ea4all-gradio-agents-mcp-hackathon-ui-retrofit

ea4all/ea4all_mcp.py

@@ -15,6 +15,7 @@ import ea4all.src.shared.utils as e4u
 from ea4all.src.graph import super_graph
 #from ea4all.src.pmo_crew.crew_runner import run_pmo_crew
 
+from typing import AsyncGenerator
 import gradio as gr
 from gradio import ChatMessage
 import os
@@ -23,8 +24,8 @@ import time
 from PIL import Image
 
 from ea4all.utils.utils import (
-    get_user_feedback, add_message, unload_dbr, on_dbrtext, load_dbr, off_dbrtext,
-    ea4all_agent_init, get_image, filter_page, ea4all_about, init_dbr
+    UIUtils,
+    ea4all_agent_init, get_image, filter_page, init_dbr
 )
 
 TITLE =  """
@@ -47,6 +48,300 @@ config = RunnableConfig(
         #stream_mode = "messages"
 )
 
+#ea4all-qna-agent-conversational-with-memory
+async def run_qna_agentic_system(prompt: str, chat_memory: list, request:gr.Request) -> AsyncGenerator[list, None]:
+    """
+    Handles conversational Q&A for the Application Landscape using an agentic system.
+
+    Args:
+        prompt (str): The user's question or message.
+        chat_memory (list): The conversation history as a list of ChatMessage objects.
+        request (gr.Request): The Gradio request object for user identification.
+
+    Returns:
+        list: Response to user's question.
+    """
+
+    format_response = ""
+
+    if not prompt:
+        format_response = "Hi, how are you today? To start our conversation, please chat your message!"
+        chat_memory.append(ChatMessage(role="assistant", content=format_response))
+        yield chat_memory
+
+    if not chat_memory:
+        chat_memory.append(ChatMessage(role="user", content=prompt))
+        yield chat_memory
+
+    if prompt:
+        #capture user ip
+        ea4all_user = e4u.get_user_identification(request)
+
+        ##Initialise APM Graph
+        #apm_graph = e4a.apm_graph
+        #inputs = {"question": prompt, "chat_memory":chat_memory}
+        inputs = {"messages": [{"role": "user", "content": prompt}]}
+        
+        #add prompt to memory
+        chat_memory.append(ChatMessage(role="user", content=prompt))
+
+        partial_message = ""
+        async for event in super_graph.astream_events(input=inputs, config=config, version="v2"):
+        #async for event in super_graph.astream(input=inputs, config=config, subgraphs=True):
+            #   chat_memory.append(ChatMessage(role="assistant", content=str(event)))
+            #   yield chat_memory
+
+            kind = event["event"]
+            tags = event.get("tags", [])
+            name =  event['name']
+            
+            #chat_memory.append(ChatMessage(role="assistant", content=f"Running: {name}"))
+            #yield chat_memory
+
+            if name == "safety_check":
+                #if kind == "on_chain_start":
+                #    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}`"))
+                #    yield chat_memory
+                if kind == "on_chain_stream":
+                    chunk = event['data'].get('chunk')
+                    if chunk and 'safety_status' in chunk and len(chunk['safety_status']) > 0:
+                        chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}`: {chunk['safety_status'][0]}"))
+                        if chunk['safety_status'][0] == 'no' and len(chunk['safety_status']) > 1:
+                            chat_memory.append(ChatMessage(role="assistant", content=f"Safety-status: {chunk['safety_status'][1]}"))
+                    yield chat_memory
+            if kind == "on_chain_end" and name == "route_question":
+                output = event['data'].get('output')
+                if output and 'source' in output:
+                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}:` {output['source']}"))
+                else:
+                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}:` (no source available)"))
+                yield chat_memory
+            if kind == "on_chain_start" and name == "retrieve":
+                chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}` RAG\n\n"))
+                yield chat_memory
+            if kind == "on_chain_start" and name in ("generate_web_search", "websearch", "stream_generation"):
+                chat_memory.append(ChatMessage(role="assistant", content= f"\n\n- `{name}`\n\n"))
+                yield chat_memory
+            if kind == "on_chain_stream" and name == "stream_generation":
+                data = event["data"]
+                # Accumulate the chunk of data
+                partial_message += data.get('chunk', '')
+                chat_memory[-1].content = partial_message
+                time.sleep(0.05)
+                yield chat_memory
+            if name == "grade_generation_v_documents_and_question":
+                if kind == "on_chain_start": 
+                    chat_memory.append(ChatMessage(role="assistant", content=f"\n\n- `{name}`: "))
