first commit

.gitignore

@@ -0,0 +1,166 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+LangChain_llm_Agent.py
+streamlit_app.py
+gemini-flash-app.py
+code_not_using_vertex.py

.streamlit/config.toml

@@ -0,0 +1,9 @@
+[theme]
+primaryColor="#f81f6f"
+backgroundColor="#00000e"
+secondaryBackgroundColor="#111930"
+textColor="#f5f8fc"
+font="sans serif"
+
+[server]
+runOnSave = true

main.py

@@ -0,0 +1,312 @@
+import streamlit as st
+from audio_recorder_streamlit import audio_recorder
+from streamlit_vertical_slider import vertical_slider
+from streamlit_lottie import st_lottie
+import json
+from PIL import Image
+from io import BytesIO
+import base64
+from utils import visualize_display_page
+import google.generativeai as genai
+from langchain_groq import ChatGroq
+import os , random
+from dotenv import load_dotenv
+load_dotenv()
+
+st.set_page_config(
+    page_title="Super GPT",
+    page_icon="👽",
+    layout="wide",
+    initial_sidebar_state="auto",
+)
+
+st.title("Super GPT Assistant")
+
+google_models = [
+    "gemini-1.5-flash",
+    "gemini-1.5-pro",
+]
+
+groq_models = [
+    "llama-3.1-8b-instant",
+    "llama-3.1-70b-versatile",
+    "llama3-70b-8192",
+    "llama3-8b-8192",
+    "gemma2-9b-it",
+    "mixtral-8x7b-32768"
+]
+
+
+@st.cache_data
+def load_lottie_file(filepath: str):
+    with open(filepath, "r") as f:
+        return json.load(f)
+
+def get_llm_info(available_models):
+    with st.sidebar:
+        tip =tip = "Select Gemini models if you require multi-modal capabilities (text, image, audio and video inputs)"
+        model = st.selectbox("Choose LLM:", available_models, help=tip)
+
+        model_type = None
+        if model.startswith(("llama", "gemma", "mixtral")): model_type = "groq"
+        elif model.startswith("gemini"): model_type = "google"
+
+        with st.popover("⚙️Model Parameters", use_container_width=True):
+            temp = st.slider("Temperature:", min_value=0.0,
+                                            max_value=2.0, value=0.5, step=0.5)
+            
+            max_tokens = st.slider("Maximum Tokens:", min_value=100,
+                                        max_value=2000, value=400, step=200)
+    return model, model_type, temp, max_tokens
+
+def messages_to_gemini(messages):
+    gemini_messages = []
+    prev_role = None
+    for message in messages:
+        if prev_role and (prev_role == message["role"]):
+            gemini_message = gemini_messages[-1]
+        else:
+            gemini_message = {
+                "role": "model" if message["role"] == "assistant" else "user",
+                "parts": [],
+            }
+
+        for content in message["content"]:
+            if content["type"] == "text":
+                gemini_message["parts"].append(content["text"])
+            elif content["type"] == "image_url":
+                gemini_message["parts"].append(base64_to_image(content["image_url"]["url"]))
+            elif content["type"] == "video_file":
+                gemini_message["parts"].append(genai.upload_file(content["video_file"]))
+            elif content["type"] == "audio_file":
+                gemini_message["parts"].append(genai.upload_file(content["audio_file"]))
+
+        if prev_role != message["role"]:
+            gemini_messages.append(gemini_message)
+
+        prev_role = message["role"]
+        
+    return gemini_messages
+
+# Function to convert file to base64
+def get_image_base64(image_raw):
+    buffered = BytesIO()
+    image_raw.save(buffered, format=image_raw.format)
+    img_byte = buffered.getvalue()
+
+    return base64.b64encode(img_byte).decode('utf-8')
+
+
+def add_media_files_to_messages():
+    if st.session_state.uploaded_file:
+        file_type = st.session_state.uploaded_file.type
+        file_content = st.session_state.uploaded_file.getvalue()
+        
+        if file_type.startswith("image"):
+            img = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "image_url",
+                        "image_url": {"url": f"data:{file_type};base64,{img}"}
+                    }]
+                }
+            )
+        elif file_type == "video/mp4":
+            video_base64 = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "video_file",
+                        "video_file": f"data:{file_type};base64,{video_base64}",
+                    }]
+                }
+            )
+        elif file_type.startswith("audio"):
+            audio_base64 = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "audio_file",
+                        "audio_file": f"data:{file_type};base64,{audio_base64}",
+                    }]
+                }
+            )
+
+
+def add_camera_img_to_messages():
+    if "camera_img" in st.session_state and st.session_state.camera_img:
+        img = base64.b64encode(st.session_state.camera_img.getvalue()).decode()
+        st.session_state.messages.append(
+            {
+                "role": "user", 
+                "content": [{
+                    "type": "image_url",
+                    "image_url": {"url": f"data:image/jpeg;base64,{img}"}
+                }]
+            }
+        )
+
+
+
+with st.sidebar:
+    st.logo("logo.png")
+    api_cols = st.columns(2)
+    with api_cols[0]:
+        default_groq_api_key = os.getenv("GROQ_API_KEY") if os.getenv("GROQ_API_KEY") is not None else ""  # only for development environment, otherwise it should return None
+        with st.popover("🔐 Groq", use_container_width=True):
+            groq_api_key = st.text_input("Get your Groq API Key (https://console.groq.com/keys)", value=default_groq_api_key, type="password")
+    
+    with api_cols[1]:
