Upload 5 files

.env

@@ -0,0 +1 @@
+GROQ_API_KEY = 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

llama2_chatbot.py

@@ -0,0 +1,143 @@
+import streamlit as st
+import os
+from dotenv import load_dotenv
+load_dotenv()
+from groq import Groq
+
+# Load environment variables
+GROQ_API_KEY = os.environ.get('GROQ_API_KEY')
+
+PRE_PROMPT = "You are a helpful assistant. You do not respond as 'User' or pretend to be 'User'. You only respond once as Assistant."
+
+if not GROQ_API_KEY:
+    st.warning("Please add your Groq API key to the .env file.")
+    st.stop()
+
+# Connect to Groq
+client = Groq(api_key=GROQ_API_KEY)
+
+#models' endpoints:
+GROQ_MODEL_ENDPOINT70B = os.environ.get(GROQ_API_KEY, model='llama3-70b-8192')
+GROQ_MODEL_ENDPOINT8B = os.environ.get(GROQ_API_KEY, model='llama3-8b-8192')
+PRE_PROMPT = "You are a helpful assistant. You do not respond as 'User' or pretend to be 'User'. You only respond once as Assistant."
+#Auth0 for auth
+
+# Set up Streamlit app
+st.set_page_config(page_title="LLaMA 3x", page_icon="🦙", layout="wide")
+
+def render_app():
+
+    # reduce font sizes for input text boxes
+    custom_css = """
+        <style>
+            .stTextArea textarea {font-size: 13px;}
+            div[data-baseweb="select"] > div {font-size: 13px !important;}
+        </style>
+    """
+    st.markdown(custom_css, unsafe_allow_html=True)
+
+    #Left sidebar menu
+    st.sidebar.header("LLaMA 3x")
+
+    #Set config for a cleaner menu, footer & background:
+    hide_streamlit_style = """
+                <style>
+                #MainMenu {visibility: hidden;}
+                footer {visibility: hidden;}
+                </style>
+                """
+    st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+    #container for the chat history
+    response_container = st.container()
+    #container for the user's text input
+    container = st.container()
+    #Set up/Initialize Session State variables:
+     # Set up/Initialize Session State variables
+    if 'chat_dialogue' not in st.session_state:
+        st.session_state['chat_dialogue'] = []
+    if 'temperature' not in st.session_state:
+        st.session_state['temperature'] = 0.1
+    if 'top_p' not in st.session_state:
+        st.session_state['top_p'] = 0.9
+    if 'max_seq_len' not in st.session_state:
+        st.session_state['max_seq_len'] = 512
+    if 'pre_prompt' not in st.session_state:
+        st.session_state['pre_prompt'] = PRE_PROMPT
+        
+        
+        #Dropdown menu to select the model edpoint:
+    selected_option = st.sidebar.selectbox('Choose a LLaMA2 model:', ['LLaMA3 70B', 'LLaMA3 8B'], key='model')
+    if selected_option == 'LLaMA-3 70B':
+        st.session_state['llm'] = GROQ_MODEL_ENDPOINT70B
+    else:
+        st.session_state['llm'] = GROQ_MODEL_ENDPOINT8B
+
+    # Model hyperparameters
+    st.session_state['temperature'] = st.sidebar.slider('Temperature:', min_value=0.01, max_value=5.0, value=0.1, step=0.01)
+    st.session_state['top_p'] = st.sidebar.slider('Top P:', min_value=0.01, max_value=1.0, value=0.9, step=0.01)
+    st.session_state['max_seq_len'] = st.sidebar.slider('Max Sequence Length:', min_value=64, max_value=4096, value=2048, step=8)
+
+
+    NEW_P = st.sidebar.text_area('Prompt before the chat starts. Edit here if desired:', PRE_PROMPT, height=60)
+    if NEW_P != PRE_PROMPT and NEW_P != "" and NEW_P != None:
+        st.session_state['pre_prompt'] = NEW_P + "\n\n"
+    else:
+        st.session_state['pre_prompt'] = PRE_PROMPT
+
+    btn_col1, btn_col2 = st.sidebar.columns(2)
+
+    # Add the "Clear Chat History" button to the sidebar
+    def clear_history():
+        st.session_state['chat_dialogue'] = []
+    clear_chat_history_button = btn_col1.button("Clear History",
+                                            use_container_width=True,
+                                            on_click=clear_history)
+
+    # add logout button
+    def logout():
+        del st.session_state['user_info']
+    logout_button = btn_col2.button("Logout",
+                                use_container_width=True,
+                                on_click=logout)
+        
+    # add links to relevant resources for users to select
+    st.sidebar.write(" ")
+
+    logo1 = 'https://storage.googleapis.com/llama2_release/a16z_logo.png'
+    logo2 = 'https://storage.googleapis.com/llama2_release/Screen%20Shot%202023-07-21%20at%2012.34.05%20PM.png'
+
+    st.sidebar.write(" ")
+    st.sidebar.markdown("*Made with ❤️ by Asman. Not associated with Meta Platforms, Inc.*")
+
+    # Display chat messages from history on app rerun
+    for message in st.session_state.chat_dialogue:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+            
+             # Accept user input
+    if prompt := st.chat_input("Message LLaMA 3x...."):
+        # Add user message to chat history
+        st.session_state.chat_dialogue.append({"role": "user", "content": prompt})
+        # Display user message in chat message container
+        with st.chat_message("user"):
+            st.markdown(prompt)
+
+        with st.chat_message("assistant"):
+            message_placeholder = st.empty()
+            full_response = ""
+            messages = [{"role": msg["role"], "content": msg["content"]} for msg in st.session_state.chat_dialogue]
+            chat_completion = client.chat.completions.create(
+                messages=messages,
+                model=selected_option,
+                temperature=st.session_state['temperature'],
+                top_p=st.session_state['top_p'],
+                max_tokens=st.session_state['max_seq_len']
+            )
+            full_response = chat_completion.choices[0].message.content
+            message_placeholder.markdown(full_response)
+
+        # Add assistant response to chat history
+        st.session_state.chat_dialogue.append({"role": "assistant", "content": full_response})
+
+render_app()