+                    yield chat_memory
+                if kind == "on_chain_end":
+                    input_data = event['data'].get('input')
+                    if input_data and hasattr(input_data, 'source'):
+                        output_value = event['data'].get('output', '')
+                        chat_memory.append(ChatMessage(role="assistant", content=f"`{input_data.source}:` {output_value}"))
+                    else:
+                        chat_memory.append(ChatMessage(role="assistant", content=f"`{event['data'].get('output', '')}`"))
+                    yield chat_memory
+            if "stream_hallucination" in tags and kind == "on_chain_start":
+                chat_memory.append(ChatMessage(role="assistant", content=f"- `{tags[-1]}`"))
+                yield chat_memory
+            if "stream_grade_answer" in tags and kind == "on_chain_start":
+                chat_memory.append(ChatMessage(role="assistant", content=f"- `{tags[-1]}`"))
+                yield chat_memory
+            if name == "supervisor":
+                if kind == "on_chain_start":
+                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}` "))
+                    yield chat_memory
+                if kind == "on_chain_stream":
+                    chunk = event['data'].get('chunk')
+                    if chunk is not None:
+                        chat_memory.append(ChatMessage(role="assistant", content=f"{chunk}"))
+                        yield chat_memory
+
+            # Set environment variable only when 'event' is defined
+            os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
+        
+        wait_for_all_tracers()
+
+#Trigger Solution Architecture Diagram QnA
+async def run_vqa_agentic_system(message: dict, chat_memory: list, request:gr.Request) -> AsyncGenerator[list, None]:
+    """
+    Handles Visual Question Answering (VQA) for uploaded architecture diagrams.
+
+    Args:
+        message (dict): Contains 'files' (list of file paths) and 'text' (user's question).
+        chat_memory (list): The conversation history as a list of ChatMessage objects.
+        request (gr.Request): The Gradio request object for user identification.
+
+    Returns:
+        list: Response to user's question.
+    """
+
+    #capture user ip
+    ea4all_user = e4u.get_user_identification(request)
+
+    """Handle file uploads and validate their types."""
+    allowed_file_types = ('JPEG', 'PNG')
+
+    print("---CALLING VISUAL QUESTION ANSWERING AGENTIC SYSTEM---")
+    print(f"Prompt: {message}")
+
+    if message['files'] == []:
+        chat_memory.append(ChatMessage(role="assistant", content="Please upload an Architecture PNG, JPEG diagram to start!"))
+        yield chat_memory
+    else:
+        diagram = message['files'][-1] ##chat_memory[-1]['content'][-1]        
+        msg = message['text'] ##chat_memory[-2]['content']
+        print(f"---DIAGRAM: {diagram}---")
+        try:
+            if msg == "":
+                msg = "Please describe this diagram."
+
+            with Image.open(diagram) as diagram_:
+                if diagram_.format not in allowed_file_types:
+                    chat_memory.append(ChatMessage(role="assistant", content="Invalid file type. Allowed file types are JPEG and PNG."))
+                    yield chat_memory
+                else:
+                    #'vqa_image = e4u.get_raw_image(diagram) #MOVED into Graph
+                    vqa_image = diagram
+
+                    #Setup Quality Assurance Agentic System
+                    #graph = e4v.ea4all_graph(config['configurable']['vqa_model'])
+
+                    #Setup enter graph
+                    diagram_graph = e4v.diagram_graph
+
+                    partial_message = ""
+                    chat_memory.append(ChatMessage(role="assistant", content="Hi, I am working on your question..."))
+                    async for event in diagram_graph.astream_events(
+                        {"question":msg, "image": vqa_image}, config, version="v2"
+                    ):
+                        if (
+                                event["event"] == "on_chat_model_stream"
+                                and "vqa_stream" in event.get('tags', [])
+                                #and event["metadata"].get("langgraph_node") == "tools"
+                            ):
+                                chunk = event["data"].get("chunk")
+                                if chunk is not None and hasattr(chunk, "content"):
+                                    partial_message += chunk.content
+                                    chat_memory[-1].content = partial_message
+                                time.sleep(e4u.CFG.STREAM_SLEEP)
+                                yield chat_memory #, message to update prompt
+                        elif not partial_message:
