first commit

app.py

@@ -0,0 +1,121 @@
+import os
+
+import openai
+import streamlit as st
+from transformers import pipeline
+
+from helpers.foundation_models import *
+
+openai_client = openai.OpenAI(api_key=os.environ["OPENAI_API_KEY"])
+
+
+st.title("🌟 Streamlit + Hugging Face Demo 🤖")
+
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+
+# Display chat messages from history on app rerun
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+
+with st.expander("Instructions"):
+    st.sidebar.markdown(
+        r"""
+        # 🌟 Streamlit + Hugging Face Demo 🤖
+
+        ## Introduction 📖
+
+        This demo showcases how to interact with Large Language Models (LLMs) on Hugging Face using Streamlit. 
+
+        ## Setup 🛠️
+
+        1. Install Requirements: 
+
+        - Streamlit: `pip install streamlit`
+        - Hugging Face Transformers: `pip install transformers`
+
+        ## Running the Demo 🚀
+
+        1. Clone the repository: `git clone <repo-url>`
+        2. Navigate to the project directory: `cd <project-directory>`
+        3. Run Streamlit: `streamlit run app.py`
+
+        ## Features 🌈
+
+        - **Text Input** 📝: Enter your query in the text box.
+        - **Model Selection** 🤖: Choose an LLM from a dropdown menu.
+        - **Submit Button** ✅: Click to submit your query to the model.
+        - **Responses** 💬: View the model's responses in real-time.
+
+        ## Contributing 🤝
+
+        Feel free to fork the repository, make changes, and submit pull requests!
+
+        ## License 📜
+
+        This project is licensed under the MIT License.
+
+        ## Contact 📬
+
+        For any queries, contact us at `email@example.com`.
+
+        ## Happy Coding! 🎉
+        """
+    )
+
+
+option = st.sidebar.selectbox(
+    "Which task do you want to do?",
+    ("Sentiment Analysis", "Medical Summarization", "ChatGPT"),
+)
+
+
+clear_button = st.sidebar.button("Clear Conversation", key="clear")
+
+
+# Reset everything
+if clear_button:
+    st.session_state.messages = []
+
+
+# React to user input
+if prompt := st.chat_input("What is up?"):
+    # Display user message in chat message container
+    st.chat_message("user").markdown(prompt)
+    # Add user message to chat history
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    if option == "Sentiment Analysis":
+        pipe_sentiment_analysis = pipeline("sentiment-analysis")
+        if prompt:
+            out = pipe_sentiment_analysis(prompt)
+            doc = f"""
+                Prompt: {prompt}
+                Sentiment: {out[0]["label"]}
+                Score: {out[0]["score"]}
+            """
+    elif option == "Medical Summarization":
+        pipe_summarization = pipeline(
+            "summarization", model="Falconsai/medical_summarization"
+        )
+        if prompt:
+            out = pipe_summarization(prompt)
+            doc = out[0]["summary_text"]
+    elif option == "ChatGPT":
+        if prompt:
+            out = call_chatgpt(query=prompt)
+            doc = out
+    else:
+        None
+
+    response = f"{doc}"
+    # Display assistant response in chat message container
+    with st.chat_message("assistant"):
+        st.markdown(response)
+    # Add assistant response to chat history
+    st.session_state.messages.append({"role": "assistant", "content": response})

helpers/foundation_models.py

@@ -0,0 +1,38 @@
+import os
+from typing import List, Tuple
+
+import openai
+import streamlit as st
+
+openai_client = openai.OpenAI(api_key=os.environ["OPENAI_API_KEY"])
+
+
+def call_chatgpt(query: str, model: str = "gpt-3.5-turbo") -> str:
+    """
+    Generates a response to a query using the specified language model.
+
+    Args:
+        query (str): The user's query that needs to be processed.
+        model (str, optional): The language model to be used. Defaults to "gpt-3.5-turbo".
+
+    Returns:
+        str: The generated response to the query.
+    """
+
+    # Prepare the conversation context with system and user messages.
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": f"Question: {query}."},
+    ]
+
+    # Use the OpenAI client to generate a response based on the model and the conversation context.
+    response = openai_client.chat.completions.create(
+        model=model,
+        messages=messages,
+    )
+
+    # Extract the content of the response from the first choice.
+    content: str = response.choices[0].message.content
+
+    # Return the generated content.
+    return content

requirements.txt

@@ -0,0 +1,3 @@
+torch
+openai
+transformers