diff --git a/.env b/.env
deleted file mode 100644
index e578db1..0000000
--- a/.env
+++ /dev/null
@@ -1,5 +0,0 @@
-# LlamaCloud API configuration
-LLAMA_CLOUD_API_KEY=llx-your-api-key-here
-
-# OpenAI API configuration  
-OPENAI_API_KEY=sk-your-openai-api-key-here
diff --git a/.env.template b/.env.template
new file mode 100644
index 0000000..eb7fa0a
--- /dev/null
+++ b/.env.template
@@ -0,0 +1,2 @@
+# Copy this to .env and set any necessary secrets
+OPENAI_API_KEY=sk-your-openai-api-key-here
diff --git a/.github/workflows/check-regeneration.yml b/.github/workflows/check-regeneration.yml
new file mode 100644
index 0000000..cb15cea
--- /dev/null
+++ b/.github/workflows/check-regeneration.yml
@@ -0,0 +1,69 @@
+name: Check Template Regeneration
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  check-template:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.13'
+        
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+      
+    - name: Run regeneration check
+      run: uv run copier/copy_utils.py check-regeneration
+      
+  check-python:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.13'
+        
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+      
+    - name: Run Python checks
+      run: uv run hatch run all-check
+      working-directory: test-proj
+      
+  check-ui:
+    runs-on: ubuntu-latest
+    
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      
+    - name: Set up Node.js
+      uses: actions/setup-node@v4
+      with:
+        node-version: '24'
+
+    - name: Enable Corepack
+      run: corepack enable
+
+    - name: Activate pnpm version
+      working-directory: test-proj/ui
+      run: corepack prepare --activate
+
+      
+    - name: Run UI checks
+      run: pnpm run all-check
+      working-directory: test-proj/ui 
\ No newline at end of file
diff --git a/.gitignore.jinja b/.gitignore.jinja
new file mode 100644
index 0000000..06b8b0d
--- /dev/null
+++ b/.gitignore.jinja
@@ -0,0 +1,4 @@
+.env
+__pycache__
+workflows.db
+.venv
diff --git a/copier.yaml b/copier.yaml
index 8439d41..eedba2f 100644
--- a/copier.yaml
+++ b/copier.yaml
@@ -8,17 +8,10 @@ project_name:
         Project name must contain only letters, numbers, and dashes
     {% endif %}
 
-llama_project_id:
-  type: str
-  help: What is your Llama Cloud project ID?
-  default: ""
-  required: true
-
-llama_org_id:
+project_title:
   type: str
-  help: What is your Llama Cloud organization ID?
-  default: ""
-  required: true
+  help: What is the title of your project? This will be used in the UI Title Bar.
+  default: "{{ project_name.replace('-', ' ').title() }}"
 
 # computed variables
 project_name_snake:
@@ -26,15 +19,10 @@ project_name_snake:
   default: "{{ project_name.replace('-', '_') }}"
   when: false
 
-project_title:
-  type: str
-  default: "{{ (project_name.replace('-', ' '))[:1] | upper ~ (project_name.replace('-', ' '))[1:] }}"
-  when: false
-
 _exclude:
   - "test-proj"
   - ".git"
   - ".github"
   - "copier"
   - "CONTRIBUTING.md"
-  - "copier.yaml"
\ No newline at end of file
+  - "copier.yaml"
diff --git a/copier/copy_utils.py b/copier/copy_utils.py
index 2c37c30..6555d29 100755
--- a/copier/copy_utils.py
+++ b/copier/copy_utils.py
@@ -44,6 +44,7 @@ def run_copier_quietly(src_path: str, dst_path: str, data: Dict[str, str]) -> No
         data=data,
         unsafe=True,
         quiet=True,
+        vcs_ref="HEAD",
     )
 
 
diff --git a/llama_deploy.yaml b/llama_deploy.yaml
deleted file mode 100644
index 1654876..0000000
--- a/llama_deploy.yaml
+++ /dev/null
@@ -1,8 +0,0 @@
-env_files:
-  - ".env"
-llama_cloud: true
-workflows:
-  upload: "document-qa.qa_workflows:DocumentUploadWorkflow"
-  chat: "document-qa.qa_workflows:ChatWorkflow"
-ui:
-  directory: ui
diff --git a/llama_deploy.yaml.jinja b/llama_deploy.yaml.jinja
deleted file mode 100644
index be93469..0000000
--- a/llama_deploy.yaml.jinja
+++ /dev/null
@@ -1,8 +0,0 @@
-env_files:
-  - ".env"
-llama_cloud: true
-workflows:
-  upload: "{{project_name_snake}}.qa_workflows:DocumentUploadWorkflow"
-  chat: "{{project_name_snake}}.qa_workflows:ChatWorkflow"
-ui:
-  directory: ui
diff --git a/pyproject.toml b/pyproject.toml
deleted file mode 100644
index 5fbb656..0000000
--- a/pyproject.toml
+++ /dev/null
@@ -1,25 +0,0 @@
-[project]
-name = "document-qa"
-version = "0.1.0"
-description = "Add your description here"
-readme = "README.md"
-authors = [
-    { name = "Terry Zhao", email = "terry@runllama.ai" }
-]
-requires-python = ">=3.12"
-dependencies = [
-    "llama-index-workflows>=2.2.0",
-    "python-cowsay>=1.2.1",
-    "llama-cloud-services>=0.6.0",
-    "llama-index-core>=0.12.0",
-    "llama-index-llms-openai>=0.3.0",
-    "llama-index-embeddings-openai>=0.3.0",
-    "python-dotenv>=1.0.1",
-]
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[dependency-groups]
-dev = []
diff --git a/pyproject.toml.jinja b/pyproject.toml.jinja
index e4a2fc3..08d2618 100644
--- a/pyproject.toml.jinja
+++ b/pyproject.toml.jinja
@@ -1,20 +1,17 @@
 [project]
-name = "{{project_name_snake}}"
+name = "{{ project_name_snake }}"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
-authors = [
-    { name = "Terry Zhao", email = "terry@runllama.ai" }
-]
+authors = []
 requires-python = ">=3.12"
 dependencies = [
-    "llama-index-workflows>=2.2.0",
-    "python-cowsay>=1.2.1",
-    "llama-cloud-services>=0.6.0",
-    "llama-index-core>=0.12.0",
-    "llama-index-llms-openai>=0.3.0",
-    "llama-index-embeddings-openai>=0.3.0",
-    "python-dotenv>=1.0.1",
+    "llama-index-workflows>=2.2.0,<3.0.0",
+    "llama-cloud-services>=0.6.68",
+    "llama-index-core>=0.14.0",
+    "llama-index-llms-openai>=0.5.6",
+    "llama-index-embeddings-openai>=0.5.1",
+    "python-dotenv>=1.1.1",
 ]
 
 [build-system]
@@ -22,5 +19,30 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [dependency-groups]
-dev = []
+dev = [
+    "hatch>=1.14.1",
+    "pytest>=8.4.2",
+    "ruff>=0.13.0",
+    "ty>=0.0.1a20",
+]
+
+[tool.hatch.envs.default.scripts]
+"format" = "ruff format ."
+"format-check" = "ruff format --check ."
+"lint" = "ruff check --fix ."
+"lint-check" = ["ruff check ."]
+typecheck = "ty check src"
+test = "pytest"
+"all-check" = ["format-check", "lint-check", "test"]
+"all-fix" = ["format", "lint", "test"]
+
+[tool.llamadeploy]
+env-files = [".env"]
+llama_cloud = true
+
+[tool.llamadeploy.ui]
+directory = "./ui"
 
+[tool.llamadeploy.workflows]
+upload = "test_proj.qa_workflows:upload"
+chat = "test_proj.qa_workflows:chat"
diff --git a/src/{{project_name_snake}}/__init__.py b/src/{{ project_name_snake }}/__init__.py
similarity index 100%
rename from src/{{project_name_snake}}/__init__.py
rename to src/{{ project_name_snake }}/__init__.py
diff --git a/src/{{ project_name_snake }}/clients.py b/src/{{ project_name_snake }}/clients.py
new file mode 100644
index 0000000..9f8d0d8
--- /dev/null
+++ b/src/{{ project_name_snake }}/clients.py	
@@ -0,0 +1,52 @@
+import functools
+import os
+import httpx
+
+from llama_cloud.client import AsyncLlamaCloud
+from llama_cloud_services import LlamaParse
+
+# deployed agents may infer their name from the deployment name
+# Note: Make sure that an agent deployment with this name actually exists
+# otherwise calls to get or set data will fail. You may need to adjust the `or `
+# name for development
+DEPLOYMENT_NAME = os.getenv("LLAMA_DEPLOY_DEPLOYMENT_NAME")
+# required for all llama cloud calls
+LLAMA_CLOUD_API_KEY = os.environ["LLAMA_CLOUD_API_KEY"]
+# get this in case running against a different environment than production
+LLAMA_CLOUD_BASE_URL = os.getenv("LLAMA_CLOUD_BASE_URL")
+LLAMA_CLOUD_PROJECT_ID = os.getenv("LLAMA_DEPLOY_PROJECT_ID")
+INDEX_NAME = "document_qa_index"
+
+
+def get_custom_client() -> httpx.AsyncClient:
+    return httpx.AsyncClient(
+        timeout=60,
+        headers={"Project-Id": LLAMA_CLOUD_PROJECT_ID}
+        if LLAMA_CLOUD_PROJECT_ID
+        else None,
+    )
+
+
+@functools.cache
+def get_llama_cloud_client() -> AsyncLlamaCloud:
+    return AsyncLlamaCloud(
+        base_url=LLAMA_CLOUD_BASE_URL,
+        token=LLAMA_CLOUD_API_KEY,
+        httpx_client=get_custom_client(),
+    )
+
+
+@functools.cache
+def get_llama_parse_client() -> LlamaParse:
+    return LlamaParse(
+        parse_mode="parse_page_with_agent",
+        model="openai-gpt-4-1-mini",
+        high_res_ocr=True,
+        adaptive_long_table=True,
+        outlined_table_extraction=True,
+        output_tables_as_HTML=True,
+        result_type="markdown",
+        api_key=LLAMA_CLOUD_API_KEY,
+        project_id=LLAMA_CLOUD_PROJECT_ID,
+        custom_client=get_custom_client(),
+    )
diff --git a/src/{{project_name_snake}}/qa_workflows.py b/src/{{ project_name_snake }}/qa_workflows.py
similarity index 59%
rename from src/{{project_name_snake}}/qa_workflows.py
rename to src/{{ project_name_snake }}/qa_workflows.py
index 96feecb..5363255 100644
--- a/src/{{project_name_snake}}/qa_workflows.py
+++ b/src/{{ project_name_snake }}/qa_workflows.py	
@@ -1,27 +1,35 @@
 import logging
 import os
-import uuid
 
 import httpx
 from llama_cloud.types import RetrievalMode
 import tempfile
 from llama_index.core.chat_engine.types import BaseChatEngine, ChatMode
 from workflows import Workflow, step, Context
-from workflows.events import StartEvent, StopEvent, Event, InputRequiredEvent, HumanResponseEvent
+from workflows.events import (
+    StartEvent,
+    StopEvent,
+    Event,
+    InputRequiredEvent,
+    HumanResponseEvent,
+)
 from workflows.retry_policy import ConstantDelayRetryPolicy
-from workflows.server import WorkflowServer
 
-from llama_cloud_services import LlamaParse, LlamaCloudIndex
+from llama_cloud_services import LlamaCloudIndex
 from llama_index.core import Settings
 from llama_index.llms.openai import OpenAI
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.core.memory import ChatMemoryBuffer
-from dotenv import load_dotenv
-from .clients import get_custom_client, get_llama_cloud_client
-from .config import PROJECT_ID, ORGANIZATION_ID
 
-# Load environment variables
-load_dotenv()
+from .clients import (
+    LLAMA_CLOUD_API_KEY,
+    LLAMA_CLOUD_BASE_URL,
+    get_custom_client,
+    get_llama_cloud_client,
+    get_llama_parse_client,
+    LLAMA_CLOUD_PROJECT_ID,
+)
+
 
 logger = logging.getLogger(__name__)
 