+                            yield chat_memory #, message
+                    
+                        os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
+                    
+                    wait_for_all_tracers()
+
+        except Exception as e:
+            yield (e.args[-1])
+
+#Run Togaf Agentic System
+async def run_reference_architecture_agentic_system(business_query: str, request:gr.Request) -> AsyncGenerator[list, None]:
+    """
+    Generates a reference architecture blueprint based on a business requirement using the TOGAF agentic system.
+
+    Args:
+        business_query (str): The business requirement or query provided by the user.
+        request (gr.Request): The Gradio request object for user identification.
+
+    Returns:
+        list: Response to user's question.
+    """
+
+    if len(business_query) < 50:
+        agent_response = "Please provide a valid Business Requirement content to start!"
+        yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
+    else: 
+        plain_text = e4u.markdown_to_plain_text(business_query)
+        agent_response = "Generating Architecture Blueprint ---TOGAF VISION TARGET--- \n\nI am working on your request..."
+        togaf_chain = e4t.togaf_graph
+        final_diagram = ""
+        vision_message = ""
+        try:
+            async for s in togaf_chain.astream_events(
+                {
+                    "messages": [
+                        HumanMessage(
+                            content=plain_text
+                        )
+                    ],
+                    "business_query": business_query,
+                },
+                config=config,
+                version="v2"
+            ):    
+                kind = s["event"]
+                tags = s.get("tags", [])
+                name = s['name']
+
+                if "gra_stream" in tags and name == "stream_vision_target":
+                    if kind == "on_chain_stream":
+                        data = s["data"]
+                        # Accumulate the chunk of data
+                        chunk = data.get('chunk')
+                        if chunk is not None and hasattr(chunk, "content"):
+                            vision_message += chunk.content
+                        time.sleep(e4u.CFG.STREAM_SLEEP)
+                        yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
+                elif name == "save_diagram" and kind == 'on_chain_end': #MOVED INTO Togaf_Task3
+                    output = s['data'].get('output', {})
+                    final_diagram = output.get('architecture_runway', "")
+                elif ("assess_business_query" in tags or "assess_landscape" in tags) and kind == 'on_chain_start': ##'on_chat_model_stream':
+                    agent_response += f"\n\n`{tags[-1]}:{name}`"
+
+                    yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
+                
+            if vision_message=="":
+                agent_response = "I cannot generate the Architecture Vision. Please provide a valid Business Requirement content to start!"
+                yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
+            elif "Error" not in final_diagram:
+                yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),final_diagram, None, gr.Tabs(visible=True)])
+            else:
+                yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, final_diagram, gr.Tabs(visible=True)])
+
+        except Exception as e:  
+            yield(
+                [
+                    e.args[-1],
+                    gr.Tabs(visible=True), 
+                    gr.Tabs(selected="id_togaf"),
+                    None,
+                    None,
+                    gr.Tabs(visible=False)
+                ]
+            )
+
+async def run_pmo_agentic_system(prompt, chat_memory):
+    """
+    Answers questions about Project Portfolio Management and Architect Demand Management.
+
+    Args:
+        prompt (str): The user's question about project portfolio or resource management.
+        chat_memory (list): The conversation history as a list of ChatMessage objects.
+
+    Yields:
+        list: Updated chat memory after each event or response.
+    """
+
+    format_response = ""
+
+    if not prompt:
+        format_response = "Hi, how are you today? To start our conversation, please chat your message!"
+        chat_memory.append(ChatMessage(role="assistant", content=format_response))
+        yield chat_memory
+
+    if not chat_memory:
+        chat_memory.append(ChatMessage(role="user", content=prompt))
+        yield chat_memory
+
+    inputs = {
+        "question": prompt,
+        "verbose": True,  # optional flags
+    }
+    
+    #yield run_pmo_crew(inputs)
+
 #Blocks w/ ChatInterface, BYOD, About
 with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as ea4all_mcp:
 
