feat: inital gradio UI implementation

Dockerfile

@@ -26,7 +26,6 @@ ENV PORT=7860
 
 # Expose the port
 EXPOSE 7860
-
+EXPOSE 7861
 # Start command for Hugging Face Space
-# CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
-CMD ["uv", "run", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uv", "run", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -74,6 +74,27 @@ API Key: sk-template-token
 API Key saved to api_key.txt
 ```
 
+### 🔑 API Key Authentication
+
+```bash
+curl -X POST "http://localhost:8000/v1/chat/completions" \
+     -H "Authorization: Bearer sk-template-token" \
+     -H "Content-Type: application/json" \
+     -d '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Hello!"}]}'
+```
+
+## Mock Implementation
+* `USE_MOCK` environment variable is set to `true`, the API will return mock responses for all endpoints. Default is `false`.
+* `MOCK_DIR` environment variable is used to specify the directory of the mock responses, default is `resources/mock`.
+* Mock file names should be same as the module and function name like below:
+     - app/api/chat_api.py - listChatCompletions - resources/mock/`chat_api_list_chat_completions.json` - mock response for GET `/v1/chat/completions`
+     - app/api/chat_api.py - createChatCompletion - resources/mock/`chat_api_create_chat_completion.json` - mock response for POST `/v1/chat/completions`
+     - app/api/chat_api.py - getChatCompletionMessages - resources/mock/`chat_api_list_messages.json` - mock response for GET `/v1/chat/completions/{completion_id}/messages`
+     - app/api/chat_api.py - getChatCompletion - resources/mock/`chat_api_retrieve_chat_completion.json` - mock response for GET `/v1/chat/completions/{completion_id}`
+     - app/api/chat_api.py - getChatPlotByMessage - resources/mock/`chat_api_retrieve_plot.json` - mock response for GET `/v1/chat/completions/{completion_id}/messages/{message_id}/plots`
+
+
+
 ## Contributing
 When you make changes to the code, please run the following commands to ensure the code is running on your local machine and formatted and linted correctly.
 
@@ -147,22 +168,17 @@ gh pr create --base main --head feature/new-feature --title "Add new feature" --
 
 
 
-### 🔑 API Key Authentication
 
-```bash
-curl -X POST "http://localhost:8000/v1/chat/completions" \
-     -H "Authorization: Bearer sk-template-token" \
-     -H "Content-Type: application/json" \
-     -d '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Hello!"}]}'
-```
 
  ## Open Issue
+ Mock Implementation:
+ - [X] Implement Mock response for all endpoints
+ - [X] Implement API-Key Authentication and validation in all endpoints
+
+ Production Implementation:
  - [ ] POST chat/completions - create a new chat completion
  - [ ] GET  chat/completions - list stored chat completions
  - [ ] GET  chat/completions/{completion_id} - get a stored chat completion by id
  - [ ] GET  chat/completions/{completion_id}/messages - get the messages in a stored chat completion by id
  - [ ] GET  chat/completions/{completion_id}/messages/{message_id}/plots - get the plots/graph-data/figure-json in a stored chat completion by id and message id
- - [ ] Implement Mock response for all endpoints
- - [ ] Implement API-Key Authentication and validation in all endpoints
- - [ ] 
- - [ ] 
+

app/core/api_response.py

@@ -22,7 +22,7 @@ def url_to_filename(url: str, method: str) -> str:
     - Input: GET "/v1/chat/completions/{completion_id}" -> "chat_completions_id_GET.json"
     - Input: GET "/v1/chat/completions/123/messages" -> "chat_completions_id_messages_GET.json"
     """
-    logger.debug(f"BEGIN: url: {url} method: {method}")
+    logger.trace(f"BEGIN: url: {url} method: {method}")
     # Remove version prefix and leading/trailing slashes
     path = url.strip("/")
     if path.startswith("v1/"):
@@ -32,15 +32,15 @@ def url_to_filename(url: str, method: str) -> str:
     path = path.replace("{completion_id}", "id")
     path = path.replace("{message_id}", "id")
 
-    logger.debug(f"replaced path: {path}")
+    logger.trace(f"replaced path: {path}")
 
     # Convert to filename format
     filename = path.replace("/", "_")
-    logger.debug(f"filename: {filename}")
+    logger.trace(f"filename: {filename}")
 
     # convert conversations_1 to conversations with dynamic id
     final_filename= re.sub(r'[_][^/]+$', '_id', filename)
-    logger.debug(f"final_filename: {final_filename}")
+    logger.trace(f"final_filename: {final_filename}")
     
