diff --git a/assets/config_custom_chromadb.json b/assets/config_custom_chromadb.json
index 75fa7412..ea53620c 100644
--- a/assets/config_custom_chromadb.json
+++ b/assets/config_custom_chromadb.json
@@ -7,7 +7,7 @@
     },
     "vectordb": {
         "name": "chromadb",
-        "class_name": "llm_stack",
+        "class_name": "genai_stack",
         "embedding": {
             "name": "HuggingFaceEmbeddings",
             "fields": {
diff --git a/assets/etl.json b/assets/etl.json
index 75a1a6f9..4bb3d20e 100644
--- a/assets/etl.json
+++ b/assets/etl.json
@@ -8,6 +8,6 @@
     },
     "vectordb": {
         "name": "chromadb",
-        "class_name": "llm_stack"
+        "class_name": "genai_stack"
     }
 }
diff --git a/genai_stack/__init__.py b/genai_stack/__init__.py
index d08b6917..2cb310a7 100644
--- a/genai_stack/__init__.py
+++ b/genai_stack/__init__.py
@@ -1,8 +1,8 @@
 """Top-level package for genai_stack."""
 
-__author__ = """AIM by DPhi"""
+__author__ = """AI Planet Tech Team"""
 __email__ = "support@aiplanet.com"
-__version__ = "0.2.2"
+__version__ = "0.2.3"
 
 import os
 
diff --git a/genai_stack/constant.py b/genai_stack/constant.py
index 4a63e152..0e7b405b 100644
--- a/genai_stack/constant.py
+++ b/genai_stack/constant.py
@@ -7,3 +7,4 @@
 VECTORDB = "/vectordb"
 ETL = "/etl"
 PROMPT_ENGINE = "/prompt-engine"
+MODEL = "/model"
diff --git a/genai_stack/etl/run.py b/genai_stack/etl/run.py
index c7febd65..c5b1c323 100644
--- a/genai_stack/etl/run.py
+++ b/genai_stack/etl/run.py
@@ -1,17 +1,17 @@
-from genai_stack.constants.etl.etl import PREBUILT_ETL_LOADERS, ETL_MODULE
+from genai_stack.constants.etl.etl import AVAILABLE_ETL_LOADERS, ETL_MODULE
 from genai_stack.utils.importing import import_class
 
 from genai_stack.core import ConfigLoader
 
 
 def list_etl_loaders():
-    return PREBUILT_ETL_LOADERS.keys()
+    return AVAILABLE_ETL_LOADERS.keys()
 
 
 def run_etl_loader(config_file: str, vectordb):
     config_cls = ConfigLoader(name="EtlLoader", config=config_file)
     etl_cls = import_class(
-        f"{ETL_MODULE}.{PREBUILT_ETL_LOADERS.get(config_cls.config.get('etl'))}".replace(
+        f"{ETL_MODULE}.{AVAILABLE_ETL_LOADERS.get(config_cls.config.get('etl'))}".replace(
             "/",
             ".",
         )
diff --git a/genai_stack/genai_server/models/model_models.py b/genai_stack/genai_server/models/model_models.py
new file mode 100644
index 00000000..a532c69c
--- /dev/null
+++ b/genai_stack/genai_server/models/model_models.py
@@ -0,0 +1,13 @@
+from pydantic import BaseModel
+
+
+class ModelBaseModel(BaseModel):
+    pass
+
+
+class ModelRequestModel(ModelBaseModel):
+    prompt: str
+
+
+class ModelResponseModel(ModelBaseModel):
+    output: str
diff --git a/genai_stack/genai_server/routers/model_routes.py b/genai_stack/genai_server/routers/model_routes.py
new file mode 100644
index 00000000..d3a89f61
--- /dev/null
+++ b/genai_stack/genai_server/routers/model_routes.py
@@ -0,0 +1,15 @@
+from fastapi import APIRouter
+
+from genai_stack.constant import API, MODEL
+from genai_stack.genai_server.settings.settings import settings
+from genai_stack.genai_server.services.model_service import ModelService
+from genai_stack.genai_server.models.model_models import ModelResponseModel, ModelRequestModel
+
+service = ModelService(store=settings.STORE)
+
+router = APIRouter(prefix=API + MODEL, tags=["model"])
+
+
+@router.post("/predict")
+def predict(data: ModelRequestModel) -> ModelResponseModel:
+    return service.predict(data=data)
diff --git a/genai_stack/genai_server/server.py b/genai_stack/genai_server/server.py
index 7bdee2e0..ebb695d1 100644
--- a/genai_stack/genai_server/server.py
+++ b/genai_stack/genai_server/server.py
@@ -1,6 +1,12 @@
 from fastapi import FastAPI
-
-from genai_stack.genai_server.routers import session_routes, retriever_routes, vectordb_routes, etl_routes, prompt_engine_routes
+from genai_stack.genai_server.routers import (
+    session_routes,
+    retriever_routes,
+    vectordb_routes,
+    etl_routes,
+    prompt_engine_routes,
+    model_routes,
+)
 