@@ -30,57 +38,45 @@ class FileEvent(StartEvent):
     file_id: str
     index_name: str
 
+
 class DownloadFileEvent(Event):
     file_id: str
 
+
 class FileDownloadedEvent(Event):
     file_id: str
     file_path: str
     filename: str
 
+
 class ChatEvent(StartEvent):
     index_name: str
     session_id: str
 
+
 # Configure LLM and embedding model
 Settings.llm = OpenAI(model="gpt-4", temperature=0.1)
 Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")
 
 custom_client = get_custom_client()
 
+
 class DocumentUploadWorkflow(Workflow):
     """Workflow to upload and index documents using LlamaParse and LlamaCloud Index"""
-    
+
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         # Get API key with validation
-        api_key = os.getenv("LLAMA_CLOUD_API_KEY")
-        if not api_key:
-            logger.warning("Warning: LLAMA_CLOUD_API_KEY not found in environment. Document upload will not work.")
-            self.parser = None
-        else:
-            # Initialize LlamaParse with recommended settings
-            logger.info(f"Initializing LlamaParse with API key: {api_key}")
-            self.parser = LlamaParse(
-                parse_mode="parse_page_with_agent",
-                model="openai-gpt-4-1-mini",
-                high_res_ocr=True,
-                adaptive_long_table=True,
-                outlined_table_extraction=True,
-                output_tables_as_HTML=True,
-                result_type="markdown",
-                api_key=api_key,
-                project_id=PROJECT_ID,
-                organization_id=ORGANIZATION_ID,
-                custom_client=custom_client
-            )
+
+        # Initialize LlamaParse with recommended settings
+        self.parser = get_llama_parse_client()
 
     @step(retry_policy=ConstantDelayRetryPolicy(maximum_attempts=3, delay=10))
     async def run_file(self, event: FileEvent, ctx: Context) -> DownloadFileEvent:
         logger.info(f"Running file {event.file_id}")
         await ctx.store.set("index_name", event.index_name)
         return DownloadFileEvent(file_id=event.file_id)
-    
+
     @step(retry_policy=ConstantDelayRetryPolicy(maximum_attempts=3, delay=10))
     async def download_file(
         self, event: DownloadFileEvent, ctx: Context
@@ -114,78 +110,61 @@ async def download_file(
             logger.error(f"Error downloading file {event.file_id}: {e}", exc_info=True)
             raise e
 
-    
     @step
     async def parse_document(self, ev: FileDownloadedEvent, ctx: Context) -> StopEvent:
         """Parse document and index it to LlamaCloud"""
         try:
             logger.info(f"Parsing document {ev.file_id}")
-            # Check if parser is initialized
-            if not self.parser:
-                return StopEvent(result={
-                    "success": False,
-                    "error": "LLAMA_CLOUD_API_KEY not configured. Please set it in your .env file."
-                })
-            
             # Get file path or content from event
             file_path = ev.file_path
             file_name = file_path.split("/")[-1]
             index_name = await ctx.store.get("index_name")
-            
+
             # Parse the document
             if file_path:
                 # Parse from file path
                 result = await self.parser.aparse(file_path)
-            
+
             # Get parsed documents
             documents = result.get_text_documents()
-            
+
             # Create or connect to LlamaCloud Index
-            try:
-                logger.info(f"Connecting to existing index {index_name}")
-                # Try to connect to existing index
-                index = LlamaCloudIndex(
-                    name=index_name,
-                    project_id=PROJECT_ID,
-                    organization_id=ORGANIZATION_ID,
-                    api_key=os.getenv("LLAMA_CLOUD_API_KEY"),
-                    custom_client=custom_client
-                )
-                for document in documents:
-                    index.insert(document)
-            except Exception:
-                # Create new index if doesn't exist
-                logger.info(f"Creating new index {index_name}")
-                index = LlamaCloudIndex.from_documents(
-                    documents=documents,
-                    name=index_name,
-                    project_id=PROJECT_ID,
-                    organization_id=ORGANIZATION_ID,
-                    api_key=os.getenv("LLAMA_CLOUD_API_KEY"),
-                    show_progress=True,
-                    custom_client=custom_client
-                )
-                
-            return StopEvent(result={
-                "success": True,
-                "index_name": index_name,
-                "index_url": f"https://cloud.llamaindex.ai/projects/{PROJECT_ID}/indexes/{index.id}",
-                "document_count": len(documents),
-                "file_name": file_name,
-                "message": f"Successfully indexed {len(documents)} documents to '{index_name}'"
-            })
-            
+            index = LlamaCloudIndex.create_index(
+                documents=documents,
+                name=index_name,
+                project_id=LLAMA_CLOUD_PROJECT_ID,
+                api_key=LLAMA_CLOUD_API_KEY,
+                base_url=LLAMA_CLOUD_BASE_URL,
+                show_progress=True,
+                custom_client=custom_client,
+            )
+
+            # Insert documents to index
+            logger.info(f"Inserting {len(documents)} documents to {index_name}")
+            for document in documents:
+                index.insert(document)
+
+            return StopEvent(
+                result={
+                    "success": True,
+                    "index_name": index_name,
+                    "document_count": len(documents),
+                    "index_url": f"https://cloud.llamaindex.ai/projects/{LLAMA_CLOUD_PROJECT_ID}/indexes/{index.id}",
+                    "file_name": file_name,
+                    "message": f"Successfully indexed {len(documents)} documents to '{index_name}'",
+                }
+            )
+
         except Exception as e:
             logger.error(e.stack_trace)
-            return StopEvent(result={
-                "success": False,
-                "error": str(e),
-                "stack_trace": e.stack_trace
-            })
+            return StopEvent(
+                result={"success": False, "error": str(e), "stack_trace": e.stack_trace}
+            )
 
 
 class ChatResponseEvent(Event):
     """Event emitted when chat engine generates a response"""
+
     response: str
     sources: list
     query: str
@@ -193,6 +172,7 @@ class ChatResponseEvent(Event):
 
 class ChatDeltaEvent(Event):
     """Streaming delta for incremental response output"""
+
     delta: str
 
 
@@ -201,7 +181,9 @@ class ChatWorkflow(Workflow):
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        self.chat_engines: dict[str, BaseChatEngine] = {}  # Cache chat engines per index
+        self.chat_engines: dict[
+            str, BaseChatEngine
+        ] = {}  # Cache chat engines per index
 
     @step
     async def initialize_chat(self, ev: ChatEvent, ctx: Context) -> InputRequiredEvent:
@@ -225,10 +207,10 @@ async def initialize_chat(self, ev: ChatEvent, ctx: Context) -> InputRequiredEve
                 # Connect to LlamaCloud Index
                 index = LlamaCloudIndex(
                     name=index_name,
-                    project_id=PROJECT_ID,
-                    organization_id=ORGANIZATION_ID,
-                    api_key=os.getenv("LLAMA_CLOUD_API_KEY"),
-                    custom_client=custom_client
+                    project_id=LLAMA_CLOUD_PROJECT_ID,
+                    api_key=LLAMA_CLOUD_API_KEY,
+                    base_url=LLAMA_CLOUD_BASE_URL,
+                    async_httpx_client=custom_client,
                 )
 
                 # Create chat engine with memory
@@ -252,13 +234,17 @@ async def initialize_chat(self, ev: ChatEvent, ctx: Context) -> InputRequiredEve
             )
 
         except Exception as e:
-            return StopEvent(result={
-                "success": False,
-                "error": f"Failed to initialize chat: {str(e)}"
-            })
+            return StopEvent(
+                result={
+                    "success": False,
+                    "error": f"Failed to initialize chat: {str(e)}",
+                }
+            )
 
     @step
-    async def process_user_response(self, ev: HumanResponseEvent, ctx: Context) -> InputRequiredEvent | HumanResponseEvent | StopEvent | None:
+    async def process_user_response(
+        self, ev: HumanResponseEvent, ctx: Context
+    ) -> InputRequiredEvent | HumanResponseEvent | StopEvent | None:
         """Process user input and generate response"""
         try:
             logger.info(f"Processing user response {ev.response}")
@@ -268,13 +254,17 @@ async def process_user_response(self, ev: HumanResponseEvent, ctx: Context) -> I
 
             # Check for exit command
             if user_input.lower() == "exit":
-                logger.info(f"User input is exit")
-                conversation_history = await ctx.store.get("conversation_history", default=[])
-                return StopEvent(result={
-                    "success": True,
-                    "message": "Chat session ended.",
-                    "conversation_history": conversation_history
-                })
+                logger.info("User input is exit")
+                conversation_history = await ctx.store.get(
+                    "conversation_history", default=[]
+                )
+                return StopEvent(
+                    result={
+                        "success": True,
+                        "message": "Chat session ended.",
+                        "conversation_history": conversation_history,
+                    }
+                )
 
             # Get session info from context
             index_name = await ctx.store.get("index_name")
@@ -295,29 +285,43 @@ async def process_user_response(self, ev: HumanResponseEvent, ctx: Context) -> I
 
             # Extract source nodes for citations
             sources = []
-            if hasattr(stream_response, 'source_nodes'):
+            if hasattr(stream_response, "source_nodes"):
                 for node in stream_response.source_nodes:
-                    sources.append({
-                        "text": node.text[:200] + "..." if len(node.text) > 200 else node.text,
-                        "score": node.score if hasattr(node, 'score') else None,
-                        "metadata": node.metadata if hasattr(node, 'metadata') else {}
-                    })
+                    sources.append(
+                        {
+                            "text": node.text[:200] + "..."
+                            if len(node.text) > 200
+                            else node.text,
+                            "score": node.score if hasattr(node, "score") else None,
+                            "metadata": node.metadata
+                            if hasattr(node, "metadata")
+                            else {},
+                        }
+                    )
 
             # Update conversation history
-            conversation_history = await ctx.store.get("conversation_history", default=[])
-            conversation_history.append({
-                "query": user_input,
-                "response": full_text.strip() if full_text else str(stream_response),
-                "sources": sources
-            })
+            conversation_history = await ctx.store.get(
+                "conversation_history", default=[]
+            )
+            conversation_history.append(
+                {
+                    "query": user_input,
+                    "response": full_text.strip()
+                    if full_text
+                    else str(stream_response),
+                    "sources": sources,
+                }
+            )
             await ctx.store.set("conversation_history", conversation_history)
 
             # After streaming completes, emit a summary response event to stream for frontend/main printing
-            ctx.write_event_to_stream(ChatResponseEvent(
-                response=full_text.strip() if full_text else str(stream_response),
-                sources=sources,
-                query=user_input,
-            ))
+            ctx.write_event_to_stream(
+                ChatResponseEvent(
+                    response=full_text.strip() if full_text else str(stream_response),
+                    sources=sources,
+                    query=user_input,
+                )
+            )
 
             # Prompt for next input
             return InputRequiredEvent(
@@ -325,14 +329,10 @@ async def process_user_response(self, ev: HumanResponseEvent, ctx: Context) -> I
             )
 
         except Exception as e:
-            return StopEvent(result={
-                "success": False,
-                "error": f"Error processing query: {str(e)}"
-            })
-
+            return StopEvent(
+                result={"success": False, "error": f"Error processing query: {str(e)}"}
+            )
 