@@ -74,266 +369,6 @@ with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as e
         Streamline the architecture operating model, taking the best of agentic workflows and architects working together.
     """
     
-    #ea4all-qna-agent-conversational-with-memory
-    async def run_qna_agentic_system(prompt, chat_memory, request:gr.Request):
-        
-        format_response = ""
-
-        if not prompt:
-            format_response = "Hi, how are you today? To start our conversation, please chat your message!"
-            chat_memory.append(ChatMessage(role="assistant", content=format_response))
-            yield chat_memory
-
-        if not chat_memory:
-            chat_memory.append(ChatMessage(role="user", content=prompt))
-            yield chat_memory
-
-        if prompt:
-            #capture user ip
-            ea4all_user = e4u.get_user_identification(request)
-
-            ##Initialise APM Graph
-            #apm_graph = e4a.apm_graph
-            #inputs = {"question": prompt, "chat_memory":chat_memory}
-            inputs = {"messages": [{"role": "user", "content": prompt}]}
-            
-            #add prompt to memory
-            chat_memory.append(ChatMessage(role="user", content=prompt))
-
-            partial_message = ""
-            async for event in super_graph.astream_events(input=inputs, config=config, version="v2"):
-            #async for event in super_graph.astream(input=inputs, config=config, subgraphs=True):
-             #   chat_memory.append(ChatMessage(role="assistant", content=str(event)))
-             #   yield chat_memory
-
-                kind = event["event"]
-                tags = event.get("tags", [])
-                name =  event['name']
-                
-                #chat_memory.append(ChatMessage(role="assistant", content=f"Running: {name}"))
-                #yield chat_memory
-
-                if name == "safety_check":
-                    #if kind == "on_chain_start":
-                    #    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}`"))
-                    #    yield chat_memory
-                    if kind == "on_chain_stream":
-                        chunk = event['data'].get('chunk')
-                        if chunk and 'safety_status' in chunk and len(chunk['safety_status']) > 0:
-                            chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}`: {chunk['safety_status'][0]}"))
-                            if chunk['safety_status'][0] == 'no' and len(chunk['safety_status']) > 1:
-                                chat_memory.append(ChatMessage(role="assistant", content=f"Safety-status: {chunk['safety_status'][1]}"))
-                        yield chat_memory
-                if kind == "on_chain_end" and name == "route_question":
-                    output = event['data'].get('output')
-                    if output and 'source' in output:
-                        chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}:` {output['source']}"))
-                    else:
-                        chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}:` (no source available)"))
-                    yield chat_memory
-                if kind == "on_chain_start" and name == "retrieve":
-                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}` RAG\n\n"))
-                    yield chat_memory
-                if kind == "on_chain_start" and name in ("generate_web_search", "websearch", "stream_generation"):
-                    chat_memory.append(ChatMessage(role="assistant", content= f"\n\n- `{name}`\n\n"))
-                    yield chat_memory
-                if kind == "on_chain_stream" and name == "stream_generation":
-                    data = event["data"]
-                    # Accumulate the chunk of data
-                    partial_message += data.get('chunk', '')
-                    chat_memory[-1].content = partial_message
-                    time.sleep(0.05)
-                    yield chat_memory
-                if name == "grade_generation_v_documents_and_question":
-                    if kind == "on_chain_start": 
-                        chat_memory.append(ChatMessage(role="assistant", content=f"\n\n- `{name}`: "))
-                        yield chat_memory
-                    if kind == "on_chain_end":
-                        input_data = event['data'].get('input')
-                        if input_data and hasattr(input_data, 'source'):
-                            output_value = event['data'].get('output', '')
-                            chat_memory.append(ChatMessage(role="assistant", content=f"`{input_data.source}:` {output_value}"))