+        default_google_api_key = os.getenv("GOOGLE_API_KEY") if os.getenv("GOOGLE_API_KEY") is not None else ""  # only for development environment, otherwise it should return None
+        with st.popover("🔐 Google", use_container_width=True):
+            google_api_key = st.text_input("Get your Google API Key (https://aistudio.google.com/app/apikey)", value=default_google_api_key, type="password")
+    
+
+if (groq_api_key == "" or groq_api_key is None or "gsk" not in groq_api_key) and (google_api_key == "" or google_api_key is None or "AIza" not in google_api_key):
+    st.warning("Please Add an API Key to proceed.")
+
+else:
+    col1, col2 = st.columns([1,6])
+
+    with col1:
+
+        audio_bytes = audio_recorder("Speak",
+                                     neutral_color="#728796",
+                                     recording_color="#f81f6f",
+                                     icon_name="microphone-lines",
+                                     icon_size="3x")
+
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+    # Handle speech input
+    if "prev_speech_hash" not in st.session_state:
+        st.session_state.prev_speech_hash = None
+
+    if audio_bytes and st.session_state.prev_speech_hash != hash(audio_bytes):
+        st.session_state.prev_speech_hash = hash(audio_bytes)
+        speech_base64 = base64.b64encode(audio_bytes).decode()
+        st.session_state.messages.append(
+            {
+                "role": "user",
+                "content": [{
+                    "type": "speech_input",
+                    "speech_input": f"data:audio/wav;base64,{speech_base64}",
+                }]
+            }
+        )
+
+    for message in st.session_state.messages:
+        with col2:
+            with st.chat_message(message["role"]):
+                for content in message["content"]:
+                    if content["type"] == "text":
+                        st.markdown(content["text"])
+                    elif content["type"] == "image_url":      
+                        st.image(content["image_url"]["url"], use_column_width=True)
+                    elif content["type"] == "video_file":
+                        st.video(content["video_file"])
+                    elif content["type"] == "audio_file":
+                        st.audio(content["audio_file"], autoplay=True)
+                    elif content["type"] == "speech_input":
+                        st.audio(content["speech_input"])
+
+    with st.sidebar:
+        st.divider()
+        columns = st.columns(2)
+        # animation
+        with columns[0]:
+            lottie_animation = load_lottie_file("animation.json")
+            if lottie_animation:
+                st_lottie(lottie_animation, height=100, width=100, quality="high", key="lottie_anim")
+
+        with columns[1]:
+            if st.toggle("Voice Response"):
+                response_lang = st.selectbox("Available Voices:", options=["Alex","Ana","Daniel"], key="voice_response")
+        
+        available_models = []  + (google_models if google_api_key else []) + (groq_models if groq_api_key else [])
+        model, model_type, temperature, max_tokens = get_llm_info(available_models)
+        st.divider()
+
+        if model_type == "google":
+            st.write("Upload a file or take a picture")
+
+            media_cols = st.columns(2)
+
+            with media_cols[0]:
+                with st.popover("📁 Upload", use_container_width=True):
+                    st.file_uploader(
+                        "Upload an image, audio or a video", 
+                        type=["png", "jpg", "jpeg", "wav", "mp3", "mp4"], 
+                        accept_multiple_files=False,
+                        key="uploaded_file",
+                        on_change=add_media_files_to_messages,
+                    )
+
+            with media_cols[1]:                    
+                with st.popover("📷 Camera", use_container_width=True):
+                    activate_camera = st.checkbox("Activate camera")
+                    if activate_camera:
+                        st.camera_input(
+                            "Take a picture", 
+                            key="camera_img",
+                            on_change=add_camera_img_to_messages,
+                        )
+    
+        
+        
+        
+        
+        
+        
+        
+        else:
+            pass
+
+
+
+
+
+    # temperature = vertical_slider(
+    #     label = "Temperature",  #Optional
+    #     key = "vert_01" ,
+    #     height = 100, #Optional - Defaults to 300#Optional - Defaults to "circle"
+    #     step = 1, #Optional - Defaults to 1
+    #     default_value=5,#Optional - Defaults to 0
+    #     min_value= 0, # Defaults to 0
+    #     max_value= 10, # Defaults to 10
+    #     track_color = "blue",
+    #     thumb_shape="square", #Optional - Defaults to #D3D3D3
+    #     slider_color = 'lighgray', #Optional - Defaults to #29B5E8
+    #     thumb_color= "orange", #Optional - Defaults to #11567f
+    #     value_always_visible = False ,#Optional - Defaults to False
+    # )
+
+
+                                
+
+
+
+if prompt:= st.chat_input("Type you question", key="question"):
+
+    with col2:
+        st.session_state.messages.append(
+                    {
+                        "role": "user", 
+                        "content": [{
+                            "type": "text",
+                            "text": prompt,
+                        }]
+                    }
+                )
+        st.chat_message("user").markdown(prompt)
+# Confirmation popup window
+# selection_dict = {"file_and_answer": "", "prompt": "", "respuesta_chat": ""}
+# st.button("Visualize", on_click=visualize_display_page, key="visualiza", args=[selection_dict])
+
+
+