     # Add method suffix
     result = f"{final_filename}_{method}"
@@ -92,9 +92,9 @@ def api_response():
         @wraps(func)
         async def wrapper(request: Request, *args, **kwargs):
             logger.trace(f"BEGIN: wrapper: {request}")
-            logger.debug(f"func: {func.__name__}")
-            logger.debug(f"args: {args}")
-            logger.debug(f"kwargs: {kwargs}")
+            logger.trace(f"func: {func.__name__}")
+            logger.trace(f"args: {args}")
+            logger.trace(f"kwargs: {kwargs}")
             if not request:
                 logger.error("Request object not found in args or kwargs")
                 raise HTTPException(
@@ -110,7 +110,7 @@ def api_response():
             if USE_MOCK:
                 python_method_name = func.__name__
                 python_module_name = func.__module__
-                logger.warning(f"Using mock response for {request.url.path} [{request.method}]")
+                logger.warning(f"Using mock response for {request.url.path} [{request.method}] > {python_module_name}.{python_method_name}")
                 try:
                     result = get_mock_response(request.url.path, python_module_name, python_method_name)
                     logger.trace(f"Mock response: {result}")

gradio.py

@@ -0,0 +1,29 @@
+# gradio.py
+import gradio as gr
+import asyncio
+import httpx
+import environs
+
+env = environs.Env()
+env.read_env()
+
+BASE_URL = env.str("BASE_URL", "http://localhost:7860")
+API_KEY = env.str("API_KEY", "sk-test-xxx")
+
+CHAT_API_ENDPOINT = f"{BASE_URL}/v1/chat/completions"
+
+async def call_chat_api(user_input):
+    headers = {"Authorization": f"sk-{API_KEY}"}
+    payload = {
+        "messages": [{"role": "user", "content": user_input}]
+    }
+    async with httpx.AsyncClient() as client:
+        response = await client.post(CHAT_API_ENDPOINT, json=payload, headers=headers)
+        return response.json().get("choices", [{}])[0].get("message", {}).get("content", "No response")
+
+def chatbot_fn(user_input):
+    return asyncio.run(call_chat_api(user_input))
+
+def launch_gradio():
+    iface = gr.Interface(fn=chatbot_fn, inputs="text", outputs="text", title="Chat with your Data")
+    iface.launch(server_name="0.0.0.0", server_port=7861, show_error=True)

main.py

@@ -6,6 +6,8 @@ from loguru import logger
 from environs import Env
 from contextlib import asynccontextmanager
 from app.db.client import mongodb
+from gradio import launch_gradio
+import threading
 
 env = Env()
 env.read_env()
@@ -16,6 +18,8 @@ STORAGE_TYPE = env.str("STORAGE_TYPE", "mongodb")
 
 print(log_config.get_log_level())
 
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """
@@ -26,6 +30,11 @@ async def lifespan(app: FastAPI):
     logger.info("Starting up application...")
     if STORAGE_TYPE == "mongodb":
         await mongodb.connect()
+    
+    # Launch Gradio in a separate thread
+    thread = threading.Thread(target=launch_gradio)
+    thread.daemon = True
+    thread.start()
     yield
 
     # Shutdown

pyproject.toml

@@ -7,6 +7,7 @@ requires-python = ">=3.12"
 dependencies = [
     "environs>=14.1.1",
     "fastapi>=0.115.12",
+    "httpx>=0.28.1",
     "loguru>=0.7.3",
     "motor>=3.7.1",
     "pydantic>=2.11.4",

uv.lock

@@ -135,6 +135,34 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515 },
 ]
 
+[[package]]
+name = "httpcore"
+version = "1.0.9"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/06/94/82699a10bca87a5556c9c59b5963f2d039dbd239f25bc2a63907a05a14cb/httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8", size = 85484 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784 },
+]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "certifi" },
+    { name = "httpcore" },
+    { name = "idna" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517 },
+]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -185,6 +213,7 @@ source = { virtual = "." }
 dependencies = [
     { name = "environs" },
     { name = "fastapi" },
+    { name = "httpx" },
     { name = "loguru" },
     { name = "motor" },
     { name = "pydantic" },
@@ -198,6 +227,7 @@ dependencies = [
 requires-dist = [
     { name = "environs", specifier = ">=14.1.1" },
     { name = "fastapi", specifier = ">=0.115.12" },
+    { name = "httpx", specifier = ">=0.28.1" },
     { name = "loguru", specifier = ">=0.7.3" },
     { name = "motor", specifier = ">=3.7.1" },
     { name = "pydantic", specifier = ">=2.11.4" },