 
-# Create workflow server
-app = WorkflowServer()
-app.add_workflow("upload", DocumentUploadWorkflow(timeout=300))
-app.add_workflow("chat", ChatWorkflow(timeout=None))
+upload = DocumentUploadWorkflow(timeout=None)
+chat = ChatWorkflow(timeout=None)
diff --git a/src/{{project_name_snake}}/__pycache__/__init__.cpython-312.pyc b/src/{{project_name_snake}}/__pycache__/__init__.cpython-312.pyc
deleted file mode 100644
index 5f8b8bb..0000000
Binary files a/src/{{project_name_snake}}/__pycache__/__init__.cpython-312.pyc and /dev/null differ
diff --git a/src/{{project_name_snake}}/__pycache__/clients.cpython-312.pyc b/src/{{project_name_snake}}/__pycache__/clients.cpython-312.pyc
deleted file mode 100644
index d006654..0000000
Binary files a/src/{{project_name_snake}}/__pycache__/clients.cpython-312.pyc and /dev/null differ
diff --git a/src/{{project_name_snake}}/__pycache__/qa_workflows.cpython-312.pyc b/src/{{project_name_snake}}/__pycache__/qa_workflows.cpython-312.pyc
deleted file mode 100644
index d8de40b..0000000
Binary files a/src/{{project_name_snake}}/__pycache__/qa_workflows.cpython-312.pyc and /dev/null differ
diff --git a/src/{{project_name_snake}}/__pycache__/workflows.cpython-312.pyc b/src/{{project_name_snake}}/__pycache__/workflows.cpython-312.pyc
deleted file mode 100644
index 5ec673f..0000000
Binary files a/src/{{project_name_snake}}/__pycache__/workflows.cpython-312.pyc and /dev/null differ
diff --git a/src/{{project_name_snake}}/clients.py b/src/{{project_name_snake}}/clients.py
deleted file mode 100644
index ea324cd..0000000
--- a/src/{{project_name_snake}}/clients.py
+++ /dev/null
@@ -1,34 +0,0 @@
-import functools
-import os
-import httpx
-
-import dotenv
-from llama_cloud.client import AsyncLlamaCloud
-
-dotenv.load_dotenv()
-
-# deployed agents may infer their name from the deployment name
-# Note: Make sure that an agent deployment with this name actually exists
-# otherwise calls to get or set data will fail. You may need to adjust the `or `
-# name for development
-agent_name = os.getenv("LLAMA_DEPLOY_DEPLOYMENT_NAME")
-agent_name_or_default = agent_name or "test-proj"
-# required for all llama cloud calls
-api_key = os.environ["LLAMA_CLOUD_API_KEY"]
-# get this in case running against a different environment than production
-base_url = os.getenv("LLAMA_CLOUD_BASE_URL")
-project_id = os.getenv("LLAMA_DEPLOY_PROJECT_ID")
-
-
-def get_custom_client():
-    return httpx.AsyncClient(
-        timeout=60, headers={"Project-Id": project_id} if project_id else None
-    )
-
-@functools.lru_cache(maxsize=None)
-def get_llama_cloud_client():
-    return AsyncLlamaCloud(
-        base_url=base_url,
-        token=api_key,
-        httpx_client=get_custom_client(),
-    )
diff --git a/src/{{project_name_snake}}/config.py.jinja b/src/{{project_name_snake}}/config.py.jinja
deleted file mode 100644
index 1d7f57a..0000000
--- a/src/{{project_name_snake}}/config.py.jinja
+++ /dev/null
@@ -1,2 +0,0 @@
-PROJECT_ID = "{{ llama_project_id }}"
-ORGANIZATION_ID = "{{ llama_org_id }}"
\ No newline at end of file
diff --git a/test-proj/.copier-answers.yml b/test-proj/.copier-answers.yml
new file mode 100644
index 0000000..8463373
--- /dev/null
+++ b/test-proj/.copier-answers.yml
@@ -0,0 +1,6 @@
+# Changes here will be overwritten by Copier; NEVER EDIT MANUALLY
+_commit: '2405947'
+_src_path: .
+llama_org_id: asdf
+llama_project_id: asdf
+project_name: test-proj
diff --git a/test-proj/.env.template b/test-proj/.env.template
new file mode 100644
index 0000000..eb7fa0a
--- /dev/null
+++ b/test-proj/.env.template
@@ -0,0 +1,2 @@
+# Copy this to .env and set any necessary secrets
+OPENAI_API_KEY=sk-your-openai-api-key-here
diff --git a/test-proj/.gitignore b/test-proj/.gitignore
new file mode 100644
index 0000000..06b8b0d
--- /dev/null
+++ b/test-proj/.gitignore
@@ -0,0 +1,4 @@
+.env
+__pycache__
+workflows.db
+.venv
diff --git a/test-proj/README.md b/test-proj/README.md
new file mode 100644
index 0000000..92d1b72
--- /dev/null
+++ b/test-proj/README.md
@@ -0,0 +1,17 @@
+# Document Q&A Application
+
+A document question-answering application built with LlamaIndex workflows and LlamaCloud services.
+
+
+This application uses LlamaDeploy. For more information see [the docs](https://developers.llamaindex.ai/python/cloud/llamadeploy/getting-started)
+
+# Getting Started
+
+1. install `uv` if you haven't `brew install uv`
+2. run `uvx llamactl serve`
+3. Visit http://localhost:4501/docs and see workflow APIs
+
+
+# Organization
+
+- `src` contains python workflow sources. The name of the deployment here is defined as `document-qa`requests. See http://localhost:4501/docs for openAPI docs
diff --git a/test-proj/pyproject.toml b/test-proj/pyproject.toml
new file mode 100644
index 0000000..7206b7e
--- /dev/null
+++ b/test-proj/pyproject.toml
@@ -0,0 +1,48 @@
+[project]
+name = "test_proj"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+authors = []
+requires-python = ">=3.12"
+dependencies = [
+    "llama-index-workflows>=2.2.0,<3.0.0",
+    "llama-cloud-services>=0.6.68",
+    "llama-index-core>=0.14.0",
+    "llama-index-llms-openai>=0.5.6",
+    "llama-index-embeddings-openai>=0.5.1",
+    "python-dotenv>=1.1.1",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[dependency-groups]
+dev = [
+    "hatch>=1.14.1",
+    "pytest>=8.4.2",
+    "ruff>=0.13.0",
+    "ty>=0.0.1a20",
+]
+
+[tool.hatch.envs.default.scripts]
+"format" = "ruff format ."
+"format-check" = "ruff format --check ."
+"lint" = "ruff check --fix ."
+"lint-check" = ["ruff check ."]
+typecheck = "ty check src"
+test = "pytest"
+"all-check" = ["format-check", "lint-check", "test"]
+"all-fix" = ["format", "lint", "test"]
+
+[tool.llamadeploy]
+env-files = [".env"]
+llama_cloud = true
+
+[tool.llamadeploy.ui]
+directory = "./ui"
+
+[tool.llamadeploy.workflows]
+upload = "test_proj.qa_workflows:upload"
+chat = "test_proj.qa_workflows:chat"
diff --git a/test-proj/src/test_proj/__init__.py b/test-proj/src/test_proj/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/test-proj/src/test_proj/clients.py b/test-proj/src/test_proj/clients.py
new file mode 100644
index 0000000..9f8d0d8
--- /dev/null
+++ b/test-proj/src/test_proj/clients.py
@@ -0,0 +1,52 @@
+import functools
+import os
+import httpx
+
+from llama_cloud.client import AsyncLlamaCloud
+from llama_cloud_services import LlamaParse
+
+# deployed agents may infer their name from the deployment name
+# Note: Make sure that an agent deployment with this name actually exists
+# otherwise calls to get or set data will fail. You may need to adjust the `or `
+# name for development
+DEPLOYMENT_NAME = os.getenv("LLAMA_DEPLOY_DEPLOYMENT_NAME")
+# required for all llama cloud calls
+LLAMA_CLOUD_API_KEY = os.environ["LLAMA_CLOUD_API_KEY"]
+# get this in case running against a different environment than production
+LLAMA_CLOUD_BASE_URL = os.getenv("LLAMA_CLOUD_BASE_URL")
+LLAMA_CLOUD_PROJECT_ID = os.getenv("LLAMA_DEPLOY_PROJECT_ID")
+INDEX_NAME = "document_qa_index"
+
+
+def get_custom_client() -> httpx.AsyncClient:
+    return httpx.AsyncClient(
+        timeout=60,
+        headers={"Project-Id": LLAMA_CLOUD_PROJECT_ID}
+        if LLAMA_CLOUD_PROJECT_ID
+        else None,
+    )
+
+
+@functools.cache
+def get_llama_cloud_client() -> AsyncLlamaCloud:
+    return AsyncLlamaCloud(
+        base_url=LLAMA_CLOUD_BASE_URL,
+        token=LLAMA_CLOUD_API_KEY,
+        httpx_client=get_custom_client(),
+    )
+
+
+@functools.cache
+def get_llama_parse_client() -> LlamaParse:
+    return LlamaParse(
+        parse_mode="parse_page_with_agent",
+        model="openai-gpt-4-1-mini",
+        high_res_ocr=True,
+        adaptive_long_table=True,
+        outlined_table_extraction=True,
+        output_tables_as_HTML=True,
+        result_type="markdown",
+        api_key=LLAMA_CLOUD_API_KEY,
+        project_id=LLAMA_CLOUD_PROJECT_ID,
+        custom_client=get_custom_client(),
+    )
diff --git a/test-proj/src/test_proj/qa_workflows.py b/test-proj/src/test_proj/qa_workflows.py
new file mode 100644
index 0000000..5363255
--- /dev/null
+++ b/test-proj/src/test_proj/qa_workflows.py
@@ -0,0 +1,338 @@
+import logging
+import os
+
+import httpx
+from llama_cloud.types import RetrievalMode
+import tempfile
+from llama_index.core.chat_engine.types import BaseChatEngine, ChatMode
+from workflows import Workflow, step, Context
+from workflows.events import (
+    StartEvent,
+    StopEvent,
+    Event,
+    InputRequiredEvent,
+    HumanResponseEvent,
+)
+from workflows.retry_policy import ConstantDelayRetryPolicy
+
+from llama_cloud_services import LlamaCloudIndex
+from llama_index.core import Settings
+from llama_index.llms.openai import OpenAI
+from llama_index.embeddings.openai import OpenAIEmbedding
+from llama_index.core.memory import ChatMemoryBuffer
+
+from .clients import (
+    LLAMA_CLOUD_API_KEY,
+    LLAMA_CLOUD_BASE_URL,
+    get_custom_client,
+    get_llama_cloud_client,
+    get_llama_parse_client,
+    LLAMA_CLOUD_PROJECT_ID,
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+class FileEvent(StartEvent):
+    file_id: str
+    index_name: str
+
+
+class DownloadFileEvent(Event):
+    file_id: str
+
+
+class FileDownloadedEvent(Event):
+    file_id: str
+    file_path: str
+    filename: str
+
+
+class ChatEvent(StartEvent):
+    index_name: str
+    session_id: str
+
+
+# Configure LLM and embedding model
+Settings.llm = OpenAI(model="gpt-4", temperature=0.1)
+Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")
+
+custom_client = get_custom_client()
+
+
+class DocumentUploadWorkflow(Workflow):
+    """Workflow to upload and index documents using LlamaParse and LlamaCloud Index"""
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        # Get API key with validation
+
+        # Initialize LlamaParse with recommended settings
+        self.parser = get_llama_parse_client()
+
+    @step(retry_policy=ConstantDelayRetryPolicy(maximum_attempts=3, delay=10))
+    async def run_file(self, event: FileEvent, ctx: Context) -> DownloadFileEvent:
+        logger.info(f"Running file {event.file_id}")
+        await ctx.store.set("index_name", event.index_name)
+        return DownloadFileEvent(file_id=event.file_id)
+
+    @step(retry_policy=ConstantDelayRetryPolicy(maximum_attempts=3, delay=10))
+    async def download_file(
+        self, event: DownloadFileEvent, ctx: Context
+    ) -> FileDownloadedEvent:
+        """Download the file reference from the cloud storage"""
+        logger.info(f"Downloading file {event.file_id}")
+        try:
+            file_metadata = await get_llama_cloud_client().files.get_file(
+                id=event.file_id
+            )
+            file_url = await get_llama_cloud_client().files.read_file_content(
+                event.file_id
+            )
+
+            temp_dir = tempfile.gettempdir()
+            filename = file_metadata.name
+            file_path = os.path.join(temp_dir, filename)
+            client = httpx.AsyncClient()
+            # Report progress to the UI
+            logger.info(f"Downloading file {file_url.url} to {file_path}")
+
+            async with client.stream("GET", file_url.url) as response:
+                with open(file_path, "wb") as f:
+                    async for chunk in response.aiter_bytes():
+                        f.write(chunk)
+            logger.info(f"Downloaded file {file_url.url} to {file_path}")
+            return FileDownloadedEvent(
+                file_id=event.file_id, file_path=file_path, filename=filename
+            )
+        except Exception as e:
+            logger.error(f"Error downloading file {event.file_id}: {e}", exc_info=True)
+            raise e
+
+    @step
+    async def parse_document(self, ev: FileDownloadedEvent, ctx: Context) -> StopEvent:
+        """Parse document and index it to LlamaCloud"""
+        try:
+            logger.info(f"Parsing document {ev.file_id}")
+            # Get file path or content from event
+            file_path = ev.file_path
+            file_name = file_path.split("/")[-1]
+            index_name = await ctx.store.get("index_name")
+
+            # Parse the document
+            if file_path:
+                # Parse from file path
+                result = await self.parser.aparse(file_path)
+
+            # Get parsed documents
+            documents = result.get_text_documents()
+
+            # Create or connect to LlamaCloud Index
+            index = LlamaCloudIndex.create_index(
+                documents=documents,
+                name=index_name,
+                project_id=LLAMA_CLOUD_PROJECT_ID,
+                api_key=LLAMA_CLOUD_API_KEY,
+                base_url=LLAMA_CLOUD_BASE_URL,
+                show_progress=True,
+                custom_client=custom_client,
+            )
+
+            # Insert documents to index
+            logger.info(f"Inserting {len(documents)} documents to {index_name}")
+            for document in documents:
+                index.insert(document)
+
+            return StopEvent(
+                result={
+                    "success": True,
+                    "index_name": index_name,
+                    "document_count": len(documents),
+                    "index_url": f"https://cloud.llamaindex.ai/projects/{LLAMA_CLOUD_PROJECT_ID}/indexes/{index.id}",
+                    "file_name": file_name,
+                    "message": f"Successfully indexed {len(documents)} documents to '{index_name}'",
+                }
+            )
+
+        except Exception as e:
+            logger.error(e.stack_trace)
+            return StopEvent(
+                result={"success": False, "error": str(e), "stack_trace": e.stack_trace}