requirements.txt

@@ -0,0 +1,13 @@
+streamlit
+google-generativeai
+audio-recorder-streamlit
+streamlit_toggle
+streamlit-vertical-slider
+streamlit-lottie
+streamlit-float
+python-dotenv
+langchain
+langchain-groq
+langchain_community
+pypdf
+pdfplumber

test.py

@@ -0,0 +1,413 @@
+import streamlit as st
+from audio_recorder_streamlit import audio_recorder
+from streamlit_vertical_slider import vertical_slider
+from streamlit_lottie import st_lottie
+import json
+from PIL import Image
+from io import BytesIO
+import base64
+from utils import visualize_display_page, about, set_safety_settings
+import google.generativeai as genai
+from langchain_groq import ChatGroq
+import os , random
+from dotenv import load_dotenv
+load_dotenv()
+
+st.set_page_config(
+    page_title="Super GPT",
+    page_icon="⚡",
+    layout="wide",
+    initial_sidebar_state="auto",
+    menu_items={"About": about(), "Get Help":"https://www.linkedin.com/in/aasher-kamal-a227a124b/"},
+)
+
+###--- Title ---###
+st.markdown("""
+    <h1 style='text-align: center;'>
+        <span style='color: #F81F6F;'>Super</span> 
+        <span style='color: #f5f8fc;'>GPT Assistant</span>
+    </h1>
+""", unsafe_allow_html=True)
+
+
+google_models = [
+    "gemini-1.5-flash",
+    "gemini-1.5-pro",
+]
+
+groq_models = [
+    "llama-3.1-8b-instant",
+    "llama-3.1-70b-versatile",
+    "llama3-70b-8192",
+    "llama3-8b-8192",
+    "gemma2-9b-it",
+    "mixtral-8x7b-32768"
+]
+
+
+@st.cache_data
+def load_lottie_file(filepath: str):
+    with open(filepath, "r") as f:
+        return json.load(f)
+
+def get_llm_info(available_models):
+    with st.sidebar:
+        tip =tip = "Select Gemini models if you require multi-modal capabilities (text, image, audio and video inputs)"
+        model = st.selectbox("Choose LLM:", available_models, help=tip)
+
+        model_type = None
+        if model.startswith(("llama", "gemma", "mixtral")): model_type = "groq"
+        elif model.startswith("gemini"): model_type = "google"
+
+        with st.popover("⚙️Model Parameters", use_container_width=True):
+            temp = st.slider("Temperature:", min_value=0.0,
+                                            max_value=2.0, value=0.5, step=0.5)
+            
+            max_tokens = st.slider("Maximum Tokens:", min_value=100,
+                                        max_value=2000, value=400, step=200)
+    return model, model_type, temp, max_tokens
+
+
+def base64_to_temp_file(base64_string, file_extension):
+    base64_string = base64_string.split(",")[1]
+    file_bytes = BytesIO(base64.b64decode(base64_string))
+    temp_file_path = f"temp_file.{file_extension}"
+    with open(temp_file_path, "wb") as temp_file:
+        temp_file.write(file_bytes.read())
+    return temp_file_path
+
+
+def messages_to_gemini(messages):
+    gemini_messages = []
+    prev_role = None
+    for message in messages:
+        if prev_role and (prev_role == message["role"]):
+            gemini_message = gemini_messages[-1]
+        else:
+            gemini_message = {
+                "role": "model" if message["role"] == "assistant" else "user",
+                "parts": [],
+            }
+
+        for content in message["content"]:
+            if content["type"] == "text":
+                gemini_message["parts"].append(content["text"])
+            elif content["type"] == "image_url":
+                gemini_message["parts"].append(base64_to_image(content["image_url"]["url"]))
+
+            elif content["type"] == "video_file":
+                video_file_path = base64_to_temp_file(content["video_file"], "mp4")
+                with st.spinner("Sending video file to Gemini..."):
+                    gemini_message["parts"].append(genai.upload_file(path=video_file_path))
+                os.remove(video_file_path)
+
+            elif content["type"] == "audio_file":
+                audio_file_path = base64_to_temp_file(content["audio_file"], "wav")
+                with st.spinner("Sending audio file to Gemini..."):
+                    gemini_message["parts"].append(genai.upload_file(path=audio_file_path))
+                os.remove(audio_file_path)
+
+            elif content["type"] == "speech_input":
+                speech_file_path = base64_to_temp_file(content["speech_input"], "wav")
+                with st.spinner("Sending audio file to Gemini..."):
+                    gemini_message["parts"].append(genai.upload_file(path=speech_file_path))
+                os.remove(speech_file_path)
+
+        if prev_role != message["role"]:
+            gemini_messages.append(gemini_message)
+
+        prev_role = message["role"]
+
+    return gemini_messages
+
+
+
+def base64_to_image(base64_string):
+    base64_string = base64_string.split(",")[1]
+    
+    return Image.open(BytesIO(base64.b64decode(base64_string)))
+
+def add_media_files_to_messages():
+    if st.session_state.uploaded_file:
+        file_type = st.session_state.uploaded_file.type
+        file_content = st.session_state.uploaded_file.getvalue()
+        
+        if file_type.startswith("image"):