-                        else:
-                            chat_memory.append(ChatMessage(role="assistant", content=f"`{event['data'].get('output', '')}`"))
-                        yield chat_memory
-                if "stream_hallucination" in tags and kind == "on_chain_start":
-                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{tags[-1]}`"))
-                    yield chat_memory
-                if "stream_grade_answer" in tags and kind == "on_chain_start":
-                    chat_memory.append(ChatMessage(role="assistant", content=f"- `{tags[-1]}`"))
-                    yield chat_memory
-                if name == "supervisor":
-                    if kind == "on_chain_start":
-                        chat_memory.append(ChatMessage(role="assistant", content=f"- `{name}` "))
-                        yield chat_memory
-                    if kind == "on_chain_stream":
-                        chunk = event['data'].get('chunk')
-                        if chunk is not None:
-                            chat_memory.append(ChatMessage(role="assistant", content=f"{chunk}"))
-                            yield chat_memory
-
-                # Set environment variable only when 'event' is defined
-                os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
-            
-            wait_for_all_tracers()
-
-    #Trigger Solution Architecture Diagram QnA
-    async def run_vqa_agentic_system(message, chat_memory, request:gr.Request):
-        #capture user ip
-        ea4all_user = e4u.get_user_identification(request)
-
-        """Handle file uploads and validate their types."""
-        allowed_file_types = ('JPEG', 'PNG')
-
-        print("---CALLING VISUAL QUESTION ANSWERING AGENTIC SYSTEM---")
-        print(f"Prompt: {message}")
-
-        if message['files'] == []:
-            chat_memory.append(ChatMessage(role="assistant", content="Please upload an Architecture PNG, JPEG diagram to start!"))
-            yield chat_memory
-        else:
-            diagram = message['files'][-1] ##chat_memory[-1]['content'][-1]        
-            msg = message['text'] ##chat_memory[-2]['content']
-            print(f"---DIAGRAM: {diagram}---")
-            try:
-                if msg == "":
-                    msg = "Please describe this diagram."
-
-                with Image.open(diagram) as diagram_:
-                    if diagram_.format not in allowed_file_types:
-                        chat_memory.append(ChatMessage(role="assistant", content="Invalid file type. Allowed file types are JPEG and PNG."))
-                        yield chat_memory
-                    else:
-                        #'vqa_image = e4u.get_raw_image(diagram) #MOVED into Graph
-                        vqa_image = diagram
-
-                        #Setup Quality Assurance Agentic System
-                        #graph = e4v.ea4all_graph(config['configurable']['vqa_model'])
-
-                        #Setup enter graph
-                        diagram_graph = e4v.diagram_graph
-
-                        partial_message = ""
-                        chat_memory.append(ChatMessage(role="assistant", content="Hi, I am working on your question..."))
-                        async for event in diagram_graph.astream_events(
-                            {"question":msg, "image": vqa_image}, config, version="v2"
-                        ):
-                            if (
-                                    event["event"] == "on_chat_model_stream"
-                                    and "vqa_stream" in event.get('tags', [])
-                                    #and event["metadata"].get("langgraph_node") == "tools"
-                                ):
-                                    chunk = event["data"].get("chunk")
-                                    if chunk is not None and hasattr(chunk, "content"):
-                                        partial_message += chunk.content
-                                        chat_memory[-1].content = partial_message
-                                    time.sleep(e4u.CFG.STREAM_SLEEP)
-                                    yield chat_memory #, message to update prompt
-                            elif not partial_message:
-                                yield chat_memory #, message
-                        
-                            os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
-                        
-                        wait_for_all_tracers()
-
-            except Exception as e:
-                yield (e.args[-1])
-
-    #Run Togaf Agentic System
-    async def run_reference_architecture_agentic_system(business_query, request:gr.Request):
