First commit

.gitignore

@@ -0,0 +1,2 @@
+*.pyc
+*.env

README.md

@@ -9,4 +9,39 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Marketer Chatbot Project
+
+## Overview
+Marketer Chatbot is a Python-based project designed to provide a simple interface for users to interact with a chatbot behaving like a marketer. The chatbot is built using the Streamlit library and Hugging Face Inference API, together with a Llama-family model.
+
+## Contents
+- `functions.py`: Contains various functions used in the project.
+- `config.py`: Configuration settings for the project.
+- `requirements.txt`: Lists the dependencies required to run the project.
+- `app.py`: The main application file.
+- `.gitignore`: Specifies files and directories to be ignored by git.
+- `.gitattributes`: Configuration for git attributes.
+
+## Getting Started
+
+### Prerequisites
+Ensure you have the following installed:
+- Python 3.x
+- pip (Python package installer)
+
+### Installation
+1. Clone the repository:
+2. Navigate to the project directory:
+    ```sh
+    cd marketer_chatbot
+    ```
+3. Install the required dependencies:
+    ```sh
+    pip install -r requirements.txt
+    ```
+
+### Running the Application
+Run the main application file:
+```sh
+streamlit run app.py
+```

app.py

@@ -0,0 +1,89 @@
+from functions import *
+
+# set the title
+st.sidebar.title(DASHBOARD_TITLE)
+info_section = st.empty()
+
+# add an explanation of what is NER and why it is important for medical tasks
+st.sidebar.markdown(
+    f"""
+    Meta Llama 3 8B Instruct is part of a family of large language models (LLMs) optimized for dialogue tasks.
+
+    This project uses Streamlit to create a simple chatbot interface that allows you to chat with the model using the Hugging Face Inference API.
+    
+    Ask the model marketing-related questions and see how it responds. Have fun!
+
+    Model used: [{MODEL_PATH}]({MODEL_LINK})
+    """
+)
+
+first_assistant_message = "Hello! I am Marketing expert. What can I help you with today?"
+
+# clear conversation
+if st.sidebar.button("Clear conversation"):
+    chat_history = [{'role':'assistant', 'content':first_assistant_message}]
+    st.session_state['chat_history'] = chat_history
+    st.rerun()
+
+# Get the chat history
+if "chat_history" not in st.session_state:
+    chat_history = [{'role':'assistant', 'content':first_assistant_message}]
+    st.session_state['chat_history'] = chat_history
+else:
+    chat_history = st.session_state['chat_history']
+
+# print the conversation
+for message in chat_history:
+    with st.chat_message(message['role']):
+        st.write(message['content'])
+
+# keep only last 10 messages
+shorter_history = [message for message in chat_history[-10:] if 'content' in message]
+
+# include a system prompt to explain the bot what to do
+system_prompt = """For this task, you are a Marketer specialized in E-commerce helping a user with marketing-related questions. Provide insights and recommendations based on the user's questions. Don't write more than 3-4 sentences per response."""
+shorter_history = [{'role': 'system', 'content': system_prompt}] + shorter_history
+
+# get the input from user
+user_input = st.chat_input("Write something...")
+
+if user_input:
+
+    with st.chat_message("user"):
+        st.write(user_input)
+
+    # make the request
+    with st.spinner("Generating the response..."):
+
+        client = InferenceClient(
+            "meta-llama/Meta-Llama-3-8B-Instruct",
+            token=HUGGING_FACE_API_KEY,
+            )
+        
+        messages = shorter_history + [{'role': 'user', 'content': user_input}]
+
+        # query the model
+        try:
+            response = client.chat_completion(
+                messages=messages,
+                max_tokens = 500,
+                stream = False,
+                )
+            
+            # get the response
+            message = response.choices[0].message['content']
+            
+            # append to the history
+            chat_history.append({'content':user_input, 'role':'user'})
+            chat_history.append(response.choices[0].message) # append the response
+
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+            st.stop()
+
+    st.session_state['chat_history'] = chat_history
+    st.rerun()
+
+
+
+

config.py

@@ -0,0 +1,13 @@
+import streamlit as st
+from dotenv import load_dotenv
+from huggingface_hub import InferenceClient
+import os
+
+# load variables from the env file
+load_dotenv()
+
+HUGGING_FACE_API_KEY = os.environ.get('HUGGING_FACE_API_KEY', None)
+
+DASHBOARD_TITLE = "The Marketer Chatbot"
+MODEL_PATH = "meta-llama/Meta-Llama-3-8B-Instruct"
+MODEL_LINK = f"https://huggingface.co/{MODEL_PATH}"

functions.py

@@ -0,0 +1 @@
+from config import *

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+python-dotenv
+huggingface_hub