+            )
+
+
+class ChatResponseEvent(Event):
+    """Event emitted when chat engine generates a response"""
+
+    response: str
+    sources: list
+    query: str
+
+
+class ChatDeltaEvent(Event):
+    """Streaming delta for incremental response output"""
+
+    delta: str
+
+
+class ChatWorkflow(Workflow):
+    """Workflow to handle continuous chat queries against indexed documents"""
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.chat_engines: dict[
+            str, BaseChatEngine
+        ] = {}  # Cache chat engines per index
+
+    @step
+    async def initialize_chat(self, ev: ChatEvent, ctx: Context) -> InputRequiredEvent:
+        """Initialize the chat session and request first input"""
+        try:
+            logger.info(f"Initializing chat {ev.index_name}")
+            index_name = ev.index_name
+            session_id = ev.session_id
+
+            # Store session info in context
+            await ctx.store.set("index_name", index_name)
+            await ctx.store.set("session_id", session_id)
+            await ctx.store.set("conversation_history", [])
+
+            # Create cache key for chat engine
+            cache_key = f"{index_name}_{session_id}"
+
+            # Initialize chat engine if not exists
+            if cache_key not in self.chat_engines:
+                logger.info(f"Initializing chat engine {cache_key}")
+                # Connect to LlamaCloud Index
+                index = LlamaCloudIndex(
+                    name=index_name,
+                    project_id=LLAMA_CLOUD_PROJECT_ID,
+                    api_key=LLAMA_CLOUD_API_KEY,
+                    base_url=LLAMA_CLOUD_BASE_URL,
+                    async_httpx_client=custom_client,
+                )
+
+                # Create chat engine with memory
+                memory = ChatMemoryBuffer.from_defaults(token_limit=3900)
+                self.chat_engines[cache_key] = index.as_chat_engine(
+                    chat_mode=ChatMode.CONTEXT,
+                    memory=memory,
+                    llm=Settings.llm,
+                    context_prompt=(
+                        "You are a helpful assistant that answers questions based on the provided documents. "
+                        "Always cite specific information from the documents when answering. "
+                        "If you cannot find the answer in the documents, say so clearly."
+                    ),
+                    verbose=False,
+                    retriever_mode=RetrievalMode.CHUNKS,
+                )
+
+            # Request first user input
+            return InputRequiredEvent(
+                prefix="Chat initialized. Ask a question (or type 'exit' to quit): "
+            )
+
+        except Exception as e:
+            return StopEvent(
+                result={
+                    "success": False,
+                    "error": f"Failed to initialize chat: {str(e)}",
+                }
+            )
+
+    @step
+    async def process_user_response(
+        self, ev: HumanResponseEvent, ctx: Context
+    ) -> InputRequiredEvent | HumanResponseEvent | StopEvent | None:
+        """Process user input and generate response"""
+        try:
+            logger.info(f"Processing user response {ev.response}")
+            user_input = ev.response.strip()
+
+            logger.info(f"User input: {user_input}")
+
+            # Check for exit command
+            if user_input.lower() == "exit":
+                logger.info("User input is exit")
+                conversation_history = await ctx.store.get(
+                    "conversation_history", default=[]
+                )
+                return StopEvent(
+                    result={
+                        "success": True,
+                        "message": "Chat session ended.",
+                        "conversation_history": conversation_history,
+                    }
+                )
+
+            # Get session info from context
+            index_name = await ctx.store.get("index_name")
+            session_id = await ctx.store.get("session_id")
+            cache_key = f"{index_name}_{session_id}"
+
+            # Get chat engine
+            chat_engine = self.chat_engines[cache_key]
+
+            # Process query with chat engine (streaming)
+            stream_response = await chat_engine.astream_chat(user_input)
+            full_text = ""
+
+            # Emit streaming deltas to the event stream
+            async for token in stream_response.async_response_gen():
+                full_text += token
+                ctx.write_event_to_stream(ChatDeltaEvent(delta=token))
+
+            # Extract source nodes for citations
+            sources = []
+            if hasattr(stream_response, "source_nodes"):
+                for node in stream_response.source_nodes:
+                    sources.append(
+                        {
+                            "text": node.text[:200] + "..."
+                            if len(node.text) > 200
+                            else node.text,
+                            "score": node.score if hasattr(node, "score") else None,
+                            "metadata": node.metadata
+                            if hasattr(node, "metadata")
+                            else {},
+                        }
+                    )
+
+            # Update conversation history
+            conversation_history = await ctx.store.get(
+                "conversation_history", default=[]
+            )
+            conversation_history.append(
+                {
+                    "query": user_input,
+                    "response": full_text.strip()
+                    if full_text
+                    else str(stream_response),
+                    "sources": sources,
+                }
+            )
+            await ctx.store.set("conversation_history", conversation_history)
+
+            # After streaming completes, emit a summary response event to stream for frontend/main printing
+            ctx.write_event_to_stream(
+                ChatResponseEvent(
+                    response=full_text.strip() if full_text else str(stream_response),
+                    sources=sources,
+                    query=user_input,
+                )
+            )
+
+            # Prompt for next input
+            return InputRequiredEvent(
+                prefix="\nAsk another question (or type 'exit' to quit): "
+            )
+
+        except Exception as e:
+            return StopEvent(
+                result={"success": False, "error": f"Error processing query: {str(e)}"}
+            )
+
+
+upload = DocumentUploadWorkflow(timeout=None)
+chat = ChatWorkflow(timeout=None)
diff --git a/test-proj/tests/test_placeholder.py b/test-proj/tests/test_placeholder.py
new file mode 100644
index 0000000..201975f
--- /dev/null
+++ b/test-proj/tests/test_placeholder.py
@@ -0,0 +1,2 @@
+def test_placeholder():
+    pass
diff --git a/test-proj/ui/.gitignore b/test-proj/ui/.gitignore
new file mode 100644
index 0000000..31ee023
--- /dev/null
+++ b/test-proj/ui/.gitignore
@@ -0,0 +1,4 @@
+node_modules
+dist
+# uses pnpm
+pnpm-lock.yaml
diff --git a/test-proj/ui/index.html b/test-proj/ui/index.html
new file mode 100644
index 0000000..37e7c42
--- /dev/null
+++ b/test-proj/ui/index.html
@@ -0,0 +1,14 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Quick Start UI</title>
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+  </html>
+
+
diff --git a/test-proj/ui/package.json b/test-proj/ui/package.json
new file mode 100644
index 0000000..cc20ce9
--- /dev/null
+++ b/test-proj/ui/package.json
@@ -0,0 +1,41 @@
+{
+  "name": "test-proj-ui",
+  "version": "0.1.0",
+  "private": true,
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "tsc --noEmit && vite build",
+    "preview": "vite preview",
+    "lint": "tsc --noEmit",
+    "format": "prettier --write src",
+    "format-check": "prettier --check src",
+    "all-check": "pnpm i && pnpm run lint && pnpm run format-check && pnpm run build",
+    "all-fix": "pnpm i && pnpm run lint && pnpm run format && pnpm run build"
+  },
+  "dependencies": {
+    "@llamaindex/ui": "^1.0.2",
+    "@llamaindex/workflows-client": "^1.2.0",
+    "@radix-ui/themes": "^3.2.1",
+    "llama-cloud-services": "^0.3.6",
+    "lucide-react": "^0.544.0",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
+    "tw-animate-css": "^1.3.8"
+  },
+  "devDependencies": {
+    "@tailwindcss/postcss": "^4",
+    "@tailwindcss/vite": "^4.1.13",
+    "@types/node": "^20",
+    "@types/react": "^19",
+    "@types/react-dom": "^19",
+    "@vitejs/plugin-react": "^4.3.4",
+    "dotenv": "^17.2.2",
+    "eslint": "^9",
+    "prettier": "^3.6.2",
+    "tailwindcss": "^4",
+    "typescript": "^5",
+    "vite": "^5.4.8"
+  },
+  "packageManager": "pnpm@10.11.0+sha512.6540583f41cc5f628eb3d9773ecee802f4f9ef9923cc45b69890fb47991d4b092964694ec3a4f738a420c918a333062c8b925d312f42e4f0c263eb603551f977"
+}
diff --git a/test-proj/ui/postcss.config.mjs b/test-proj/ui/postcss.config.mjs
new file mode 100644
index 0000000..f3cc6d3
--- /dev/null
+++ b/test-proj/ui/postcss.config.mjs
@@ -0,0 +1,5 @@
+import tailwind from "@tailwindcss/postcss";
+
+export default {
+  plugins: [tailwind()],
+};
diff --git a/test-proj/ui/src/App.tsx b/test-proj/ui/src/App.tsx
new file mode 100644
index 0000000..6658701
--- /dev/null
+++ b/test-proj/ui/src/App.tsx
@@ -0,0 +1,14 @@
+import { ApiProvider } from "@llamaindex/ui";
+import Home from "./pages/Home";
+import { Theme } from "@radix-ui/themes";
+import { clients } from "@/libs/clients";
+
+export default function App() {
+  return (
+    <Theme>
+      <ApiProvider clients={clients}>
+        <Home />
+      </ApiProvider>
+    </Theme>
+  );
+}
diff --git a/test-proj/ui/src/components/ChatBot.tsx b/test-proj/ui/src/components/ChatBot.tsx
new file mode 100644
index 0000000..979506f
--- /dev/null
+++ b/test-proj/ui/src/components/ChatBot.tsx
@@ -0,0 +1,492 @@
+// This is a temporary chatbot component that is used to test the chatbot functionality.
+// LlamaIndex will replace it with better chatbot component.
+import { useState, useRef, useEffect, FormEvent, KeyboardEvent } from "react";
+import {
+  Send,
+  Loader2,
+  Bot,
+  User,
+  MessageSquare,
+  Trash2,
+  RefreshCw,
+} from "lucide-react";
+import {
+  Button,
+  Input,
+  ScrollArea,
+  Card,
+  CardContent,
+  cn,
+  useWorkflowTaskCreate,
+  useWorkflowTask,
+} from "@llamaindex/ui";
+import { AGENT_NAME } from "../libs/config";
+import { toHumanResponseRawEvent } from "@/libs/utils";
+
+type Role = "user" | "assistant";
+interface Message {
+  id: string;
+  role: Role;
+  content: string;
+  timestamp: Date;
+  error?: boolean;
+}
+export default function ChatBot() {
+  const { createTask } = useWorkflowTaskCreate();
+  const messagesEndRef = useRef<HTMLDivElement>(null);
+  const inputRef = useRef<HTMLInputElement>(null);
+  const [messages, setMessages] = useState<Message[]>([]);
+  const [input, setInput] = useState("");
+  const [isLoading, setIsLoading] = useState(false);
+  const [handlerId, setHandlerId] = useState<string | null>(null);
+  const lastProcessedEventIndexRef = useRef<number>(0);
+  const [canSend, setCanSend] = useState<boolean>(false);
+  const streamingMessageIndexRef = useRef<number | null>(null);
+
+  // Deployment + auth setup
+  const deployment = AGENT_NAME || "document-qa";
+  const platformToken = (import.meta as any).env?.VITE_LLAMA_CLOUD_API_KEY as
+    | string
+    | undefined;
+  const projectId = (import.meta as any).env?.VITE_LLAMA_DEPLOY_PROJECT_ID as
+    | string
+    | undefined;
+  const defaultIndexName =
+    (import.meta as any).env?.VITE_DEFAULT_INDEX_NAME || "document_qa_index";
+  const sessionIdRef = useRef<string>(
+    `chat-${Math.random().toString(36).slice(2)}-${Date.now()}`,
+  );
+
+  // UI text defaults
+  const title = "AI Document Assistant";
+  const placeholder = "Ask me anything about your documents...";
+  const welcomeMessage =
+    "Welcome! 👋 Upload a document with the control above, then ask questions here.";
+
+  // Helper functions for message management
+  const appendMessage = (role: Role, msg: string): void => {
+    setMessages((prev) => {
+      const id = `${role}-stream-${Date.now()}`;
+      const idx = prev.length;
+      streamingMessageIndexRef.current = idx;
+      return [
+        ...prev,
+        {
+          id,
+          role,
+          content: msg,
+          timestamp: new Date(),
+        },
+      ];
+    });
+  };
+
+  const updateMessage = (index: number, message: string) => {
+    setMessages((prev) => {
+      if (index < 0 || index >= prev.length) return prev;
+      const copy = [...prev];
+      const existing = copy[index];
+      copy[index] = { ...existing, content: message };
+      return copy;
+    });
+  };
+
+  // Initialize with welcome message
+  useEffect(() => {
+    if (messages.length === 0) {
+      const welcomeMsg: Message = {
+        id: "welcome",
+        role: "assistant",
+        content: welcomeMessage,
+        timestamp: new Date(),
+      };
+      setMessages([welcomeMsg]);
+    }
+  }, []);
+
+  // Create chat task on init
+  useEffect(() => {
+    (async () => {
+      if (!handlerId) {
+        const handler = await createTask("chat", {
+          index_name: defaultIndexName,
+          session_id: sessionIdRef.current,
+        });
+        setHandlerId(handler.handler_id);
+      }
+    })();
+  }, []);
+
+  // Subscribe to task/events using hook (auto stream when handler exists)
+  const { events } = useWorkflowTask(handlerId ?? "", Boolean(handlerId));
+
+  // Process streamed events into messages
+  useEffect(() => {
