Update 1

app.py

@@ -1,5 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
 import os
 import groq
 import warnings
@@ -7,12 +10,21 @@ import asyncio
 from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
 from llama_index.llms.groq import Groq
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-
-# A warning may appear which doesn't 
-# affect the operation of the code
-# Suppress it with this code
 warnings.filterwarnings("ignore", message=".*clean_up_tokenization_spaces.*")
 
+theme = gr.themes.Soft(
+    primary_hue=gr.themes.Color(c100="#cde3fb", c200="#cde3fb", c300="#81b9f4", c400="#4f9df0", c50="rgba(221.44736842105263, 237.49427917620136, 255, 1)", c500="#0473ea", c600="#0473ea", c700="#0473ea", c800="#0473ea", c900="#0083B3", c950="#0083b3"),
+    secondary_hue=gr.themes.Color(c100="#d7f6cc", c200="#d7f6cc", c300="#9be880", c400="#9be880", c50="#d7f6cc", c500="#74df4c", c600="#38d200", c700="#38d200", c800="rgba(50.43333333333328, 189.125, 0, 1)", c900="rgba(41.409166666666614, 155.28437499999998, 0, 1)", c950="#134e28"),
+    neutral_hue=gr.themes.Color(c100="#e5e5e5", c200="#d4d4d4", c300="#a8a9aa", c400="#a8a9aa", c50="#f9fafb", c500="rgb(134, 135, 136)", c600="rgb(134, 135, 136)", c700="#525355", c800="#525355", c900="rgba(52.90131578947368, 53.54254385964912, 54.82499999999999, 1)", c950="#353637"),
+    font=[gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR')],
+    font_mono=[gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR'), gr.themes.GoogleFont('Noto Sans KR')],
+)
+
+
+
+"""
+RAG Custom Functins
+"""
 # Global variables
 index = None
 query_engine = None
@@ -24,10 +36,6 @@ Settings.llm = llm  # Ensure Groq is the LLM being used
 # Initialize our chosen embedding model
 embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-# These are our RAG functions, called in response to user
-# initiated events e.g clicking the Load Documents button
-# on the GUI
-#
 def load_documents(file_objs):
     global index, query_engine
     try:
@@ -75,26 +83,176 @@ def clear_all():
     return None, "", [], ""  # Reset file input, load output, chatbot, and message input to default states
 
 
-# Create the Gradio interface
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# RAG Multi-file Chat Application")
 