-
-        if len(business_query) < 50:
-            agent_response = "Please provide a valid Business Requirement content to start!"
-            yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
-        else: 
-            plain_text = e4u.markdown_to_plain_text(business_query)
-            agent_response = "Generating Architecture Blueprint ---TOGAF VISION TARGET--- \n\nI am working on your request..."
-            togaf_chain = e4t.togaf_graph
-            final_diagram = ""
-            vision_message = ""
-            try:
-                async for s in togaf_chain.astream_events(
-                    {
-                        "messages": [
-                            HumanMessage(
-                                content=plain_text
-                            )
-                        ],
-                        "business_query": business_query,
-                    },
-                    config=config,
-                    version="v2"
-                ):    
-                    kind = s["event"]
-                    tags = s.get("tags", [])
-                    name = s['name']
-
-                    if "gra_stream" in tags and name == "stream_vision_target":
-                        if kind == "on_chain_stream":
-                            data = s["data"]
-                            # Accumulate the chunk of data
-                            chunk = data.get('chunk')
-                            if chunk is not None and hasattr(chunk, "content"):
-                                vision_message += chunk.content
-                            time.sleep(e4u.CFG.STREAM_SLEEP)
-                            yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
-                    elif name == "save_diagram" and kind == 'on_chain_end': #MOVED INTO Togaf_Task3
-                        output = s['data'].get('output', {})
-                        final_diagram = output.get('architecture_runway', "")
-                    elif ("assess_business_query" in tags or "assess_landscape" in tags) and kind == 'on_chain_start': ##'on_chat_model_stream':
-                        agent_response += f"\n\n`{tags[-1]}:{name}`"
-
-                        yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
-                    
-                if vision_message=="":
-                    agent_response = "I cannot generate the Architecture Vision. Please provide a valid Business Requirement content to start!"
-                    yield([agent_response,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, None, gr.Tabs(visible=False)])
-                elif "Error" not in final_diagram:
-                    yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),final_diagram, None, gr.Tabs(visible=True)])
-                else:
-                    yield([vision_message,gr.Tabs(visible=True), gr.Tabs(selected="id_togaf"),None, final_diagram, gr.Tabs(visible=True)])
-
-            except Exception as e:  
-                yield(
-                    [
-                        e.args[-1],
-                        gr.Tabs(visible=True), 
-                        gr.Tabs(selected="id_togaf"),
-                        None,
-                        None,
-                        gr.Tabs(visible=False)
-                    ]
-                )
-
-    async def run_pmo_agentic_system(prompt, chat_memory):
-        """
-        Answer a question about Project Portfolio Management and Architect Demand Management.
-
-        Args:
-            prompt (str): The propject portfolio user question
-            chat_memory (list): The tool message history
-
-        Returns:
-            str: A summary answering the user question
-        """
-        format_response = ""
-
-        if not prompt:
-            format_response = "Hi, how are you today? To start our conversation, please chat your message!"
-            chat_memory.append(ChatMessage(role="assistant", content=format_response))
-            yield chat_memory
-
-        if not chat_memory:
-            chat_memory.append(ChatMessage(role="user", content=prompt))
-            yield chat_memory
-
-        inputs = {
-            "question": prompt,
-            "verbose": True,  # optional flags
-        }
-        
-        #yield run_pmo_crew(inputs)
-
     #EA4ALL-Agentic system menu
     with gr.Tabs(selected="how_to") as tabs:
         with gr.Tab(label="Architect Demand Management"):
@@ -427,36 +462,36 @@ with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as e
                 container=True,
                 interactive=False,
             )
-            gr.Markdown(ea4all_about)
+            gr.Markdown(UIUtils.ea4all_about)
 