 
 def get_genai_server_app():
@@ -21,5 +27,6 @@ def get_genai_server_app():
     app.include_router(vectordb_routes.router)
     app.include_router(etl_routes.router)
     app.include_router(prompt_engine_routes.router)
+    app.include_router(model_routes.router)
 
     return app
diff --git a/genai_stack/genai_server/services/model_service.py b/genai_stack/genai_server/services/model_service.py
new file mode 100644
index 00000000..04d33eff
--- /dev/null
+++ b/genai_stack/genai_server/services/model_service.py
@@ -0,0 +1,13 @@
+from genai_stack.genai_platform.services.base_service import BaseService
+from genai_stack.genai_server.models.model_models import ModelRequestModel, ModelResponseModel
+from genai_stack.genai_server.utils import get_current_stack
+from genai_stack.genai_server.settings.config import stack_config
+
+
+class ModelService(BaseService):
+    def predict(self, data: ModelRequestModel) -> ModelResponseModel:
+        stack = get_current_stack(config=stack_config)
+        response = stack.model.predict(data.prompt)
+        return ModelResponseModel(
+            output=response["output"],
+        )
diff --git a/genai_stack/llm_stack.py b/genai_stack/genai_stack.py
similarity index 100%
rename from genai_stack/llm_stack.py
rename to genai_stack/genai_stack.py
diff --git a/genai_stack/model/__init__.py b/genai_stack/model/__init__.py
index 42f40b4f..fdd3eb4a 100644
--- a/genai_stack/model/__init__.py
+++ b/genai_stack/model/__init__.py
@@ -1,4 +1,3 @@
-from .server import HttpServer
 from .base import BaseModel
 from .gpt3_5 import OpenAIGpt35Model
 from .run import list_supported_models, get_model_class, AVAILABLE_MODEL_MAPS, run_custom_model
diff --git a/genai_stack/model/gpt3_5.py b/genai_stack/model/gpt3_5.py
index f68327b3..0a5efe47 100644
--- a/genai_stack/model/gpt3_5.py
+++ b/genai_stack/model/gpt3_5.py
@@ -7,30 +7,58 @@
 
