio.change(update_foo,
+                                 inputs=[anger_level_radio, anger_level_state],
+                                 outputs=[anger_level_state])
+
+    with gr.Tab("Max Words"):
+        num_words_slider = gr.Slider(label="Max number of words to generate (0 for don't care)",
+                                     value=NUM_WORDS_DEFAULT, minimum=0, maximum=MAX_WORDS, step=10)
+        num_words_slider.change(update_foo,
+                                inputs=[num_words_slider, num_words_state],
+                                outputs=[num_words_state])
+
+    with gr.Tab("Embeddings"):
+        embeddings_text_box = gr.Textbox(label="Enter text for embeddings and hit Create:",
+                                         lines=20)
+
+        with gr.Row():
+            use_embeddings_cb = gr.Checkbox(label="Use embeddings", value=False)
+            use_embeddings_cb.change(update_use_embeddings, inputs=[use_embeddings_cb, use_embeddings_state],
+                                     outputs=[use_embeddings_state])
+
+            embeddings_text_submit = gr.Button(value="Create", variant="secondary").style(full_width=False)
+            embeddings_text_submit.click(update_embeddings,
+                                         inputs=[embeddings_text_box, embeddings_state, qa_chain_state],
+                                         outputs=[docsearch_state])
+
+    gr.HTML("""<center>
+        Powered by <a href='https://github.com/hwchase17/langchain'>LangChain 🦜️🔗</a>
+        </center>""")
+
+    message.submit(chat, inputs=[openai_api_key_textbox, message, history_state, chain_state, trace_chain_state,
+                                 speak_text_state, monologue_state,
+                                 express_chain_state, num_words_state, formality_state,
+                                 anticipation_level_state, joy_level_state, trust_level_state, fear_level_state,
+                                 surprise_level_state, sadness_level_state, disgust_level_state, anger_level_state,
+                                 lang_level_state, translate_to_state, literary_style_state,
+                                 qa_chain_state, docsearch_state, use_embeddings_state,
+                                 force_translate_state],
+                   outputs=[chatbot, history_state, my_file, audio_html, tmp_aud_file, message])
+
+    submit.click(chat, inputs=[openai_api_key_textbox, message, history_state, chain_state, trace_chain_state,
+                               speak_text_state, monologue_state,
+                               express_chain_state, num_words_state, formality_state,
+                               anticipation_level_state, joy_level_state, trust_level_state, fear_level_state,
+                               surprise_level_state, sadness_level_state, disgust_level_state, anger_level_state,
+                               lang_level_state, translate_to_state, literary_style_state,
+                               qa_chain_state, docsearch_state, use_embeddings_state,
+                               force_translate_state],
+                 outputs=[chatbot, history_state, my_file, audio_html, tmp_aud_file, message])
+
+    openai_api_key_textbox.change(set_openai_api_key,
+                                  inputs=[openai_api_key_textbox, use_gpt4_state],
+                                  outputs=[chain_state, express_chain_state, llm_state, embeddings_state,
+                                           qa_chain_state, memory_state, use_gpt4_state])
+    openai_api_key_textbox.submit(set_openai_api_key,
+                                  inputs=[openai_api_key_textbox, use_gpt4_state],
+                                  outputs=[chain_state, express_chain_state, llm_state, embeddings_state,
+                                           qa_chain_state, memory_state, use_gpt4_state])
+    # if (os.environ["OPENAI_API_KEY"] is not None):
+    #     openai_api_key_textbox.value = os.environ["OPENAI_API_KEY"]
+
+block.launch(debug=True)

azure_utils.py

@@ -0,0 +1,155 @@
+# This class stores Azure voice data. Specifically, the class stores several records containing
+# language, lang_code, gender, voice_id and engine. The class also has a method to return the
+# voice_id, lang_code and engine given a language and gender.