     #Podcast upload progress
-    podcast.change(show_progress='full')
+    podcast.change(show_progress='full', show_api=False,)
    
     #Togaf upload file
-    dbr_file.clear(unload_dbr,outputs=dbr_text)
-    dbr_file.change(on_dbrtext,inputs=dbr_file,outputs=dbr_text)
-    dbr_file.upload(load_dbr,inputs=dbr_file, outputs=dbr_text)
-    dbr_cls.click(off_dbrtext,outputs=[dbr_text, tabs_togaf, tab_diagram])
+    #dbr_file.clear(unload_dbr,outputs=dbr_text)
+    #dbr_file.change(on_dbrtext,inputs=dbr_file,outputs=dbr_text)
+    dbr_file.upload(UIUtils.load_dbr,inputs=dbr_file, outputs=dbr_text, show_api=False)
+    #dbr_cls.click(off_dbrtext,outputs=[dbr_text, tabs_togaf, tab_diagram])
 
     #Refactored ea4all_chatbot / vqa_chatbot (ChatInterface -> Chatbot)
     qna_prompt.submit(run_qna_agentic_system,[qna_prompt,ea4all_chatbot],ea4all_chatbot)
-    qna_prompt.submit(lambda: "", None, [qna_prompt])
-    ea4all_chatbot.like(fn=get_user_feedback)
-    qna_examples.input(lambda value: value, qna_examples, qna_prompt)
+    #qna_prompt.submit(lambda: "", None, [qna_prompt])
+    #ea4all_chatbot.like(fn=get_user_feedback)
+    #qna_examples.input(lambda value: value, qna_examples, qna_prompt)
 
     #Execute Reference Architecture
     dbr_run.click(run_reference_architecture_agentic_system,show_progress='full',inputs=[dbr_text],outputs=[togaf_vision,tabs_togaf,tabs_reference_architecture, architecture_runway, diagram_header, tab_diagram])
 
-    chat_msg = vqa_prompt.submit(add_message, [vqa_prompt, ea4all_vqa], [vqa_prompt, ea4all_vqa])
+    chat_msg = vqa_prompt.submit(UIUtils.add_message, [vqa_prompt, ea4all_vqa], [vqa_prompt, ea4all_vqa], show_api=False)
     bot_msg = chat_msg.then(run_vqa_agentic_system, [vqa_prompt, ea4all_vqa], ea4all_vqa, api_name="bot_response")
     
-    ea4all_vqa.like(fn=get_user_feedback)
-    vqa_examples.input(lambda value: value, vqa_examples, vqa_prompt)
+    #ea4all_vqa.like(fn=get_user_feedback)
+    #vqa_examples.input(lambda value: value, vqa_examples, vqa_prompt)
 
     #Invoke CrewAI PMO Agentic System
     pmo_prompt.submit(run_pmo_agentic_system,[pmo_prompt,pmo_chatbot],pmo_chatbot)
-    pmo_prompt.submit(lambda: "", None, [pmo_prompt])
-    pmo_examples.input(lambda value: value, pmo_examples, pmo_prompt)
+    pmo_prompt.submit(lambda: "", None, [pmo_prompt], show_api=False)
+    #pmo_examples.input(lambda value: value, pmo_examples, pmo_prompt)
 
     #Set initial state of apm and llm
-    ea4all_mcp.load(ea4all_agent_init, outputs=[ea4all_agent_metadata,ea4all_chatbot, ea4all_vqa, pmo_chatbot, confluence_list, confluence_df, apm_df, pmo_df])
+    ea4all_mcp.load(ea4all_agent_init, outputs=[ea4all_agent_metadata,ea4all_chatbot, ea4all_vqa, pmo_chatbot, confluence_list, confluence_df, apm_df, pmo_df], show_api=False)

ea4all/utils/utils.py

@@ -18,27 +18,47 @@ import os
 import time
 import pandas as pd
 import gradio as gr
-from PIL import Image
 