 class OpenAIGpt35Parameters(BaseModelConfigModel):
     model_name: str = Field(default="gpt-3.5-turbo-16k", alias="model")
-    """Model name to use."""
+    """
+    Model name to use.
+
+    """
     temperature: float = 0
-    """What sampling temperature to use."""
+    """
+    What sampling temperature to use.
+    
+    """
     model_kwargs: Dict[str, Any] = Field(default_factory=dict)
-    """Holds any model parameters valid for `create` call not explicitly specified."""
+    """
+    Holds any model parameters valid for `create` call not explicitly specified.
+
+    """
     openai_api_key: str
-    """Base URL path for API requests, 
-    leave blank if not using a proxy or service emulator."""
+    """
+    Base URL path for API requests, 
+    leave blank if not using a proxy or service emulator.
+
+    """
     openai_api_base: Optional[str] = None
     openai_organization: Optional[str] = None
     # to support explicit proxy for OpenAI
     openai_proxy: Optional[str] = None
     request_timeout: Optional[Union[float, Tuple[float, float]]] = None
-    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""
+    """
+    Timeout for requests to OpenAI completion API. Default is 600 seconds.
+
+    """
     max_retries: int = 6
-    """Maximum number of retries to make when generating."""
+    """
+    Maximum number of retries to make when generating.
+
+    """
     streaming: bool = False
-    """Whether to stream the results or not."""
+    """
+    Whether to stream the results or not.
+
+    """
     n: int = 1
-    """Number of chat completions to generate for each prompt."""
+    """
+    Number of chat completions to generate for each prompt.
+    
+    """
     max_tokens: Optional[int] = None
-    """Maximum number of tokens to generate."""
+    """
+    Maximum number of tokens to generate.
+    
+    """
     tiktoken_model_name: Optional[str] = None
-    """The model name to pass to tiktoken when using this class. 
+    """
+    The model name to pass to tiktoken when using this class. 
     Tiktoken is used to count the number of tokens in documents to constrain 
     them to be under a certain limit. By default, when set to None, this will 
     be the same as the embedding model name. However, there are some cases 
@@ -38,7 +66,9 @@ class OpenAIGpt35Parameters(BaseModelConfigModel):
     supported by tiktoken. This can include when using Azure embeddings or 
     when using one of the many model providers that expose an OpenAI-like 
     API but with different models. In those cases, in order to avoid erroring 
-    when tiktoken is called, you can specify a model name to use here."""
+    when tiktoken is called, you can specify a model name to use here.
+    
+    """
 
 
 class OpenAIGpt35ModelConfigModel(BaseModelConfigModel):
diff --git a/genai_stack/model/hf.py b/genai_stack/model/hf.py
index 2fc99ee4..95253494 100644
--- a/genai_stack/model/hf.py
+++ b/genai_stack/model/hf.py
@@ -1,6 +1,4 @@
 from typing import Optional, Dict
-
-import torch
 from langchain.llms import HuggingFacePipeline
 
 from genai_stack.model.base import BaseModel, BaseModelConfig, BaseModelConfigModel
@@ -31,18 +29,14 @@ class HuggingFaceModel(BaseModel):
     def _post_init(self, *args, **kwargs):
         self.model = self.load()
 
-    def get_device(self):
-        return torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-
     def load(self):
         model = HuggingFacePipeline.from_model_id(
-            model_id=self.config.model,
-            task=self.config.task,
-            model_kwargs=self.config.model_kwargs,
-            device=self.get_device(),
+            model_id=self.config.model, task=self.config.task, model_kwargs=self.config.model_kwargs
         )
         return model
 