+
+NEURAL_ENGINE = "neural"
+STANDARD_ENGINE = "standard"
+
+
+class AzureVoiceData:
+    def get_voice(self, language, gender):
+        for voice in self.voice_data:
+            if voice['language'] == language and voice['gender'] == gender:
+                return voice['azure_voice']
+        return None
+
+    def __init__(self):
+        self.voice_data = [
+            {'language': 'Arabic',
+             'azure_voice': 'ar-EG-ShakirNeural',
+             'gender': 'Male'},
+            {'language': 'Arabic (Gulf)',
+             'azure_voice': 'ar-KW-FahedNeural',
+             'gender': 'Male'},
+            {'language': 'Catalan',
+             'azure_voice': 'ca-ES-EnricNeural',
+             'gender': 'Male'},
+            {'language': 'Chinese (Cantonese)',
+             'azure_voice': 'yue-CN-YunSongNeural',
+             'gender': 'Male'},
+            {'language': 'Chinese (Mandarin)',
+             'azure_voice': 'zh-CN-YunxiNeural',
+             'gender': 'Male'},
+            {'language': 'Danish',
+             'azure_voice': 'da-DK-JeppeNeural',
+             'gender': 'Male'},
+            {'language': 'Dutch',
+             'azure_voice': 'nl-NL-MaartenNeural',
+             'gender': 'Male'},
+            {'language': 'English (Australian)',
+             'azure_voice': 'en-AU-KenNeural',
+             'gender': 'Male'},
+            {'language': 'English (British)',
+             'azure_voice': 'en-GB-RyanNeural',
+             'gender': 'Male'},
+            {'language': 'English (Indian)',
+             'azure_voice': 'en-IN-PrabhatNeural',
+             'gender': 'Male'},
+            {'language': 'English (New Zealand)',
+             'azure_voice': 'en-NZ-MitchellNeural',
+             'gender': 'Male'},
+            {'language': 'English (South African)',
+             'azure_voice': 'en-ZA-LukeNeural',
+             'gender': 'Male'},
+            {'language': 'English (US)',
+             'azure_voice': 'en-US-ChristopherNeural',
+             'gender': 'Male'},
+            {'language': 'English (Welsh)',
+             'azure_voice': 'cy-GB-AledNeural',
+             'gender': 'Male'},
+            {'language': 'Finnish',
+             'azure_voice': 'fi-FI-HarriNeural',
+             'gender': 'Male'},
+            {'language': 'French',
+             'azure_voice': 'fr-FR-HenriNeural',
+             'gender': 'Male'},
+            {'language': 'French (Canadian)',
+             'azure_voice': 'fr-CA-AntoineNeural',
+             'gender': 'Male'},
+            {'language': 'German',
+             'azure_voice': 'de-DE-KlausNeural',
+             'gender': 'Male'},
+            {'language': 'German (Austrian)',
+             'azure_voice': 'de-AT-JonasNeural',
+             'gender': 'Male'},
+            {'language': 'Hindi',
+             'azure_voice': 'hi-IN-MadhurNeural',
+             'gender': 'Male'},
+            {'language': 'Icelandic',
+             'azure_voice': 'is-IS-GunnarNeural',
+             'gender': 'Male'},
+            {'language': 'Italian',
+             'azure_voice': 'it-IT-GianniNeural',
+             'gender': 'Male'},
+            {'language': 'Japanese',
+             'azure_voice': 'ja-JP-KeitaNeural',
+             'gender': 'Male'},
+            {'language': 'Korean',
+             'azure_voice': 'ko-KR-GookMinNeural',
+             'gender': 'Male'},
+            {'language': 'Norwegian',
+             'azure_voice': 'nb-NO-FinnNeural',
+             'gender': 'Male'},
+            {'language': 'Polish',
+             'azure_voice': 'pl-PL-MarekNeural',
+             'gender': 'Male'},
+            {'language': 'Portuguese (Brazilian)',
+             'azure_voice': 'pt-BR-NicolauNeural',
+             'gender': 'Male'},
+            {'language': 'Portuguese (European)',
+             'azure_voice': 'pt-PT-DuarteNeural',
+             'gender': 'Male'},
+            {'language': 'Romanian',
+             'azure_voice': 'ro-RO-EmilNeural',
+             'gender': 'Male'},
+            {'language': 'Russian',
+             'azure_voice': 'ru-RU-DmitryNeural',
+             'gender': 'Male'},
+            {'language': 'Spanish (European)',
+             'azure_voice': 'es-ES-TeoNeural',
+             'gender': 'Male'},
+            {'language': 'Spanish (Mexican)',
+             'azure_voice': 'es-MX-LibertoNeural',
+             'gender': 'Male'},
+            {'language': 'Spanish (US)',
+             'azure_voice': 'es-US-AlonsoNeural"',
+             'gender': 'Male'},
+            {'language': 'Swedish',
+             'azure_voice': 'sv-SE-MattiasNeural',
+             'gender': 'Male'},
+            {'language': 'Turkish',
+             'azure_voice': 'tr-TR-AhmetNeural',
+             'gender': 'Male'},
+            {'language': 'Welsh',
+             'azure_voice': 'cy-GB-AledNeural',
+             'gender': 'Male'},
+        ]
+
+
+# Run from the command-line
+if __name__ == '__main__':
+    azure_voice_data = AzureVoiceData()
+
+    azure_voice = azure_voice_data.get_voice('English (US)', 'Male')
+    print('English (US)', 'Male', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('English (US)', 'Female')
+    print('English (US)', 'Female', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('French', 'Female')
+    print('French', 'Female', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('French', 'Male')
+    print('French', 'Male', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('Japanese', 'Female')
+    print('Japanese', 'Female', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('Japanese', 'Male')
+    print('Japanese', 'Male', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('Hindi', 'Female')
+    print('Hindi', 'Female', azure_voice)
+
+    azure_voice = azure_voice_data.get_voice('Hindi', 'Male')
+    print('Hindi', 'Male', azure_voice)

polly_utils.py

@@ -0,0 +1,633 @@
+# This class stores Polly voice data. Specifically, the class stores several records containing
+# language, lang_code, gender, voice_id and engine. The class also has a method to return the
+# voice_id, lang_code and engine given a language and gender.