-#ea4all-about
-def ea4all_about():
-    readme = e4u.load_mock_content(e4u.CFG.EA4ALL_ABOUT)
-    return readme
+class UIUtils:
+    #ea4all-about
+    @staticmethod
+    def ea4all_about(show_api=False):
+        readme = e4u.load_mock_content(e4u.CFG.EA4ALL_ABOUT)
+        return readme
+
+    #vqa_chatbot (ChatInterface -> Chatbot)
+    @staticmethod
+    def add_message(message, history, show_api=False):
+        if message["text"] is not None:
+            history.append({"role": "user", "content": message["text"]})
+        
+        if len(message['files']) > 0:
+            history.append({"role": "user", "content": {"path": message['files'][-1]}})
+        
+        return (
+            gr.MultimodalTextbox(value=message, interactive=True, placeholder="Upload a diagram and type your message..."),
+            history
+        )
+
+    #Upload & clear business requirement
+    @staticmethod
+    def load_dbr(file, show_api=False):
+        return file.decode()
 
 #Load demo business requirements
-def init_dbr():
+def init_dbr(show_api=False):
     # Open the file in read mode ('r')
     with open(e4u._join_paths(BaseConfiguration.ea4all_store, gra.dbr_mock), 'r') as file:
         # Read the contents of the file
         contents = file.read()
     return contents
 
-def init_df():
+def init_df(show_api=False):
     return vectorstore.apm_dataframe_loader(e4u._join_paths(BaseConfiguration.ea4all_store, IndexConfiguration.apm_catalogue))
 
 #load core-architecture image
 #fix the issue with gr.Image(path) inside a docker containder
-def get_image(_image):
+def get_image(_image, show_api=False):
     #from PIL import Image
     # Load an image
     image = e4u._join_paths(BaseConfiguration.ea4all_images,_image)
@@ -46,7 +66,7 @@ def get_image(_image):
 
     return image
 
-def ea4all_confluence():
+def ea4all_confluence(show_api=False):
 
     #Confluence API Key
     confluence_api_key = os.environ['CONFLUENCE_API_KEY']
@@ -70,12 +90,12 @@ def ea4all_confluence():
 
     return df        
 
-def filter_page(page_list, title):
+def filter_page(page_list, title, show_api=False):
     x =  page_list[page_list["title"] == title]
     return x.iloc[0]['page_content']
 
 #get LLM response user's feedback
-def get_user_feedback(evt: gr.SelectData, request:gr.Request):
+def get_user_feedback(evt: gr.SelectData, request:gr.Request, show_api=False):
     ##{evt.index} {evt.value} {evt._data['liked']}
     try:     
         uuid_str = os.environ["EA4ALL_" + e4u.get_user_identification(request).replace(".","_")]
@@ -92,7 +112,7 @@ def get_user_feedback(evt: gr.SelectData, request:gr.Request):
         gr.Warning(f"Couldn't capture a feedback: {e}")
 
 #Set initial state of apm, llm and capture user-ip
-async def ea4all_agent_init(request:gr.Request):
+async def ea4all_agent_init(request:gr.Request, show_api=False):
 
     agentic_qna_desc="""Hi,
         improve effieciency, knowledge sharing, and get valuable insights from your IT landscape using natural language.
@@ -130,35 +150,17 @@ async def ea4all_agent_init(request:gr.Request):
     )
 
 #authentication
-def ea4all_login(username, password):
+def ea4all_login(username, password, show_api=False):
     return (username==password)
 
 #TABS & Reference Architecture look-and-feel control
-def off_dbrtext():
+def off_dbrtext(show_api=False):
     return gr.TextArea(visible=False), gr.Tab(visible=False), gr.Tab(visible=False)
 
-def on_dbrtext(file):
+def on_dbrtext(file,show_api=False):
     if file:
         return gr.TextArea(visible=True)
     return gr.TextArea(visible=False)
 
-#Upload & clear business requirement
-def load_dbr(file):
-    return file.decode()
-
-def unload_dbr():
+def unload_dbr(show_api=False):
     return gr.TextArea(visible=False)
-
-#vqa_chatbot (ChatInterface -> Chatbot)
-def add_message(message, history):
-    if message["text"] is not None:
-        history.append({"role": "user", "content": message["text"]})
-    
-    if len(message['files']) > 0:
-        history.append({"role": "user", "content": {"path": message['files'][-1]}})
-    
-    return (
-        gr.MultimodalTextbox(value=message, interactive=True, placeholder="Upload a diagram and type your message..."),
-        history
-    )
-