+    if (!events || events.length === 0) return;
+    let startIdx = lastProcessedEventIndexRef.current;
+    if (startIdx < 0) startIdx = 0;
+    if (startIdx >= events.length) return;
+
+    for (let i = startIdx; i < events.length; i++) {
+      const ev: any = events[i];
+      const type = ev?.type as string | undefined;
+      const rawData = ev?.data as any;
+      if (!type) continue;
+      const data = (rawData && (rawData._data ?? rawData)) as any;
+
+      if (type.includes("ChatDeltaEvent")) {
+        const delta: string = data?.delta ?? "";
+        if (!delta) continue;
+        if (streamingMessageIndexRef.current === null) {
+          appendMessage("assistant", delta);
+        } else {
+          const idx = streamingMessageIndexRef.current;
+          const current = messages[idx!]?.content ?? "";
+          if (current === "Thinking...") {
+            updateMessage(idx!, delta);
+          } else {
+            updateMessage(idx!, current + delta);
+          }
+        }
+      } else if (type.includes("ChatResponseEvent")) {
+        // finalize current stream
+        streamingMessageIndexRef.current = null;
+      } else if (type.includes("InputRequiredEvent")) {
+        // ready for next user input; enable send
+        setCanSend(true);
+        setIsLoading(false);
+        inputRef.current?.focus();
+      } else if (type.includes("StopEvent")) {
+        // finished; no summary bubble needed (chat response already streamed)
+      }
+    }
+    lastProcessedEventIndexRef.current = events.length;
+  }, [events, messages]);
+
+  const scrollToBottom = () => {
+    messagesEndRef.current?.scrollIntoView({ behavior: "smooth" });
+  };
+
+  useEffect(() => {
+    scrollToBottom();
+  }, [messages]);
+
+  // No manual SSE cleanup needed
+
+  const getCommonHeaders = () => ({
+    ...(platformToken ? { authorization: `Bearer ${platformToken}` } : {}),
+    ...(projectId ? { "Project-Id": projectId } : {}),
+  });
+
+  const startChatIfNeeded = async (): Promise<string> => {
+    if (handlerId) return handlerId;
+    const handler = await createTask("chat", {
+      index_name: defaultIndexName,
+      session_id: sessionIdRef.current,
+    });
+    setHandlerId(handler.handler_id);
+    return handler.handler_id;
+  };
+
+  // Removed manual SSE ensureEventStream; hook handles streaming
+
+  const handleSubmit = async (e: FormEvent) => {
+    e.preventDefault();
+
+    const trimmedInput = input.trim();
+    if (!trimmedInput || isLoading || !canSend) return;
+
+    // Add user message
+    const userMessage: Message = {
+      id: `user-${Date.now()}`,
+      role: "user",
+      content: trimmedInput,
+      timestamp: new Date(),
+    };
+
+    const newMessages = [...messages, userMessage];
+    setMessages(newMessages);
+    setInput("");
+    setIsLoading(true);
+    setCanSend(false);
+
+    // Immediately create an assistant placeholder to avoid visual gap before deltas
+    if (streamingMessageIndexRef.current === null) {
+      appendMessage("assistant", "Thinking...");
+    }
+
+    try {
+      // Ensure chat handler exists (created on init)
+      const hid = await startChatIfNeeded();
+
+      // Send user input as HumanResponseEvent
+      const postRes = await fetch(`/deployments/${deployment}/events/${hid}`, {
+        method: "POST",
+        headers: {
+          "Content-Type": "application/json",
+          ...getCommonHeaders(),
+        },
+        body: JSON.stringify({
+          event: JSON.stringify(toHumanResponseRawEvent(trimmedInput)),
+        }),
+      });
+      if (!postRes.ok) {
+        throw new Error(
+          `Failed to send message: ${postRes.status} ${postRes.statusText}`,
+        );
+      }
+
+      // The assistant reply will be streamed by useWorkflowTask and appended incrementally
+    } catch (err) {
+      console.error("Chat error:", err);
+
+      // Add error message
+      const errorMessage: Message = {
+        id: `error-${Date.now()}`,
+        role: "assistant",
+        content: `Sorry, I encountered an error: ${err instanceof Error ? err.message : "Unknown error"}. Please try again.`,
+        timestamp: new Date(),
+        error: true,
+      };
+
+      setMessages((prev) => [...prev, errorMessage]);
+    } finally {
+      setIsLoading(false);
+      // Focus back on input
+      inputRef.current?.focus();
+    }
+  };
+
+  const handleKeyDown = (e: KeyboardEvent<HTMLInputElement>) => {
+    // Submit on Enter (without Shift)
+    if (e.key === "Enter" && !e.shiftKey) {
+      e.preventDefault();
+      handleSubmit(e as any);
+    }
+  };
+
+  const clearChat = () => {
+    setMessages([
+      {
+        id: "welcome",
+        role: "assistant" as const,
+        content: welcomeMessage,
+        timestamp: new Date(),
+      },
+    ]);
+    setInput("");
+    inputRef.current?.focus();
+  };
+
+  const retryLastMessage = () => {
+    const lastUserMessage = messages.filter((m) => m.role === "user").pop();
+    if (lastUserMessage) {
+      // Remove the last assistant message if it was an error
+      const lastMessage = messages[messages.length - 1];
+      if (lastMessage.role === "assistant" && lastMessage.error) {
+        setMessages((prev) => prev.slice(0, -1));
+      }
+      setInput(lastUserMessage.content);
+      inputRef.current?.focus();
+    }
+  };
+
+  return (
+    <div
+      className={cn(
+        "flex flex-col h-full bg-white dark:bg-gray-800 rounded-lg shadow-lg",
+      )}
+    >
+      {/* Header */}
+      <div className="px-4 py-3 border-b dark:border-gray-700">
+        <div className="flex items-center justify-between">
+          <div className="flex items-center gap-2">
+            <MessageSquare className="w-5 h-5 text-blue-600 dark:text-blue-400" />
+            <h3 className="font-semibold text-gray-900 dark:text-white">
+              {title}
+            </h3>
+            {isLoading && (
+              <span className="text-xs text-gray-500 dark:text-gray-400">
+                Thinking...
+              </span>
+            )}
+          </div>
+          <div className="flex items-center gap-2">
+            {messages.some((m) => m.error) && (
+              <button
+                onClick={retryLastMessage}
+                className="p-1.5 text-gray-500 hover:text-gray-700 dark:text-gray-400 dark:hover:text-gray-200 hover:bg-gray-100 dark:hover:bg-gray-700 rounded"
+                title="Retry last message"
+              >
+                <RefreshCw className="w-4 h-4" />
+              </button>
+            )}
+            {messages.length > 0 && (
+              <button
+                onClick={clearChat}
+                className="p-1.5 text-gray-500 hover:text-gray-700 dark:text-gray-400 dark:hover:text-gray-200 hover:bg-gray-100 dark:hover:bg-gray-700 rounded"
+                title="Clear chat"
+              >
+                <Trash2 className="w-4 h-4" />
+              </button>
+            )}
+          </div>
+        </div>
+      </div>
+
+      {/* Messages */}
+      <ScrollArea className="flex-1 p-4 overflow-y-auto">
+        {messages.length === 0 ? (
+          <div className="flex items-center justify-center h-full min-h-[300px]">
+            <div className="text-center">
+              <Bot className="w-12 h-12 text-gray-400 dark:text-gray-600 mx-auto mb-3" />
+              <p className="text-gray-500 dark:text-gray-400 mb-2">
+                No messages yet
+              </p>
+              <p className="text-sm text-gray-400 dark:text-gray-500">
+                Start a conversation!
+              </p>
+            </div>
+          </div>
+        ) : (
+          <div className="space-y-4">
+            {messages.map((message) => (
+              <div
+                key={message.id}
+                className={cn(
+                  "flex gap-3",
+                  message.role === "user" ? "justify-end" : "justify-start",
+                )}
+              >
+                {message.role !== "user" && (
+                  <div
+                    className={cn(
+                      "w-8 h-8 rounded-full flex items-center justify-center flex-shrink-0",
+                      message.error
+                        ? "bg-red-100 dark:bg-red-900"
+                        : "bg-blue-100 dark:bg-blue-900",
+                    )}
+                  >
+                    <Bot
+                      className={cn(
+                        "w-5 h-5",
+                        message.error
+                          ? "text-red-600 dark:text-red-400"
+                          : "text-blue-600 dark:text-blue-400",
+                      )}
+                    />
+                  </div>
+                )}
+                <div
+                  className={cn(
+                    "max-w-[70%]",
+                    message.role === "user" ? "order-1" : "order-2",
+                  )}
+                >
+                  <Card
+                    className={cn(
+                      "py-0",
+                      message.role === "user"
+                        ? "bg-blue-600 text-white border-blue-600"
+                        : message.error
+                          ? "bg-red-50 dark:bg-red-900/20 border-red-200 dark:border-red-800"
+                          : "bg-gray-50 dark:bg-gray-700",
+                    )}
+                  >
+                    <CardContent className="p-3">
+                      <p
+                        className={cn(
+                          "whitespace-pre-wrap text-sm",
+                          message.error && "text-red-700 dark:text-red-400",
+                        )}
+                      >
+                        {message.content}
+                      </p>
+                      <p
+                        className={cn(
+                          "text-xs mt-1 opacity-70",
+                          message.role === "user"
+                            ? "text-blue-100"
+                            : message.error
+                              ? "text-red-500 dark:text-red-400"
+                              : "text-gray-500 dark:text-gray-400",
+                        )}
+                      >
+                        {message.timestamp.toLocaleTimeString()}
+                      </p>
+                    </CardContent>
+                  </Card>
+                </div>
+                {message.role === "user" && (
+                  <div className="w-8 h-8 rounded-full bg-gray-100 dark:bg-gray-800 flex items-center justify-center flex-shrink-0 order-2">
+                    <User className="w-5 h-5 text-gray-600 dark:text-gray-400" />
+                  </div>
+                )}
+              </div>
+            ))}
+
+            {isLoading && (
+              <div className="flex gap-3 justify-start">
+                <div className="w-8 h-8 rounded-full bg-blue-100 dark:bg-blue-900 flex items-center justify-center">
+                  <Bot className="w-5 h-5 text-blue-600 dark:text-blue-400" />
+                </div>
+                <Card className="bg-gray-50 dark:bg-gray-700 py-0">
+                  <CardContent className="p-3">
+                    <div className="flex items-center gap-2">
+                      <div className="flex gap-1">
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "0ms" }}
+                        ></span>
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "150ms" }}
+                        ></span>
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "300ms" }}
+                        ></span>
+                      </div>
+                    </div>
+                  </CardContent>
+                </Card>
+              </div>
+            )}
+            <div ref={messagesEndRef} />
+          </div>
+        )}
+      </ScrollArea>
+
+      {/* Input */}
+      <div className="border-t dark:border-gray-700 p-4">
+        <form onSubmit={handleSubmit} className="flex gap-2">
+          <Input
+            ref={inputRef}
+            value={input}
+            onChange={(e) => setInput(e.target.value)}
+            onKeyDown={handleKeyDown}
+            placeholder={placeholder}
+            disabled={isLoading}
+            className="flex-1"
+            autoFocus
+          />
+          <Button
+            type="submit"
+            disabled={!canSend || isLoading || !input.trim()}
+            size="icon"
+            title="Send message"
+          >
+            {!canSend || isLoading ? (
+              <Loader2 className="w-4 h-4 animate-spin" />
+            ) : (
+              <Send className="w-4 h-4" />
+            )}
+          </Button>
+        </form>
+        <p className="text-xs text-gray-400 dark:text-gray-500 mt-2">
+          Press Enter to send • Shift+Enter for new line
+        </p>
+      </div>
+    </div>
+  );
+}
diff --git a/test-proj/ui/src/index.css b/test-proj/ui/src/index.css
new file mode 100644
index 0000000..d8e401f
--- /dev/null
+++ b/test-proj/ui/src/index.css
@@ -0,0 +1,120 @@
+@import "tailwindcss";
+@import "tw-animate-css";
+
+@custom-variant dark (&:is(.dark *));
+
+@theme inline {
+  --radius-sm: calc(var(--radius) - 4px);
+  --radius-md: calc(var(--radius) - 2px);
+  --radius-lg: var(--radius);
+  --radius-xl: calc(var(--radius) + 4px);
+  --color-background: var(--background);
+  --color-foreground: var(--foreground);
+  --color-card: var(--card);
+  --color-card-foreground: var(--card-foreground);
+  --color-popover: var(--popover);
+  --color-popover-foreground: var(--popover-foreground);
+  --color-primary: var(--primary);
+  --color-primary-foreground: var(--primary-foreground);