     def predict(self, prompt: str):
         response = self.model(prompt)
-        return {"output": response[0]["generated_text"]}
+        # Note: Huggingface model response format is different for different model
+        # so user should extract the info which is required.
+        return {"output": response}
diff --git a/genai_stack/model/server.py b/genai_stack/model/server.py
deleted file mode 100644
index c5d4c78e..00000000
--- a/genai_stack/model/server.py
+++ /dev/null
@@ -1,86 +0,0 @@
-import uvicorn
-from fastapi import FastAPI, Request
-from fastapi.responses import Response, JSONResponse
-
-
-class HttpServer:
-    name: str = None
-
-    def predict(self, data=None):
-        print(data)
-        raise NotImplementedError
-
-    def chat_history(self):
-        raise NotImplementedError
-
-    async def predict_api(self, request: Request):
-        # Accessing request data
-        request_body = await request.body()
-
-        response_data = self.predict(request_body)
-        ResponseClass = self.response_class or JSONResponse
-        return ResponseClass(content=response_data)
-
-    async def chat_history_api(self, request: Request):
-        response_data = self.chat_history()
-        ResponseClass = self.response_class or JSONResponse
-        return ResponseClass(content=response_data)
-
-    def run_http_server(
-        self,
-        host: str = "127.0.0.1",
-        port: int = 8082,
-        response_class: Response = Response,
-    ):
-        self.response_class = response_class
-        self.app = FastAPI(
-            title="genai_stack Model Server",
-            description=f"genai_stack {self.name} HTTP Model Server",
-        )
-        app: FastAPI = self.app
-
-        app.post("/predict", response_class=response_class)(self.predict_api)
-        app.get("/chat_history", response_class=response_class)(self.chat_history_api)
-
-        uvicorn.run(app, host=host, port=port)
-
-
-# import asyncio
-
-# import uvicorn
-# from fastapi import FastAPI, Request
-# from fastapi.responses import JSONResponse
-
-# class HttpServer:
-#     def __init__(self):
-#         self.version = "0.0.1"
-
-#         self.app = FastAPI(
-#             title="genai_stack Model Server",
-#             description="genai_stack HTTP Model Server using FastAPI",
-#         )
-#         self.serving_task: Optional[asyncio.Task] = None
-
-#     async def serve(self):
-#         app: FastAPI = self.app
-
-#         @app.post("/version")
-#         async def predict(request: Request) -> JSONResponse:
-#             # Accessing request data
-#             request_body = await request.json()
-
-#             return JSONResponse(
-#                 {
-#                     "Request body": request_body,
-#                 }
-#             )
-
-#         # serve
-#         config = uvicorn.Config(app, host="127.0.0.1", port=8082)
-#         server = uvicorn.Server(config)
-#         await server.serve()
-
-
-# if __name__ == "__main__":
-#     instance = HttpServer()
-#     asyncio.run(instance.serve())
diff --git a/genai_stack/retriever/base.py b/genai_stack/retriever/base.py
index d6d0a52e..3a8b544a 100644
--- a/genai_stack/retriever/base.py
+++ b/genai_stack/retriever/base.py
@@ -6,6 +6,7 @@ class BaseRetrieverConfigModel(BaseModel):
     """
     Data Model for the configs
     """
+
     pass
 
 
@@ -16,55 +17,26 @@ class BaseRetrieverConfig(StackComponentConfig):
 class BaseRetriever(StackComponent):
     config_class = BaseRetrieverConfig
 
-    def get_prompt(self, query:str):
+    def get_prompt(self, query: str):
         """
         This method returns the prompt template from the prompt engine component
         """
         return self.mediator.get_prompt_template(query)
 
-    def retrieve(self, query:str) -> dict:
+    def retrieve(self, query: str) -> dict:
         """
         This method returns the model response for the prompt template.
         """
         raise NotImplementedError()
-    
-    def get_context(self, query:str):
+
+    def get_context(self, query: str):
         """
         This method returns the relevant documents returned by the similarity search from a vectordb based on the query
         """
         raise NotImplementedError()
-    
+
     def get_chat_history(self) -> str:
         """
         This method returns the chat conversation history
         """
         return self.mediator.get_chat_history()
-
-
-# from typing import Any
-
-# from genai_stack.core import BaseComponent
-# from genai_stack.constants.retriever import RETRIEVER_CONFIG_KEY
-# from genai_stack.vectordb.base import BaseVectordb
-
-# class BaseRetriever(BaseComponent):
-#     module_name = "BaseRetriever"
-#     config_key = RETRIEVER_CONFIG_KEY
-
-#     def __init__(self, config: str, vectordb: BaseVectordb = None):
-#         super().__init__(self.module_name, config)
-#         self.parse_config(self.config_key, self.required_fields)
-#         self.vectordb = vectordb
-
-#     def retrieve(self, query: Any):
-#         raise NotImplementedError()
-
-#     def get_langchain_retriever(self):
-#         return self.vectordb.get_langchain_client().as_retriever()
-
-#     def get_langchain_memory_retriever(self):
-#         return self.vectordb.get_langchain_memory_client().as_retriever()
-
-#     @classmethod
-#     def from_config(cls, config):
-#         raise NotImplementedError
\ No newline at end of file
diff --git a/genai_stack/retriever/langchain.py b/genai_stack/retriever/langchain.py
index 0e2f3842..6e322a15 100644
--- a/genai_stack/retriever/langchain.py
+++ b/genai_stack/retriever/langchain.py
@@ -10,6 +10,7 @@ class LangChainRetrieverConfigModel(BaseRetrieverConfigModel):
     """
     Data Model for the configs
     """
+
     pass
 