+
+NEURAL_ENGINE = "neural"
+STANDARD_ENGINE = "standard"
+
+
+class PollyVoiceData:
+    def get_voice(self, language, gender):
+        for voice in self.voice_data:
+            if voice['language'] == language and voice['gender'] == gender:
+                if voice['neural'] == 'Yes':
+                    return voice['voice_id'], voice['lang_code'], NEURAL_ENGINE
+        for voice in self.voice_data:
+            if voice['language'] == language and voice['gender'] == gender:
+                if voice['standard'] == 'Yes':
+                    return voice['voice_id'], voice['lang_code'], STANDARD_ENGINE
+        return None, None, None
+
+    def get_whisper_lang_code(self, language):
+        for voice in self.voice_data:
+            if voice['language'] == language:
+                return voice['whisper_lang_code']
+        return "en"
+
+    def __init__(self):
+        self.voice_data = [
+            {'language': 'Arabic',
+             'lang_code': 'arb',
+             'whisper_lang_code': 'ar',
+             'voice_id': 'Zeina',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Arabic (Gulf)',
+             'lang_code': 'ar-AE',
+             'whisper_lang_code': 'ar',
+             'voice_id': 'Hala',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Catalan',
+             'lang_code': 'ca-ES',
+             'whisper_lang_code': 'ca',
+             'voice_id': 'Arlet',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Chinese (Cantonese)',
+             'lang_code': 'yue-CN',
+             'whisper_lang_code': 'zh',
+             'voice_id': 'Hiujin',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Chinese (Mandarin)',
+             'lang_code': 'cmn-CN',
+             'whisper_lang_code': 'zh',
+             'voice_id': 'Zhiyu',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Danish',
+             'lang_code': 'da-DK',
+             'whisper_lang_code': 'da',
+             'voice_id': 'Naja',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Danish',
+             'lang_code': 'da-DK',
+             'whisper_lang_code': 'da',
+             'voice_id': 'Mads',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Dutch',
+             'lang_code': 'nl-NL',
+             'whisper_lang_code': 'nl',
+             'voice_id': 'Laura',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Dutch',
+             'lang_code': 'nl-NL',
+             'whisper_lang_code': 'nl',
+             'voice_id': 'Lotte',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Dutch',
+             'lang_code': 'nl-NL',
+             'whisper_lang_code': 'nl',
+             'voice_id': 'Ruben',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'English (Australian)',
+             'lang_code': 'en-AU',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Nicole',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'English (Australian)',
+             'lang_code': 'en-AU',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Olivia',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (Australian)',
+             'lang_code': 'en-AU',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Russell',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'English (British)',
+             'lang_code': 'en-GB',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Amy',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (British)',
+             'lang_code': 'en-GB',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Emma',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (British)',
+             'lang_code': 'en-GB',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Brian',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (British)',
+             'lang_code': 'en-GB',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Arthur',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (Indian)',
+             'lang_code': 'en-IN',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Aditi',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'English (Indian)',
+             'lang_code': 'en-IN',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Raveena',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'English (Indian)',
+             'lang_code': 'en-IN',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Kajal',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (New Zealand)',
+             'lang_code': 'en-NZ',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Aria',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (South African)',
+             'lang_code': 'en-ZA',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Ayanda',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Ivy',
+             'gender': 'Female (child)',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Joanna',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Kendra',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Kimberly',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Salli',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Joey',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Justin',
+             'gender': 'Male (child)',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Kevin',
+             'gender': 'Male (child)',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'English (US)',
+             'lang_code': 'en-US',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Matthew',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'English (Welsh)',