+  --color-secondary: var(--secondary);
+  --color-secondary-foreground: var(--secondary-foreground);
+  --color-muted: var(--muted);
+  --color-muted-foreground: var(--muted-foreground);
+  --color-accent: var(--accent);
+  --color-accent-foreground: var(--accent-foreground);
+  --color-destructive: var(--destructive);
+  --color-border: var(--border);
+  --color-input: var(--input);
+  --color-ring: var(--ring);
+  --color-chart-1: var(--chart-1);
+  --color-chart-2: var(--chart-2);
+  --color-chart-3: var(--chart-3);
+  --color-chart-4: var(--chart-4);
+  --color-chart-5: var(--chart-5);
+  --color-sidebar: var(--sidebar);
+  --color-sidebar-foreground: var(--sidebar-foreground);
+  --color-sidebar-primary: var(--sidebar-primary);
+  --color-sidebar-primary-foreground: var(--sidebar-primary-foreground);
+  --color-sidebar-accent: var(--sidebar-accent);
+  --color-sidebar-accent-foreground: var(--sidebar-accent-foreground);
+  --color-sidebar-border: var(--sidebar-border);
+  --color-sidebar-ring: var(--sidebar-ring);
+}
+
+:root {
+  --radius: 0.625rem;
+  --card: oklch(1 0 0);
+  --card-foreground: oklch(0.141 0.005 285.823);
+  --popover: oklch(1 0 0);
+  --popover-foreground: oklch(0.141 0.005 285.823);
+  --primary: oklch(0.21 0.006 285.885);
+  --primary-foreground: oklch(0.985 0 0);
+  --secondary: oklch(0.967 0.001 286.375);
+  --secondary-foreground: oklch(0.21 0.006 285.885);
+  --muted: oklch(0.967 0.001 286.375);
+  --muted-foreground: oklch(0.552 0.016 285.938);
+  --accent: oklch(0.967 0.001 286.375);
+  --accent-foreground: oklch(0.21 0.006 285.885);
+  --destructive: oklch(0.577 0.245 27.325);
+  --border: oklch(0.92 0.004 286.32);
+  --input: oklch(0.92 0.004 286.32);
+  --ring: oklch(0.705 0.015 286.067);
+  --chart-1: oklch(0.646 0.222 41.116);
+  --chart-2: oklch(0.6 0.118 184.704);
+  --chart-3: oklch(0.398 0.07 227.392);
+  --chart-4: oklch(0.828 0.189 84.429);
+  --chart-5: oklch(0.769 0.188 70.08);
+  --sidebar: oklch(0.985 0 0);
+  --sidebar-foreground: oklch(0.141 0.005 285.823);
+  --sidebar-primary: oklch(0.21 0.006 285.885);
+  --sidebar-primary-foreground: oklch(0.985 0 0);
+  --sidebar-accent: oklch(0.967 0.001 286.375);
+  --sidebar-accent-foreground: oklch(0.21 0.006 285.885);
+  --sidebar-border: oklch(0.92 0.004 286.32);
+  --sidebar-ring: oklch(0.705 0.015 286.067);
+  --background: oklch(1 0 0);
+  --foreground: oklch(0.141 0.005 285.823);
+}
+
+.dark {
+  --background: oklch(0.141 0.005 285.823);
+  --foreground: oklch(0.985 0 0);
+  --card: oklch(0.21 0.006 285.885);
+  --card-foreground: oklch(0.985 0 0);
+  --popover: oklch(0.21 0.006 285.885);
+  --popover-foreground: oklch(0.985 0 0);
+  --primary: oklch(0.92 0.004 286.32);
+  --primary-foreground: oklch(0.21 0.006 285.885);
+  --secondary: oklch(0.274 0.006 286.033);
+  --secondary-foreground: oklch(0.985 0 0);
+  --muted: oklch(0.274 0.006 286.033);
+  --muted-foreground: oklch(0.705 0.015 286.067);
+  --accent: oklch(0.274 0.006 286.033);
+  --accent-foreground: oklch(0.985 0 0);
+  --destructive: oklch(0.704 0.191 22.216);
+  --border: oklch(1 0 0 / 10%);
+  --input: oklch(1 0 0 / 15%);
+  --ring: oklch(0.552 0.016 285.938);
+  --chart-1: oklch(0.488 0.243 264.376);
+  --chart-2: oklch(0.696 0.17 162.48);
+  --chart-3: oklch(0.769 0.188 70.08);
+  --chart-4: oklch(0.627 0.265 303.9);
+  --chart-5: oklch(0.645 0.246 16.439);
+  --sidebar: oklch(0.21 0.006 285.885);
+  --sidebar-foreground: oklch(0.985 0 0);
+  --sidebar-primary: oklch(0.488 0.243 264.376);
+  --sidebar-primary-foreground: oklch(0.985 0 0);
+  --sidebar-accent: oklch(0.274 0.006 286.033);
+  --sidebar-accent-foreground: oklch(0.985 0 0);
+  --sidebar-border: oklch(1 0 0 / 10%);
+  --sidebar-ring: oklch(0.552 0.016 285.938);
+}
+
+@layer base {
+  * {
+    @apply border-border outline-ring/50;
+  }
+  body {
+    @apply bg-background text-foreground;
+  }
+}
diff --git a/test-proj/ui/src/libs/clients.ts b/test-proj/ui/src/libs/clients.ts
new file mode 100644
index 0000000..f6d521c
--- /dev/null
+++ b/test-proj/ui/src/libs/clients.ts
@@ -0,0 +1,39 @@
+import {
+  ApiClients,
+  cloudApiClient,
+  createWorkflowClient,
+  createWorkflowConfig,
+} from "@llamaindex/ui";
+import { AGENT_NAME } from "./config";
+
+const platformToken = import.meta.env.VITE_LLAMA_CLOUD_API_KEY;
+const apiBaseUrl = import.meta.env.VITE_LLAMA_CLOUD_BASE_URL;
+const projectId = import.meta.env.VITE_LLAMA_DEPLOY_PROJECT_ID;
+
+// Configure the platform client
+cloudApiClient.setConfig({
+  ...(apiBaseUrl && { baseUrl: apiBaseUrl }),
+  headers: {
+    // optionally use a backend API token scoped to a project. For local development,
+    ...(platformToken && { authorization: `Bearer ${platformToken}` }),
+    // This header is required for requests to correctly scope to the agent's project
+    // when authenticating with a user cookie
+    ...(projectId && { "Project-Id": projectId }),
+  },
+});
+
+const workflowsClient = createWorkflowClient(
+  createWorkflowConfig({
+    baseUrl: `/deployments/${AGENT_NAME}/`,
+    headers: {
+      ...(platformToken && { authorization: `Bearer ${platformToken}` }),
+    },
+  }),
+);
+
+const clients: ApiClients = {
+  workflowsClient: workflowsClient,
+  cloudApiClient: cloudApiClient,
+};
+
+export { clients };
diff --git a/ui/src/libs/config.ts b/test-proj/ui/src/libs/config.ts
similarity index 54%
rename from ui/src/libs/config.ts
rename to test-proj/ui/src/libs/config.ts
index 87ce41f..fec32d8 100644
--- a/ui/src/libs/config.ts
+++ b/test-proj/ui/src/libs/config.ts
@@ -1,2 +1,2 @@
-export const APP_TITLE = "Test Project";
-export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
\ No newline at end of file
+export const APP_TITLE = "Test Proj";
+export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
diff --git a/test-proj/ui/src/libs/utils.ts b/test-proj/ui/src/libs/utils.ts
new file mode 100644
index 0000000..a710e76
--- /dev/null
+++ b/test-proj/ui/src/libs/utils.ts
@@ -0,0 +1,7 @@
+export function toHumanResponseRawEvent(str: string) {
+  return {
+    __is_pydantic: true,
+    value: { _data: { response: str } },
+    qualified_name: "workflows.events.HumanResponseEvent",
+  };
+}
diff --git a/test-proj/ui/src/main.tsx b/test-proj/ui/src/main.tsx
new file mode 100644
index 0000000..ca19892
--- /dev/null
+++ b/test-proj/ui/src/main.tsx
@@ -0,0 +1,11 @@
+import React from "react";
+import ReactDOM from "react-dom/client";
+import App from "./App";
+import "@llamaindex/ui/styles.css";
+import "./index.css";
+
+ReactDOM.createRoot(document.getElementById("root")!).render(
+  <React.StrictMode>
+    <App />
+  </React.StrictMode>,
+);
diff --git a/test-proj/ui/src/pages/Home.tsx b/test-proj/ui/src/pages/Home.tsx
new file mode 100644
index 0000000..89208a0
--- /dev/null
+++ b/test-proj/ui/src/pages/Home.tsx
@@ -0,0 +1,48 @@
+import ChatBot from "../components/ChatBot";
+import { WorkflowTrigger } from "@llamaindex/ui";
+import { APP_TITLE } from "../libs/config";
+
+export default function Home() {
+  return (
+    <div className="min-h-screen bg-gray-50 dark:bg-gray-900 p-6">
+      <div className="max-w-7xl mx-auto">
+        {/* Header */}
+        <header className="mb-8">
+          <h1 className="text-3xl font-bold text-gray-900 dark:text-white">
+            {APP_TITLE}
+          </h1>
+          <p className="text-gray-600 dark:text-gray-400 mt-2">
+            Upload documents and ask questions about them
+          </p>
+        </header>
+
+        <div>
+          <div className="flex mb-4">
+            <WorkflowTrigger
+              workflowName="upload"
+              inputFields={[
+                {
+                  key: "index_name",
+                  label: "Index Name",
+                  placeholder: "e.g. document_qa_index",
+                  required: true,
+                },
+              ]}
+              customWorkflowInput={(files, fieldValues) => {
+                return {
+                  file_id: files[0].fileId,
+                  index_name: fieldValues.index_name,
+                };
+              }}
+            />
+          </div>
+          <div>
+            <div className="h-[700px]">
+              <ChatBot />
+            </div>
+          </div>
+        </div>
+      </div>
+    </div>
+  );
+}
diff --git a/test-proj/ui/src/vite-env.d.ts b/test-proj/ui/src/vite-env.d.ts
new file mode 100644
index 0000000..25ad5bc
--- /dev/null
+++ b/test-proj/ui/src/vite-env.d.ts
@@ -0,0 +1,15 @@
+/// <reference types="vite/client" />
+
+interface ImportMetaEnv {
+  readonly VITE_LLAMA_CLOUD_API_KEY?: string;
+  readonly VITE_LLAMA_CLOUD_BASE_URL?: string;
+
+  // injected from llama_deploy
+  readonly VITE_LLAMA_DEPLOY_BASE_PATH: string;
+  readonly VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME: string;
+  readonly VITE_LLAMA_DEPLOY_PROJECT_ID: string;
+}
+
+interface ImportMeta {
+  readonly env: ImportMetaEnv;
+}
diff --git a/test-proj/ui/tsconfig.json b/test-proj/ui/tsconfig.json
new file mode 100644
index 0000000..099ed9d
--- /dev/null
+++ b/test-proj/ui/tsconfig.json
@@ -0,0 +1,22 @@
+{
+  "compilerOptions": {
+    "target": "ES2020",
+    "lib": ["ES2020", "DOM", "DOM.Iterable"],
+    "allowJs": true,
+    "skipLibCheck": true,
+    "strict": true,
+    "esModuleInterop": true,
+    "module": "ESNext",
+    "moduleResolution": "Bundler",
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "noEmit": true,
+    "jsx": "react-jsx",
+    "types": ["vite/client"],
+    "baseUrl": ".",
+    "paths": {
+      "@/*": ["src/*"]
+    }
+  },
+  "include": ["src"]
+}
diff --git a/test-proj/ui/vite.config.ts b/test-proj/ui/vite.config.ts
new file mode 100644
index 0000000..966a1d5
--- /dev/null
+++ b/test-proj/ui/vite.config.ts
@@ -0,0 +1,49 @@
+import { defineConfig } from "vite";
+import react from "@vitejs/plugin-react";
+import path from "path";
+import dotenv from "dotenv";
+
+dotenv.config({ path: '../.env' });
+
+// https://vitejs.dev/config/
+export default defineConfig(({}) => {
+  const deploymentId = process.env.LLAMA_DEPLOY_DEPLOYMENT_URL_ID;
+  const basePath = process.env.LLAMA_DEPLOY_DEPLOYMENT_BASE_PATH;
+  const projectId = process.env.LLAMA_DEPLOY_PROJECT_ID;
+  const port = process.env.PORT ? Number(process.env.PORT) : 3000;
+  const baseUrl = process.env.LLAMA_CLOUD_BASE_URL;
+  const apiKey = process.env.LLAMA_CLOUD_API_KEY;
+
+  return {
+    plugins: [react()],
+    resolve: {
+      alias: {
+        "@": path.resolve(__dirname, "./src"),
+      },
+    },
+    server: {
+      port: port,
+      host: true,
+    },
+    build: {
+      outDir: "dist",
+      sourcemap: true,
+    },
+    base: basePath,
+    define: {
+      "import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME":
+        JSON.stringify(deploymentId),
+      "import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_BASE_PATH": JSON.stringify(basePath),
+      ...(projectId && {
+        "import.meta.env.VITE_LLAMA_DEPLOY_PROJECT_ID":
+          JSON.stringify(projectId),
+      }),
+      ...(baseUrl && {
+        "import.meta.env.VITE_LLAMA_CLOUD_BASE_URL": JSON.stringify(baseUrl),
+      }),
+      ...(apiKey && {
+        "import.meta.env.VITE_LLAMA_CLOUD_API_KEY": JSON.stringify(apiKey),
+      }),
+    },
+  };
+});
diff --git a/ui/package.json.jinja b/ui/package.json.jinja
index e5d90d4..36904ec 100644
--- a/ui/package.json.jinja
+++ b/ui/package.json.jinja
@@ -5,14 +5,19 @@
   "type": "module",
   "scripts": {
     "dev": "vite",
-    "build": "tsc -b && vite build",
-    "preview": "vite preview"
+    "build": "tsc --noEmit && vite build",
+    "preview": "vite preview",
+    "lint": "tsc --noEmit",
+    "format": "prettier --write src",
+    "format-check": "prettier --check src",
+    "all-check": "pnpm i && pnpm run lint && pnpm run format-check && pnpm run build",
+    "all-fix": "pnpm i && pnpm run lint && pnpm run format && pnpm run build"
   },
   "dependencies": {
     "@llamaindex/ui": "^1.0.2",
     "@llamaindex/workflows-client": "^1.2.0",
-    "llama-cloud-services": "^0.3.6",
     "@radix-ui/themes": "^3.2.1",
+    "llama-cloud-services": "^0.3.6",
     "lucide-react": "^0.544.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
@@ -27,6 +32,7 @@
     "@vitejs/plugin-react": "^4.3.4",
     "dotenv": "^17.2.2",
     "eslint": "^9",
+    "prettier": "^3.6.2",
     "tailwindcss": "^4",
     "typescript": "^5",
     "vite": "^5.4.8"
diff --git a/ui/src/App.tsx b/ui/src/App.tsx
index a52a680..6658701 100644
--- a/ui/src/App.tsx
+++ b/ui/src/App.tsx
@@ -10,5 +10,5 @@ export default function App() {
         <Home />
       </ApiProvider>
     </Theme>
-  )
-}
\ No newline at end of file
+  );
+}
diff --git a/ui/src/components/ChatBot.tsx b/ui/src/components/ChatBot.tsx
index f3af441..979506f 100644
--- a/ui/src/components/ChatBot.tsx
+++ b/ui/src/components/ChatBot.tsx
@@ -1,8 +1,25 @@
 // This is a temporary chatbot component that is used to test the chatbot functionality.
 // LlamaIndex will replace it with better chatbot component.
 import { useState, useRef, useEffect, FormEvent, KeyboardEvent } from "react";
-import { Send, Loader2, Bot, User, MessageSquare, Trash2, RefreshCw } from "lucide-react";
-import { Button, Input, ScrollArea, Card, CardContent, cn, useWorkflowTaskCreate, useWorkflowTask } from "@llamaindex/ui";
+import {
+  Send,
+  Loader2,
+  Bot,
+  User,
+  MessageSquare,
+  Trash2,
+  RefreshCw,
+} from "lucide-react";
+import {
+  Button,
+  Input,
+  ScrollArea,
+  Card,
+  CardContent,
+  cn,
+  useWorkflowTaskCreate,
+  useWorkflowTask,
+} from "@llamaindex/ui";
 import { AGENT_NAME } from "../libs/config";
 import { toHumanResponseRawEvent } from "@/libs/utils";
 