+            img = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "image_url",
+                        "image_url": {"url": f"data:{file_type};base64,{img}"}
+                    }]
+                }
+            )
+        elif file_type == "video/mp4":
+            video_base64 = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "video_file",
+                        "video_file": f"data:{file_type};base64,{video_base64}",
+                    }]
+                }
+            )
+        elif file_type.startswith("audio"):
+            audio_base64 = base64.b64encode(file_content).decode()
+            st.session_state.messages.append(
+                {
+                    "role": "user", 
+                    "content": [{
+                        "type": "audio_file",
+                        "audio_file": f"data:{file_type};base64,{audio_base64}",
+                    }]
+                }
+            )
+
+
+def add_camera_img_to_messages():
+    if "camera_img" in st.session_state and st.session_state.camera_img:
+        img = base64.b64encode(st.session_state.camera_img.getvalue()).decode()
+        st.session_state.messages.append(
+            {
+                "role": "user", 
+                "content": [{
+                    "type": "image_url",
+                    "image_url": {"url": f"data:image/jpeg;base64,{img}"}
+                }]
+            }
+        )
+
+
+def reset_conversation():
+    if "messages" in st.session_state and len(st.session_state.messages) > 0:
+        st.session_state.pop("messages", None)
+
+    for file in genai.list_files():
+        genai.delete_file(file.name)
+
+
+def stream_llm_response(model_params, model_type="google", api_key=None):
+    response_message = ""
+    if model_type == "google": 
+        genai.configure(api_key=api_key)
+        model = genai.GenerativeModel(
+                model_name = model_params["model"],
+                generation_config={
+                    "temperature": model_params["temperature"],
+                    "max_output_tokens": model_params["max_tokens"],
+                },
+                safety_settings=set_safety_settings(),
+                system_instruction="""You are a helpful assistant who asnwers user's questions professionally and politely."""
+            )
+        gemini_messages = messages_to_gemini(st.session_state.messages)
+
+        for chunk in model.generate_content(contents=gemini_messages, stream=True,):
+            chunk_text = chunk.text or ""
+            response_message += chunk_text
+            yield chunk_text
+
+    st.session_state.messages.append({
+    "role": "assistant", 
+    "content": [
+        {
+            "type": "text",
+            "text": response_message,
+        }
+    ]})
+
+
+
+
+
+with st.sidebar:
+    st.logo("logo.png")
+    api_cols = st.columns(2)
+    with api_cols[0]:
+        default_groq_api_key = os.getenv("GROQ_API_KEY") if os.getenv("GROQ_API_KEY") is not None else ""  # only for development environment, otherwise it should return None
+        with st.popover("🔐 Groq", use_container_width=True):
+            groq_api_key = st.text_input("Get your Groq API Key (https://console.groq.com/keys)", value=default_groq_api_key, type="password")
+    
+    with api_cols[1]:
+        default_google_api_key = os.getenv("GOOGLE_API_KEY") if os.getenv("GOOGLE_API_KEY") is not None else ""  # only for development environment, otherwise it should return None
+        with st.popover("🔐 Google", use_container_width=True):
+            google_api_key = st.text_input("Get your Google API Key (https://aistudio.google.com/app/apikey)", value=default_google_api_key, type="password")
+ 
+
+if (groq_api_key == "" or groq_api_key is None or "gsk" not in groq_api_key) and (google_api_key == "" or google_api_key is None or "AIza" not in google_api_key):
+    st.warning("Please Add an API Key to proceed.")
+
+
+else:
+    with st.sidebar:
+        st.divider()
+        columns = st.columns(2)
+        # animation
+        with columns[0]:
+            lottie_animation = load_lottie_file("animation.json")
+            if lottie_animation:
+                st_lottie(lottie_animation, height=100, width=100, quality="high", key="lottie_anim")
+
+        with columns[1]:
+            if st.toggle("Voice Response"):
+                response_lang = st.selectbox("Available Voices:", options=["Alex","Ana","Daniel"], key="voice_response")
+        
+        available_models = []  + (google_models if google_api_key else []) + (groq_models if groq_api_key else [])
+        model, model_type, temperature, max_tokens = get_llm_info(available_models)
+
+        model_params = {
+                "model": model,
+                "temperature": temperature,
+                "max_tokens": max_tokens
+            }
+        
+        st.divider()
+
+        if model_type == "google":
+            st.write("Upload a file or take a picture")
+
+            media_cols = st.columns(2)
+
+            with media_cols[0]:
+                with st.popover("📁 Upload", use_container_width=True):