 
@@ -23,55 +24,23 @@ class LangChainRetriever(BaseRetriever):
     def retrieve(self, query: str, context: List[Document] = None):
         prompt_template = self.get_prompt(query=query)
 
-        prompt_dict = {
-            "query": query
-        }
+        prompt_dict = {"query": query}
         metadata = None
         if "context" in prompt_template.input_variables:
             if not context:
                 context = self.mediator.search_vectordb(query=query)
             metadata = context[0].metadata if context else None
-            prompt_dict['context'] = parse_search_results(context)
+            prompt_dict["context"] = parse_search_results(context)
         if "history" in prompt_template.input_variables:
-            prompt_dict['history'] = self.get_chat_history()
+            prompt_dict["history"] = self.get_chat_history()
         else:
             # Cache and memory cannot co-exist. Memory is given priority.
-            cache = self.mediator.get_cache(
-                query=query,
-                metadata=metadata
-            )
+            cache = self.mediator.get_cache(query=query, metadata=metadata)
             if cache:
-                return {'output': cache}
-        final_prompt_template = prompt_template.template.format(
-            **{k: v for k, v in prompt_dict.items()}
-        )
+                return {"output": cache}
+        final_prompt_template = prompt_template.template.format(**{k: v for k, v in prompt_dict.items()})
         response = self.mediator.get_model_response(prompt=final_prompt_template)
-        self.mediator.add_text(user_text=query, model_text=response['output'])
+        self.mediator.add_text(user_text=query, model_text=response["output"])
         if "history" not in prompt_template.input_variables:
-            self.mediator.set_cache(
-                response=response['output'],
-                query=query,
-                metadata=metadata
-            )
+            self.mediator.set_cache(response=response["output"], query=query, metadata=metadata)
         return response
-
-# from typing import List
-# from langchain.docstore.document import Document
-
-# from .base import BaseRetriever
-
-
-# class LangChainRetriever(BaseRetriever):
-#     required_fields = []
-
-#     def retrieve(self, query):
-#         vectordb = self.vectordb
-#         return self.parse_search_results(vectordb.search(query))
-
-#     def parse_search_results(self, search_results: List[Document]):
-#         result = ""
-
-#         for idx, search_result in enumerate(search_results):
-#             result += f"{idx + 1}. {search_result.page_content} \n"
-
-#         return result
diff --git a/setup.py b/setup.py
index 812e5dfd..660648ac 100644
--- a/setup.py
+++ b/setup.py
@@ -33,7 +33,7 @@
 test_requirements = []
 
 setup(
-    author="AIM by DPhi",
+    author="AI Planet Tech Team",
     author_email="support@aiplanet.com",
     python_requires=">=3.8",
     classifiers=[
@@ -88,6 +88,6 @@
     test_suite="tests",
     tests_require=test_requirements,
     url="https://github.com/aiplanethub/genai-stack",
-    version="0.2.1",
+    version="0.2.3",
     zip_safe=False,
 )
diff --git a/ui/requirements.txt b/ui/requirements.txt
index c95f5fd3..12790d66 100644
--- a/ui/requirements.txt
+++ b/ui/requirements.txt
@@ -45,7 +45,7 @@ tornado==6.3.2
 typing_extensions==4.7.1
 tzdata==2023.3
 tzlocal==4.3.1
-urllib3==2.0.4
+urllib3==2.0.6
 validators==0.20.0
 watchdog==3.0.0
 zipp==3.16.2