+             'lang_code': 'en-GB-WLS',
+             'whisper_lang_code': 'en',
+             'voice_id': 'Geraint',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Finnish',
+             'lang_code': 'fi-FI',
+             'whisper_lang_code': 'fi',
+             'voice_id': 'Suvi',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'French',
+             'lang_code': 'fr-FR',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Celine',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'French',
+             'lang_code': 'fr-FR',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Lea',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'French',
+             'lang_code': 'fr-FR',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Mathieu',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'French (Canadian)',
+             'lang_code': 'fr-CA',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Chantal',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'French (Canadian)',
+             'lang_code': 'fr-CA',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Gabrielle',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'French (Canadian)',
+             'lang_code': 'fr-CA',
+             'whisper_lang_code': 'fr',
+             'voice_id': 'Liam',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'German',
+             'lang_code': 'de-DE',
+             'whisper_lang_code': 'de',
+             'voice_id': 'Marlene',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'German',
+             'lang_code': 'de-DE',
+             'whisper_lang_code': 'de',
+             'voice_id': 'Vicki',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'German',
+             'lang_code': 'de-DE',
+             'whisper_lang_code': 'de',
+             'voice_id': 'Hans',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'German',
+             'lang_code': 'de-DE',
+             'whisper_lang_code': 'de',
+             'voice_id': 'Daniel',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'German (Austrian)',
+             'lang_code': 'de-AT',
+             'whisper_lang_code': 'de',
+             'voice_id': 'Hannah',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Hindi',
+             'lang_code': 'hi-IN',
+             'whisper_lang_code': 'hi',
+             'voice_id': 'Aditi',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Hindi',
+             'lang_code': 'hi-IN',
+             'whisper_lang_code': 'hi',
+             'voice_id': 'Kajal',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Icelandic',
+             'lang_code': 'is-IS',
+             'whisper_lang_code': 'is',
+             'voice_id': 'Dora',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Icelandic',
+             'lang_code': 'is-IS',
+             'whisper_lang_code': 'is',
+             'voice_id': 'Karl',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Italian',
+             'lang_code': 'it-IT',
+             'whisper_lang_code': 'it',
+             'voice_id': 'Carla',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Italian',
+             'lang_code': 'it-IT',
+             'whisper_lang_code': 'it',
+             'voice_id': 'Bianca',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Japanese',
+             'lang_code': 'ja-JP',
+             'whisper_lang_code': 'ja',
+             'voice_id': 'Mizuki',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Japanese',
+             'lang_code': 'ja-JP',
+             'whisper_lang_code': 'ja',
+             'voice_id': 'Takumi',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Korean',
+             'lang_code': 'ko-KR',
+             'whisper_lang_code': 'ko',
+             'voice_id': 'Seoyeon',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Norwegian',
+             'lang_code': 'nb-NO',
+             'whisper_lang_code': 'no',
+             'voice_id': 'Liv',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Norwegian',
+             'lang_code': 'nb-NO',
+             'whisper_lang_code': 'no',
+             'voice_id': 'Ida',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Polish',
+             'lang_code': 'pl-PL',
+             'whisper_lang_code': 'pl',
+             'voice_id': 'Ewa',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Polish',
+             'lang_code': 'pl-PL',
+             'whisper_lang_code': 'pl',
+             'voice_id': 'Maja',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Polish',
+             'lang_code': 'pl-PL',
+             'whisper_lang_code': 'pl',
+             'voice_id': 'Jacek',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Polish',
+             'lang_code': 'pl-PL',
+             'whisper_lang_code': 'pl',
+             'voice_id': 'Jan',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Polish',
+             'lang_code': 'pl-PL',
+             'whisper_lang_code': 'pl',
+             'voice_id': 'Ola',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Portuguese (Brazilian)',
+             'lang_code': 'pt-BR',
+             'whisper_lang_code': 'pt',
+             'voice_id': 'Camila',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Portuguese (Brazilian)',
+             'lang_code': 'pt-BR',
+             'whisper_lang_code': 'pt',
+             'voice_id': 'Vitoria',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Portuguese (Brazilian)',