+                    st.file_uploader(
+                        "Upload an image, audio or a video", 
+                        type=["png", "jpg", "jpeg", "wav", "mp3", "mp4"], 
+                        accept_multiple_files=False,
+                        key="uploaded_file",
+                        on_change=add_media_files_to_messages,
+                    )
+
+            with media_cols[1]:                    
+                with st.popover("📷 Camera", use_container_width=True):
+                    activate_camera = st.checkbox("Activate camera")
+                    if activate_camera:
+                        st.camera_input(
+                            "Take a picture", 
+                            key="camera_img",
+                            on_change=add_camera_img_to_messages,
+                        )
+
+        
+        else:
+            pass
+
+######-----  Main Interface -----#######
+    chat_col1, chat_col2 = st.columns([1,6])
+
+    with chat_col1:
+        ###--- Audio Recording ---###
+        audio_bytes = audio_recorder("Speak",
+                                     neutral_color="#f5f8fc",
+                                     recording_color="#f81f6f",
+                                     icon_name="microphone-lines",
+                                     icon_size="3x")
+
+        ###--- Reset Conversation ---###
+        st.button(
+                "🗑️ Reset",
+                use_container_width=True,
+                on_click=reset_conversation,
+                help="If clicked, conversation will be reset.",
+            )
+
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+    # Handle speech input
+    if "prev_speech_hash" not in st.session_state:
+        st.session_state.prev_speech_hash = None
+
+    if audio_bytes and st.session_state.prev_speech_hash != hash(audio_bytes):
+        st.session_state.prev_speech_hash = hash(audio_bytes)
+        speech_base64 = base64.b64encode(audio_bytes).decode()
+        st.session_state.messages.append(
+            {
+                "role": "user",
+                "content": [{
+                    "type": "speech_input",
+                    "speech_input": f"data:audio/wav;base64,{speech_base64}",
+                }]
+            }
+        )
+
+        
+    with chat_col2:
+        message_container = st.container(height=380, border=False)
+
+        for message in st.session_state.messages:
+            avatar = "assistant.png" if message["role"] == "assistant" else "user.png"
+
+            with message_container.chat_message(message["role"], avatar=avatar):
+                for content in message["content"]:
+                    if content["type"] == "text":
+                        st.markdown(content["text"])
+                    elif content["type"] == "image_url":      
+                        st.image(content["image_url"]["url"])
+                    elif content["type"] == "video_file":
+                        st.video(content["video_file"])
+                    elif content["type"] == "audio_file":
+                        st.audio(content["audio_file"], autoplay=True)
+                    elif content["type"] == "speech_input":
+                        st.audio(content["speech_input"])
+
+    ###----- User Question -----###
+    if prompt:= st.chat_input("Type you question", key="question"):
+        message_container.chat_message("user", avatar="user.png").markdown(prompt)
+
+        st.session_state.messages.append(
+                    {
+                        "role": "user", 
+                        "content": [{
+                            "type": "text",
+                            "text": prompt,
+                        }]
+                    }
+                )
+        
+        ###----- Generate response -----###
+        with message_container.chat_message("assistant", avatar="assistant.png"):
+
+            model2key = {
+                        "openai": groq_api_key,
+                        "google": google_api_key,
+                    }
+
+            st.write_stream(stream_llm_response(
+                        model_params=model_params, 
+                        model_type=model_type, 
+                        api_key=model2key[model_type]
+                    )
+                )
+
+                # response = "Hello! How can I help you today?"
+                # message_container.chat_message("assistant", avatar="assistant.png").markdown(response)
+
+        # st.session_state.messages.append(
+        #             {
+        #                 "role": "assistant", 
+        #                 "content": [{
+        #                     "type": "text",
+        #                     "text": response,
+        #                 }]
+        #             }
+        #         )
+
+
+
+
+
+
+                                
+
+
+
+
+# Confirmation popup window
+# selection_dict = {"file_and_answer": "", "prompt": "", "respuesta_chat": ""}
+# st.button("Visualize", on_click=visualize_display_page, key="visualiza", args=[selection_dict])
+
+
+

