ea4all-gradio-agents-mcp-hackathon-tools-refactoring

ea4all/ea4all_mcp.py

@@ -49,40 +49,39 @@ config = RunnableConfig(
 )
 
 #ea4all-qna-agent-conversational-with-memory
-async def run_qna_agentic_system(prompt: str, chat_memory: list, request:gr.Request) -> AsyncGenerator[list, None]:
+async def run_qna_agentic_system(question: str, chat_memory: list) -> AsyncGenerator[list, None]:
     """
     description: 
         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.
+        question (str): The user's question or message.
+        chat_memory (list): The conversation history.
         request (gr.Request): The Gradio request object for user identification.
     Returns:
-        list: Response to user's question.
+        reponse: Response to user's architectural question.
     """
 
     format_response = ""
-
-    if not prompt:
+    if not question:
         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))
+        chat_memory.append(ChatMessage(role="user", content=question))
         yield chat_memory
 
-    if prompt:
+    if question:
         #capture user ip
-        ea4all_user = e4u.get_user_identification(request)
+        #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}]}
+        #inputs = {"question": question, "chat_memory":chat_memory}
+        inputs = {"messages": [{"role": "user", "content": question}]}
         
-        #add prompt to memory
-        chat_memory.append(ChatMessage(role="user", content=prompt))
+        #add question to memory
+        chat_memory.append(ChatMessage(role="user", content=question))
 
         partial_message = ""
         async for event in super_graph.astream_events(input=inputs, config=config, version="v2"):
@@ -157,29 +156,34 @@ async def run_qna_agentic_system(prompt: str, chat_memory: list, request:gr.Requ
                         yield chat_memory
 
             # Set environment variable only when 'event' is defined
-            os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
+            #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]:
+async def run_vqa_agentic_system(question: str, diagram: str, chat_memory: list, request: gr.Request) -> AsyncGenerator[list, None]:
     """
     description: 
         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.
+        question (str): User's question about the Architecture Diagram.
+        diagram (str): Path to the diagram file.
+        chat_memory: The conversation history.
     Returns:
-        list: Response to user's question.
+        response: Response to user's question.
     """
 
     #capture user ip
-    ea4all_user = e4u.get_user_identification(request)
+    #ea4all_user = e4u.get_user_identification(request)
 
     """Handle file uploads and validate their types."""
     allowed_file_types = ('JPEG', 'PNG')
 
+    message = {
+        'text': question,
+        'files': [diagram] if isinstance(diagram, str) else diagram
+    }
+
     print("---CALLING VISUAL QUESTION ANSWERING AGENTIC SYSTEM---")
     print(f"Prompt: {message}")
 
@@ -223,11 +227,11 @@ async def run_vqa_agentic_system(message: dict, chat_memory: list, request:gr.Re
                                     partial_message += chunk.content
                                     chat_memory[-1].content = partial_message
                                 time.sleep(e4u.CFG.STREAM_SLEEP)
-                                yield chat_memory #, message to update prompt
+                                yield chat_memory #, message to update question
                         elif not partial_message:
                             yield chat_memory #, message
                     
-                        os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
+                        #os.environ["EA4ALL_" + ea4all_user.replace(".", "_")] = str(event['run_id'])
                     
                     wait_for_all_tracers()
 
@@ -235,15 +239,14 @@ async def run_vqa_agentic_system(message: dict, chat_memory: list, request:gr.Re
             yield (e.args[-1])
 
 #Run Togaf Agentic System
-async def run_reference_architecture_agentic_system(business_query: str, request:gr.Request) -> AsyncGenerator[list, None]:
+async def run_reference_architecture_agentic_system(business_query: str) -> AsyncGenerator[list, None]:
     """
     description: 
         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.
+        business_query (str): Description of a business problem / requirement.
     Returns:
-        list: Response to user's question.
+        response: High-level architecture blueprint and target diagram.
     """
 
     if len(business_query) < 50:
@@ -309,30 +312,29 @@ async def run_reference_architecture_agentic_system(business_query: str, request
                 ]
             )
 
