Upload 4 files

.devcontainer/devcontainer.json

@@ -0,0 +1,33 @@
+{
+  "name": "Python 3",
+  // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+  "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
+  "customizations": {
+    "codespaces": {
+      "openFiles": [
+        "README.md",
+        "streamlit_app.py"
+      ]
+    },
+    "vscode": {
+      "settings": {},
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance"
+      ]
+    }
+  },
+  "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
+  "postAttachCommand": {
+    "server": "streamlit run streamlit_app.py --server.enableCORS false --server.enableXsrfProtection false"
+  },
+  "portsAttributes": {
+    "8501": {
+      "label": "Application",
+      "onAutoForward": "openPreview"
+    }
+  },
+  "forwardPorts": [
+    8501
+  ]
+}

.streamlit/config.toml

@@ -0,0 +1,6 @@
+[theme]
+primaryColor="#F63366"
+backgroundColor="#FFFFFF"
+secondaryBackgroundColor="#F0F2F6"
+textColor="#262730"
+font="sans serif"

requirements.txt

@@ -0,0 +1,2 @@
+streamlit
+replicate

streamlit_app.py

@@ -0,0 +1,84 @@
+import streamlit as st
+import replicate
+import os
+
+# App title
+st.set_page_config(page_title="🦙💬 Llama 2 Chatbot")
+
+# Replicate Credentials
+with st.sidebar:
+    st.title('🦙💬 Llama 2 Chatbot')
+    if 'REPLICATE_API_TOKEN' in st.secrets:
+        st.success('API key already provided!', icon='✅')
+        replicate_api = st.secrets['REPLICATE_API_TOKEN']
+    else:
+        replicate_api = st.text_input('Enter Replicate API token:', type='password')
+        if not (replicate_api.startswith('r8_') and len(replicate_api)==40):
+            st.warning('Please enter your credentials!', icon='⚠️')
+        else:
+            st.success('Proceed to entering your prompt message!', icon='👉')
+
+    # Refactored from https://github.com/a16z-infra/llama2-chatbot
+    st.subheader('Models and parameters')
+    selected_model = st.sidebar.selectbox('Choose a Llama2 model', ['Llama2-7B', 'Llama2-13B', 'Llama2-70B'], key='selected_model')
+    if selected_model == 'Llama2-7B':
+        llm = 'a16z-infra/llama7b-v2-chat:4f0a4744c7295c024a1de15e1a63c880d3da035fa1f49bfd344fe076074c8eea'
+    elif selected_model == 'Llama2-13B':
+        llm = 'a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5'
+    else:
+        llm = 'replicate/llama70b-v2-chat:e951f18578850b652510200860fc4ea62b3b16fac280f83ff32282f87bbd2e48'
+    
+    temperature = st.sidebar.slider('temperature', min_value=0.01, max_value=5.0, value=0.1, step=0.01)
+    top_p = st.sidebar.slider('top_p', min_value=0.01, max_value=1.0, value=0.9, step=0.01)
+    max_length = st.sidebar.slider('max_length', min_value=64, max_value=4096, value=512, step=8)
+    
+    language = st.sidebar.selectbox('Language', ['English', 'Spanish'], index=0)
+    
+    st.markdown('📖 Learn how to build this app in this [blog](https://blog.streamlit.io/how-to-build-a-llama-2-chatbot/)!')
+os.environ['REPLICATE_API_TOKEN'] = replicate_api
+
+# Store LLM generated responses
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
+
+# Display or clear chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+def clear_chat_history():
+    st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
+st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
+
+# Function for generating LLaMA2 response
+def generate_llama2_response(prompt_input, language='English'):
+    string_dialogue = "You are a helpful assistant. You do not respond as 'User' or pretend to be 'User'. You only respond once as 'Assistant'."
+    for dict_message in st.session_state.messages:
+        if dict_message["role"] == "user":
+            string_dialogue += "User: " + dict_message["content"] + "\n\n"
+        else:
+            string_dialogue += "Assistant: " + dict_message["content"] + "\n\n"
+    output = replicate.run(llm, 
+                           input={"prompt": f"{string_dialogue} {prompt_input} Assistant: ",
+                                  "temperature":temperature, "top_p":top_p, "max_length":max_length, "repetition_penalty":1, "language": language})
+    return output
+
+# User-provided prompt
+if prompt := st.chat_input(disabled=not replicate_api):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# Generate a new response if last message is not from assistant
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = generate_llama2_response(prompt, language='Spanish')
+            placeholder = st.empty()
+            full_response = ''
+            for item in response:
+                full_response += item
+                placeholder.markdown(full_response)
+            placeholder.markdown(full_response)
+    message = {"role": "assistant", "content": full_response}
+    st.session_state.messages.append(message)