utils.py

@@ -0,0 +1,76 @@
+import streamlit as st
+from streamlit_vertical_slider import vertical_slider
+
+@st.dialog("Confirm Selection 👇", width="large")
+def visualize_display_page(selection_dict):
+    """
+    Visualize the answers and selected
+    Args:
+        st (streamlit): streamlit object
+        selection_dict (dict): dictionary with the selected answers
+    """
+    # get the name of the file
+
+    txt = st.text_area(
+        "File and Timestamp",
+        value=selection_dict.get("file_and_answer"),
+        key="file_and_answer",
+        height=70,
+    )
+    txt3 = st.text_area(
+        "Prompt sent to Gemini",
+        value=selection_dict.get("prompt"),
+        key="prompt",
+    )
+    txt2 = st.text_area(
+        "Response Gemini",
+        height=300,
+        key="respuesta_chat",
+        value=selection_dict.get("respuesta_chat"),
+    )
+    if st.button("Accept", key="accept_inside_select_answer"):
+        st.rerun()
+
+def about():
+    about_text = """Welcome to the Super GPT Assistant App. This app is created by Aasher Kamal.
+"""
+    return about_text
+
+def temperature_slider():
+    temperature = vertical_slider(
+        label = "Temperature",  #Optional
+        key = "vert_01" ,
+        height = 100, #Optional - Defaults to 300#Optional - Defaults to "circle"
+        step = 1, #Optional - Defaults to 1
+        default_value=5,#Optional - Defaults to 0
+        min_value= 0, # Defaults to 0
+        max_value= 10, # Defaults to 10
+        track_color = "blue",
+        thumb_shape="square", #Optional - Defaults to #D3D3D3
+        slider_color = 'lighgray', #Optional - Defaults to #29B5E8
+        thumb_color= "orange", #Optional - Defaults to #11567f
+        value_always_visible = False ,#Optional - Defaults to False
+    )
+    return temperature
+
+def set_safety_settings():
+    safety_settings = [
+    {
+        "category": "HARM_CATEGORY_HARASSMENT",
+        "threshold": "BLOCK_NONE"
+    },
+    {
+        "category": "HARM_CATEGORY_HATE_SPEECH",
+        "threshold": "BLOCK_NONE"
+    },
+    {
+        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
+        "threshold": "BLOCK_NONE"
+    },
+    {
+        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
+        "threshold": "BLOCK_NONE"
+    },
+]
+
+    return safety_settings