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+# gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+# gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+# gr.Slider(
+#     minimum=0.1,
+#     maximum=1.0,
+#     value=0.95,
+#     step=0.05,
+#     label="Top-p (nucleus sampling)",
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message="당신은 스탠다드차타드은행 한국 지사의 친절하고 유능한 AI 어시스턴트입니다. 한국어로 원활하게 소통하며, 번역, 문서 작성, 그리고 다양한 업무 지원을 신속하고 정확하게 처리합니다. 필요한 정보를 제공하고, 직원들이 업무를 효율적으로 수행할 수 있도록 돕는 역할을 수행합니다.",
+    max_tokens=512,
+    temperature=0.2,
+    top_p=0.95,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+
+# """
+# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# """
+
+# Define the functions for each tab
+def scbk_gpt_response(user_message):
+    # Placeholder function for SCBK-GPT response
+    response = f"SCBK-GPT: {user_message}"
+    return response
+
+def data_analysis(data):
+    # Placeholder function for data analysis
+    df = pd.DataFrame(data)
+    summary = df.describe()
+    return summary
+
+def rag_response(query, document):
+    # Placeholder function for RAG response
+    # Here you would implement the logic to process the query and the document
+    return f"RAG: {query} from {document.name}"
+
+def agentic_ai_response(task):
+    # Placeholder function for Agentic AI response
+    return f"Agentic AI: {task}"
+
+custom_css = """
+.contain {
+    display: flex;
+    flex-direction: column;
+    height: 100vh;
+}
+#custom_chatbot {
+    flex-grow: 1;
+    display: flex;
+    flex-direction: column;
+}
+#custom_chatbot .gr-chatbot {
+    flex-grow: 1;
+    overflow-y: auto;
+}
+"""
+
+# Create the Gradio app with the Soft theme
+with gr.Blocks(theme=theme, fill_height=True, css=custom_css) as demo:
+    # Add a banner with a title and a logo
     with gr.Row():
-        file_input = gr.File(label="Select files to load", file_count="multiple")
-        load_btn = gr.Button("Load Documents")
+        #gr.Image("/file=logo.png", elem_classes="app-logo", show_download_button=False, width=200)  # Logo on the left
+        # gr.Markdown("<img src='/file=/logo.png' alt='SCBK' width='200'>")
+        # gr.Markdown("# SCBK-GPT Demo by AI Usage 1조", elem_classes="app-title")  # Title on the right
+        gr.Markdown(
+            """
+            <link href="https://fonts.googleapis.com/css2?family=Noto+Sans+KR:wght@400;700&display=swap" rel="stylesheet">
+            <div style="display: flex; align-items: center; justify-content: center; background: linear-gradient(to right, #2B3A89, #285FBF); padding: 20px; font-family: 'Noto Sans KR', sans-serif;"">
+                <img src="https://i.namu.wiki/i/UUHBBtfx06qUnW4B7oVOiBAAQJ1C3ynKfEI3YjIlvhnuOtkQHejb4_ziBhD7p4n_O9G9LwFz-bRokNibnKaZ9Y8GQsH13OmZTBGuTXBrcS-YkN8ra67jiCaAFcDQDspjbwQk8duLiQ1cX0jg-WsQBA.svg" alt="SCBK" width="200" style="margin-right: 10px;">
+                <h1 style="margin: 0; color: white; font-size: 2em;">
+                    SCBK-GPT<br>
+                    <span style="font-size: 0.6em; color: white; vertical-align: middle;">by AI Usage 1조</span>
+                </h1>
+            </div>
+            """
+        )
+
+    # Tab 1: SCBK-GPT
+    with gr.Tab("SCBK-GPT"):
+        custom_chatbot = gr.Chatbot(elem_id="custom_chatbot")
+        gr.ChatInterface(
+            respond,
+            additional_inputs=[],
+            chatbot=custom_chatbot,
+            multimodal=False,
+            examples=["안녕하세요","Asset이 뭔지 설명해줘"],
+        )
+
+    # Tab 2: Data Analysis
+    with gr.Tab("Data Analysis"):
+        data_input = gr.File(label="Upload CSV File", file_types=[".csv"])
+        query_input = gr.Textbox(label="Ask a Question")
+        analysis_output = gr.Textbox(label="Answer")
+        analyze_button = gr.Button("Analyze")
+        
+        def analyze_data(file, query):
+            df = pd.read_csv(file.name)
+            # Placeholder for actual data analysis logic
+            answer = f"Answer to '{query}': {df.head().to_string()}"
+            return answer
+        
+        analyze_button.click(analyze_data, inputs=[data_input, query_input], outputs=analysis_output)
+
+    # Tab 3: RAG
+    with gr.Tab("RAG"):
+        # document_input = gr.File(label="Upload Document", file_types=[".pdf", ".txt"])
+        # query_input = gr.Textbox(label="Query")
+        # rag_output = gr.Textbox(label="Response")
+        # query_button = gr.Button("Query")
+        # query_button.click(rag_response, inputs=[query_input, document_input], outputs=rag_output)
+        gr.Markdown("# RAG Multi-file Chat Application")
+
+        with gr.Row():
+            file_input = gr.File(label="Select files to load", file_count="multiple", file_types=[".pdf", ".txt"])
+            load_btn = gr.Button("문서 업로드")
+
+        load_output = gr.Textbox(label="로딩 Status")
+
+        msg = gr.Textbox(label="질문을 입력해 주세요")
+        chatbot = gr.Chatbot()  
+        clear = gr.Button("Clear")
 
-    load_output = gr.Textbox(label="Load Status")
+        # Set up event handlers
+        load_btn.click(load_documents, inputs=[file_input], outputs=[load_output])
+        msg.submit(perform_rag, inputs=[msg, chatbot], outputs=[chatbot])
+        clear.click(clear_all, outputs=[file_input, load_output, chatbot, msg], queue=False)
 
-    msg = gr.Textbox(label="Enter your question")
-    chatbot = gr.Chatbot()  
-    clear = gr.Button("Clear")
 
-    # Set up event handlers
-    load_btn.click(load_documents, inputs=[file_input], outputs=[load_output])
-    msg.submit(perform_rag, inputs=[msg, chatbot], outputs=[chatbot])
-    clear.click(clear_all, outputs=[file_input, load_output, chatbot, msg], queue=False)
+    # Tab 4: Agentic AI
+    with gr.Tab("Agentic AI"):
+        task_input = gr.Textbox(label="Task")
+        agentic_output = gr.Textbox(label="Response")
+        task_button = gr.Button("Submit Task")
+        task_button.click(agentic_ai_response, inputs=task_input, outputs=agentic_output)
 
-# Run the app
+       
+# Launch the app
 if __name__ == "__main__":
-    demo.queue()
-    demo.launch()
+    demo.launch(show_error=True)