requirements.txt

@@ -0,0 +1,67 @@
+aiodns==3.0.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+async-timeout==4.0.2
+attrs==23.1.0
+blinker==1.6.2
+Brotli==1.0.9
+cachetools==5.3.1
+certifi==2023.5.7
+cffi==1.15.1
+charset-normalizer==3.2.0
+click==8.1.5
+decorator==5.1.1
+ecdsa==0.18.0
+frozenlist==1.4.0
+gitdb==4.0.10
+GitPython==3.1.32
+idna==3.4
+importlib-metadata==6.8.0
+Jinja2==3.1.2
+jsonschema==4.18.3
+jsonschema-specifications==2023.6.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+mdurl==0.1.2
+multidict==6.0.4
+numpy==1.25.1
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.23.4
+pyarrow==12.0.1
+pyasn1==0.5.0
+pycares==4.3.0
+pycparser==2.21
+pydantic==1.10.11
+pydeck==0.8.1b0
+Pygments==2.15.1
+Pympler==1.0.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-jose==3.3.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+referencing==0.29.1
+replicate==0.8.4
+requests==2.31.0
+rich==13.4.2
+rpds-py==0.8.10
+rsa==4.9
+six==1.16.0
+smmap==5.0.0
+streamlit==1.24.1
+streamlit-auth0-component==0.1.5
+streamlit-chat==0.1.1
+tenacity==8.2.2
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.2
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.3
+validators==0.20.0
+yarl==1.9.2
+zipp==3.16.2

utils.py

@@ -0,0 +1,28 @@
+import replicate
+import time
+
+# Initialize debounce variables
+last_call_time = 0
+debounce_interval = 2  # Set the debounce interval (in seconds) to your desired value
+
+def debounce_replicate_run(llm, prompt, max_len, temperature, top_p, API_TOKEN):
+    global last_call_time
+    print("last call time: ", last_call_time)
+
+    # Get the current time
+    current_time = time.time()
+
+    # Calculate the time elapsed since the last call
+    elapsed_time = current_time - last_call_time
+
+    # Check if the elapsed time is less than the debounce interval
+    if elapsed_time < debounce_interval:
+        print("Debouncing")
+        return "Hello! You are sending requests too fast. Please wait a few seconds before sending another request."
+
+
+    # Update the last call time to the current time
+    last_call_time = time.time()
+    
+    output = replicate.run(llm, input={"prompt": prompt + "Assistant: ", "max_length": max_len, "temperature": temperature, "top_p": top_p, "repetition_penalty": 1}, api_token=API_TOKEN)
+    return output