-async def run_pmo_agentic_system(prompt, chat_memory):
+async def run_pmo_agentic_system(question:str, chat_memory: list) -> AsyncGenerator[list, None]:
     """
     description: 
         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.
+        question (str): The user's question about project portfolio or resource management.
+        chat_memory: The conversation history.
     Returns:
-        list: Updated chat memory after each event or response.
+        response: Architect Demand Allocation Report
     """
 
     format_response = ""
-
-    if not prompt:
+    if not question:
         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))
+        chat_memory.append(ChatMessage(role="user", content=question))
         yield chat_memory
 
     inputs = {
-        "question": prompt,
+        "question": question,
         "verbose": True,  # optional flags
     }
     
@@ -376,7 +378,7 @@ with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as e
                 ea4all_pmo_description = gr.Markdown(value=agentic_pmo_desc)
                 pmo_chatbot = gr.Chatbot(label="EA4ALL your AI Architect Companion", type="messages")
                 pmo_prompt = gr.Textbox(lines=1, show_label=False, max_lines=1, submit_btn=True, stop_btn=True,autofocus=True, placeholder="Type your message here or select an example...")
-                with gr.Accordion("Open for prompt examples", open=False):
+                with gr.Accordion("Open for question examples", open=False):
                     pmo_examples = gr.Dropdown(e4u.get_relevant_questions(PMO_MOCK_QNA), value=None,label="Questions", interactive=True)
                 gr.ClearButton([pmo_chatbot,pmo_prompt], value="Clear", size="sm", visible=False)
             with gr.Tab(label="Project Portfolio Sample Dataset", id="id_pmo_ds"):
@@ -387,7 +389,7 @@ with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as e
                     ea4all_agent_metadata = gr.Markdown(value=agentic_qna_desc)
                     ea4all_chatbot = gr.Chatbot(label="EA4ALL your AI Architect Companion", type="messages")
                     qna_prompt = gr.Textbox(lines=1, show_label=False, max_lines=1, submit_btn=True, stop_btn=True,autofocus=True, placeholder="Type your message here or select an example...")
-                    with gr.Accordion("Open for prompt examples", open=False):
+                    with gr.Accordion("Open for question examples", open=False):
                         qna_examples = gr.Dropdown(e4u.get_relevant_questions(APM_MOCK_QNA), value=None,label="Questions", interactive=True)
                     gr.ClearButton([ea4all_chatbot,qna_prompt], value="Clear", size="sm", visible=False)
                 with gr.Tab(label="Sample Dataset", id="id_apm_ds"):
@@ -396,14 +398,14 @@ with gr.Blocks(title="Your ArchitectGPT",fill_height=True, fill_width=True) as e
             gr.Markdown(value=agentic_vqa_desc)
             ea4all_vqa = gr.Chatbot(label="EA4ALL your AI Multimodal Architect Companion", type="messages")
             vqa_prompt = gr.MultimodalTextbox(interactive=True, show_label=False, submit_btn=True, stop_btn=True, autofocus=True, placeholder="Upload your diagram and type your message or select an example...")
-            with gr.Accordion("Open for prompt examples", open=False):
+            with gr.Accordion("Open for question examples", open=False):
                 vqa_examples = gr.Dropdown(e4u.get_vqa_examples(), value=None,label="Diagram and Questions", interactive=True)
             gr.ClearButton([ea4all_vqa,vqa_prompt,vqa_examples], value="Clear", size="sm", visible=True)
         with gr.Tab(label="Reference Architecture", id="id_refarch"):
             with gr.Tabs(selected="id_dbr") as tabs_reference_architecture:
                 with gr.Tab(label='Business Requirement', id="id_dbr"):
                     gr.Markdown(value=agentic_togaf_desc)
-                    dbr_text=gr.TextArea(value="Provide a Business Requirement Specification or Select the exemple provided.", lines=14, interactive=True)
+                    dbr_text=gr.TextArea(value="Provide a Business Problem / Requirement Specification or select an example provided.", lines=14, interactive=True)
                     with gr.Row():
                         dbr_file=gr.File(
                             value=e4u._join_paths(BaseConfiguration.ea4all_store, gra.dbr_mock),