@@ -28,19 +45,27 @@ export default function ChatBot() {
 
   // Deployment + auth setup
   const deployment = AGENT_NAME || "document-qa";
-  const platformToken = (import.meta as any).env?.VITE_LLAMA_CLOUD_API_KEY as string | undefined;
-  const projectId = (import.meta as any).env?.VITE_LLAMA_DEPLOY_PROJECT_ID as string | undefined;
-  const defaultIndexName = (import.meta as any).env?.VITE_DEFAULT_INDEX_NAME || "document_qa_index";
-  const sessionIdRef = useRef<string>(`chat-${Math.random().toString(36).slice(2)}-${Date.now()}`);
+  const platformToken = (import.meta as any).env?.VITE_LLAMA_CLOUD_API_KEY as
+    | string
+    | undefined;
+  const projectId = (import.meta as any).env?.VITE_LLAMA_DEPLOY_PROJECT_ID as
+    | string
+    | undefined;
+  const defaultIndexName =
+    (import.meta as any).env?.VITE_DEFAULT_INDEX_NAME || "document_qa_index";
+  const sessionIdRef = useRef<string>(
+    `chat-${Math.random().toString(36).slice(2)}-${Date.now()}`,
+  );
 
   // UI text defaults
   const title = "AI Document Assistant";
   const placeholder = "Ask me anything about your documents...";
-  const welcomeMessage = "Welcome! 👋 Upload a document with the control above, then ask questions here.";
+  const welcomeMessage =
+    "Welcome! 👋 Upload a document with the control above, then ask questions here.";
 
   // Helper functions for message management
   const appendMessage = (role: Role, msg: string): void => {
-    setMessages(prev => {
+    setMessages((prev) => {
       const id = `${role}-stream-${Date.now()}`;
       const idx = prev.length;
       streamingMessageIndexRef.current = idx;
@@ -57,7 +82,7 @@ export default function ChatBot() {
   };
 
   const updateMessage = (index: number, message: string) => {
-    setMessages(prev => {
+    setMessages((prev) => {
       if (index < 0 || index >= prev.length) return prev;
       const copy = [...prev];
       const existing = copy[index];
@@ -73,7 +98,7 @@ export default function ChatBot() {
         id: "welcome",
         role: "assistant",
         content: welcomeMessage,
-        timestamp: new Date()
+        timestamp: new Date(),
       };
       setMessages([welcomeMsg]);
     }
@@ -176,7 +201,7 @@ export default function ChatBot() {
       id: `user-${Date.now()}`,
       role: "user",
       content: trimmedInput,
-      timestamp: new Date()
+      timestamp: new Date(),
     };
 
     const newMessages = [...messages, userMessage];
@@ -202,11 +227,13 @@ export default function ChatBot() {
           ...getCommonHeaders(),
         },
         body: JSON.stringify({
-          event: JSON.stringify(toHumanResponseRawEvent(trimmedInput))
+          event: JSON.stringify(toHumanResponseRawEvent(trimmedInput)),
         }),
       });
       if (!postRes.ok) {
-        throw new Error(`Failed to send message: ${postRes.status} ${postRes.statusText}`);
+        throw new Error(
+          `Failed to send message: ${postRes.status} ${postRes.statusText}`,
+        );
       }
 