+             'lang_code': 'pt-BR',
+             'whisper_lang_code': 'pt',
+             'voice_id': 'Ricardo',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Portuguese (European)',
+             'lang_code': 'pt-PT',
+             'whisper_lang_code': 'pt',
+             'voice_id': 'Ines',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Portuguese (European)',
+             'lang_code': 'pt-PT',
+             'whisper_lang_code': 'pt',
+             'voice_id': 'Cristiano',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Romanian',
+             'lang_code': 'ro-RO',
+             'whisper_lang_code': 'ro',
+             'voice_id': 'Carmen',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Russian',
+             'lang_code': 'ru-RU',
+             'whisper_lang_code': 'ru',
+             'voice_id': 'Tatyana',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Russian',
+             'lang_code': 'ru-RU',
+             'whisper_lang_code': 'ru',
+             'voice_id': 'Maxim',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Spanish (European)',
+             'lang_code': 'es-ES',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Conchita',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Spanish (European)',
+             'lang_code': 'es-ES',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Lucia',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Spanish (European)',
+             'lang_code': 'es-ES',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Enrique',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Spanish (Mexican)',
+             'lang_code': 'es-MX',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Mia',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Spanish (US)',
+             'lang_code': 'es-US',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Lupe',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'Yes'},
+            {'language': 'Spanish (US)',
+             'lang_code': 'es-US',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Penelope',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Spanish (US)',
+             'lang_code': 'es-US',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Miguel',
+             'gender': 'Male',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Spanish (US)',
+             'lang_code': 'es-US',
+             'whisper_lang_code': 'es',
+             'voice_id': 'Pedro',
+             'gender': 'Male',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Swedish',
+             'lang_code': 'sv-SE',
+             'whisper_lang_code': 'sv',
+             'voice_id': 'Astrid',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Swedish',
+             'lang_code': 'sv-SE',
+             'whisper_lang_code': 'sv',
+             'voice_id': 'Elin',
+             'gender': 'Female',
+             'neural': 'Yes',
+             'standard': 'No'},
+            {'language': 'Turkish',
+             'lang_code': 'tr-TR',
+             'whisper_lang_code': 'tr',
+             'voice_id': 'Filiz',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'},
+            {'language': 'Welsh',
+             'lang_code': 'cy-GB',
+             'whisper_lang_code': 'cy',
+             'voice_id': 'Gwyneth',
+             'gender': 'Female',
+             'neural': 'No',
+             'standard': 'Yes'}
+        ]
+
+
+# Run from the command-line
+if __name__ == '__main__':
+    polly_voice_data = PollyVoiceData()
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('English (US)', 'Male')
+    print('English (US)', 'Male', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('English (US)', 'Female')
+    print('English (US)', 'Female', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('French', 'Female')
+    print('French', 'Female', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('French', 'Male')
+    print('French', 'Male', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('Japanese', 'Female')
+    print('Japanese', 'Female', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('Japanese', 'Male')
+    print('Japanese', 'Male', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('Hindi', 'Female')
+    print('Hindi', 'Female', voice_id, language_code, engine)
+
+    voice_id, language_code, engine = polly_voice_data.get_voice('Hindi', 'Male')
+    print('Hindi', 'Male', voice_id, language_code, engine)
+
+    whisper_lang_code = polly_voice_data.get_whisper_lang_code('English (US)')
+    print('English (US) whisper_lang_code:', whisper_lang_code)
+
+    whisper_lang_code = polly_voice_data.get_whisper_lang_code('Chinese (Mandarin)')
+    print('Chinese (Mandarin) whisper_lang_code:', whisper_lang_code)
+
+    whisper_lang_code = polly_voice_data.get_whisper_lang_code('Norwegian')
+    print('Norwegian whisper_lang_code:', whisper_lang_code)
+
+    whisper_lang_code = polly_voice_data.get_whisper_lang_code('Dutch')
+    print('Dutch whisper_lang_code:', whisper_lang_code)
+
+    whisper_lang_code = polly_voice_data.get_whisper_lang_code('Foo')
+    print('Foo whisper_lang_code:', whisper_lang_code)

requirements.txt

@@ -0,0 +1,10 @@
+openai==0.27.2
+gradio==3.21.0
+google-search-results==2.4.2
+google-api-python-client==2.81.0
+wolframalpha
+langchain==0.0.113
+requests==2.28.2
+git+https://github.com/openai/whisper.git
+boto3==1.26.93
+faiss-cpu