       // The assistant reply will be streamed by useWorkflowTask and appended incrementally
@@ -219,10 +246,10 @@ export default function ChatBot() {
         role: "assistant",
         content: `Sorry, I encountered an error: ${err instanceof Error ? err.message : "Unknown error"}. Please try again.`,
         timestamp: new Date(),
-        error: true
+        error: true,
       };
 
-      setMessages(prev => [...prev, errorMessage]);
+      setMessages((prev) => [...prev, errorMessage]);
     } finally {
       setIsLoading(false);
       // Focus back on input
@@ -232,7 +259,7 @@ export default function ChatBot() {
 
   const handleKeyDown = (e: KeyboardEvent<HTMLInputElement>) => {
     // Submit on Enter (without Shift)
-    if (e.key === 'Enter' && !e.shiftKey) {
+    if (e.key === "Enter" && !e.shiftKey) {
       e.preventDefault();
       handleSubmit(e as any);
     }
@@ -244,20 +271,20 @@ export default function ChatBot() {
         id: "welcome",
         role: "assistant" as const,
         content: welcomeMessage,
-        timestamp: new Date()
-      }
+        timestamp: new Date(),
+      },
     ]);
     setInput("");
     inputRef.current?.focus();
   };
 
   const retryLastMessage = () => {
-    const lastUserMessage = messages.filter(m => m.role === "user").pop();
+    const lastUserMessage = messages.filter((m) => m.role === "user").pop();
     if (lastUserMessage) {
       // Remove the last assistant message if it was an error
       const lastMessage = messages[messages.length - 1];
       if (lastMessage.role === "assistant" && lastMessage.error) {
-        setMessages(prev => prev.slice(0, -1));
+        setMessages((prev) => prev.slice(0, -1));
       }
       setInput(lastUserMessage.content);
       inputRef.current?.focus();
@@ -265,19 +292,27 @@ export default function ChatBot() {
   };
 
   return (
-    <div className={cn("flex flex-col h-full bg-white dark:bg-gray-800 rounded-lg shadow-lg")}> 
+    <div
+      className={cn(
+        "flex flex-col h-full bg-white dark:bg-gray-800 rounded-lg shadow-lg",
+      )}
+    >
       {/* Header */}
       <div className="px-4 py-3 border-b dark:border-gray-700">
         <div className="flex items-center justify-between">
           <div className="flex items-center gap-2">
             <MessageSquare className="w-5 h-5 text-blue-600 dark:text-blue-400" />
-            <h3 className="font-semibold text-gray-900 dark:text-white">{title}</h3>
+            <h3 className="font-semibold text-gray-900 dark:text-white">
+              {title}
+            </h3>
             {isLoading && (
-              <span className="text-xs text-gray-500 dark:text-gray-400">Thinking...</span>
+              <span className="text-xs text-gray-500 dark:text-gray-400">
+                Thinking...
+              </span>
             )}
           </div>
           <div className="flex items-center gap-2">
-            {messages.some(m => m.error) && (
+            {messages.some((m) => m.error) && (
               <button
                 onClick={retryLastMessage}
                 className="p-1.5 text-gray-500 hover:text-gray-700 dark:text-gray-400 dark:hover:text-gray-200 hover:bg-gray-100 dark:hover:bg-gray-700 rounded"
@@ -320,51 +355,63 @@ export default function ChatBot() {
                 key={message.id}
                 className={cn(
                   "flex gap-3",
-                  message.role === "user" ? "justify-end" : "justify-start"
+                  message.role === "user" ? "justify-end" : "justify-start",
                 )}
               >
                 {message.role !== "user" && (
-                  <div className={cn(
-                    "w-8 h-8 rounded-full flex items-center justify-center flex-shrink-0",
-                    message.error
-                      ? "bg-red-100 dark:bg-red-900"
-                      : "bg-blue-100 dark:bg-blue-900"
-                  )}>
-                    <Bot className={cn(
-                      "w-5 h-5",
+                  <div
+                    className={cn(
+                      "w-8 h-8 rounded-full flex items-center justify-center flex-shrink-0",
                       message.error
-                        ? "text-red-600 dark:text-red-400"
-                        : "text-blue-600 dark:text-blue-400"
-                    )} />
+                        ? "bg-red-100 dark:bg-red-900"
+                        : "bg-blue-100 dark:bg-blue-900",
+                    )}
+                  >
+                    <Bot
+                      className={cn(
+                        "w-5 h-5",
+                        message.error
+                          ? "text-red-600 dark:text-red-400"
+                          : "text-blue-600 dark:text-blue-400",
+                      )}
+                    />
                   </div>
                 )}
-                <div className={cn(
-                  "max-w-[70%]",
-                  message.role === "user" ? "order-1" : "order-2"
-                )}>
-                  <Card className={cn(
-                    "py-0",
-                    message.role === "user"
-                      ? "bg-blue-600 text-white border-blue-600"
-                      : message.error
-                      ? "bg-red-50 dark:bg-red-900/20 border-red-200 dark:border-red-800"
-                      : "bg-gray-50 dark:bg-gray-700"
-                  )}>
+                <div
+                  className={cn(
+                    "max-w-[70%]",
+                    message.role === "user" ? "order-1" : "order-2",
+                  )}
+                >
+                  <Card
+                    className={cn(
+                      "py-0",
+                      message.role === "user"
+                        ? "bg-blue-600 text-white border-blue-600"
+                        : message.error
+                          ? "bg-red-50 dark:bg-red-900/20 border-red-200 dark:border-red-800"
+                          : "bg-gray-50 dark:bg-gray-700",
+                    )}
+                  >
                     <CardContent className="p-3">
-                      <p className={cn(
-                        "whitespace-pre-wrap text-sm",
-                        message.error && "text-red-700 dark:text-red-400"
-                      )}>
+                      <p
+                        className={cn(
+                          "whitespace-pre-wrap text-sm",
+                          message.error && "text-red-700 dark:text-red-400",
+                        )}
+                      >
                         {message.content}
                       </p>
-                      <p className={cn(
-                        "text-xs mt-1 opacity-70",
-                        message.role === "user"
-                          ? "text-blue-100"
-                          : message.error
-                          ? "text-red-500 dark:text-red-400"
-                          : "text-gray-500 dark:text-gray-400"
-                      )}>
+                      <p
+                        className={cn(
+                          "text-xs mt-1 opacity-70",
+                          message.role === "user"
+                            ? "text-blue-100"
+                            : message.error
+                              ? "text-red-500 dark:text-red-400"
+                              : "text-gray-500 dark:text-gray-400",
+                        )}
+                      >
                         {message.timestamp.toLocaleTimeString()}
                       </p>
                     </CardContent>
@@ -387,9 +434,18 @@ export default function ChatBot() {
                   <CardContent className="p-3">
                     <div className="flex items-center gap-2">
                       <div className="flex gap-1">
-                        <span className="w-2 h-2 bg-gray-500 rounded-full animate-bounce" style={{ animationDelay: '0ms' }}></span>
-                        <span className="w-2 h-2 bg-gray-500 rounded-full animate-bounce" style={{ animationDelay: '150ms' }}></span>
-                        <span className="w-2 h-2 bg-gray-500 rounded-full animate-bounce" style={{ animationDelay: '300ms' }}></span>
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "0ms" }}
+                        ></span>
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "150ms" }}
+                        ></span>
+                        <span
+                          className="w-2 h-2 bg-gray-500 rounded-full animate-bounce"
+                          style={{ animationDelay: "300ms" }}
+                        ></span>
                       </div>
                     </div>
                   </CardContent>
@@ -420,7 +476,7 @@ export default function ChatBot() {
             size="icon"
             title="Send message"
           >
-            {(!canSend || isLoading) ? (
+            {!canSend || isLoading ? (
               <Loader2 className="w-4 h-4 animate-spin" />
             ) : (
               <Send className="w-4 h-4" />
@@ -433,4 +489,4 @@ export default function ChatBot() {
       </div>
     </div>
   );
-}
\ No newline at end of file
+}
diff --git a/ui/src/libs/clients.ts b/ui/src/libs/clients.ts
index 192f57d..f6d521c 100644
--- a/ui/src/libs/clients.ts
+++ b/ui/src/libs/clients.ts
@@ -1,4 +1,9 @@
-import { ApiClients, cloudApiClient, createWorkflowClient, createWorkflowConfig } from "@llamaindex/ui";
+import {
+  ApiClients,
+  cloudApiClient,
+  createWorkflowClient,
+  createWorkflowConfig,
+} from "@llamaindex/ui";
 import { AGENT_NAME } from "./config";
 
 const platformToken = import.meta.env.VITE_LLAMA_CLOUD_API_KEY;
@@ -17,12 +22,14 @@ cloudApiClient.setConfig({
   },
 });
 
-const workflowsClient = createWorkflowClient(createWorkflowConfig({
-  baseUrl: `/deployments/${AGENT_NAME}/`,
-  headers: {
-    ...(platformToken && { authorization: `Bearer ${platformToken}` }),
-  }
-}));
+const workflowsClient = createWorkflowClient(
+  createWorkflowConfig({
+    baseUrl: `/deployments/${AGENT_NAME}/`,
+    headers: {
+      ...(platformToken && { authorization: `Bearer ${platformToken}` }),
+    },
+  }),
+);
 
 const clients: ApiClients = {
   workflowsClient: workflowsClient,
diff --git a/ui/src/libs/config.ts.jinja b/ui/src/libs/config.ts.jinja
index 8832fe5..acd8c84 100644
--- a/ui/src/libs/config.ts.jinja
+++ b/ui/src/libs/config.ts.jinja
@@ -1,2 +1,2 @@
-export const APP_TITLE = "{{ project_title }}"
+export const APP_TITLE = "{{ project_title }}";
 export const AGENT_NAME = import.meta.env.VITE_LLAMA_DEPLOY_DEPLOYMENT_NAME;
diff --git a/ui/src/libs/utils.ts b/ui/src/libs/utils.ts
index 183e8a2..a710e76 100644
--- a/ui/src/libs/utils.ts
+++ b/ui/src/libs/utils.ts
@@ -1,3 +1,7 @@
 export function toHumanResponseRawEvent(str: string) {
-    return { __is_pydantic: true, value: { _data: { response: str } }, qualified_name: "workflows.events.HumanResponseEvent" }
-}
\ No newline at end of file
+  return {
+    __is_pydantic: true,
+    value: { _data: { response: str } },
+    qualified_name: "workflows.events.HumanResponseEvent",
+  };
+}
diff --git a/ui/src/main.tsx b/ui/src/main.tsx
index fa6dbbf..ca19892 100644
--- a/ui/src/main.tsx
+++ b/ui/src/main.tsx
@@ -7,7 +7,5 @@ import "./index.css";
 ReactDOM.createRoot(document.getElementById("root")!).render(
   <React.StrictMode>
     <App />
-  </React.StrictMode>
+  </React.StrictMode>,
 );
-
-
diff --git a/ui/src/pages/Home.tsx b/ui/src/pages/Home.tsx
index 1a20aa2..89208a0 100644
--- a/ui/src/pages/Home.tsx
+++ b/ui/src/pages/Home.tsx
@@ -20,12 +20,14 @@ export default function Home() {
           <div className="flex mb-4">
             <WorkflowTrigger
               workflowName="upload"
-              inputFields={[{
-                key: "index_name",
-                label: "Index Name",
-                placeholder: "e.g. document_qa_index",
-                required: true,
-              }]}
+              inputFields={[
+                {
+                  key: "index_name",
+                  label: "Index Name",
+                  placeholder: "e.g. document_qa_index",
+                  required: true,
+                },
+              ]}
               customWorkflowInput={(files, fieldValues) => {
                 return {
                   file_id: files[0].fileId,
@@ -43,4 +45,4 @@ export default function Home() {
       </div>
     </div>
   );
-}
\ No newline at end of file
+}
diff --git a/ui/src/vite-env.d.ts b/ui/src/vite-env.d.ts
index 77b8ee8..25ad5bc 100644
--- a/ui/src/vite-env.d.ts
+++ b/ui/src/vite-env.d.ts
@@ -13,4 +13,3 @@ interface ImportMetaEnv {
 interface ImportMeta {
   readonly env: ImportMetaEnv;
 }
-