Updated to API

app.py

@@ -1,64 +1,73 @@
-import gradio as gr
+from fastapi import FastAPI
+from pydantic import BaseModel
+from typing import List, Literal, Optional
 from huggingface_hub import InferenceClient
+from fastapi.responses import JSONResponse
+import uuid
+import time
+import uvicorn
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+app = FastAPI()
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# OpenAI-compatible request message
+class Message(BaseModel):
+    role: Literal["system", "user", "assistant"]
+    content: str
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# OpenAI-compatible request body
+class ChatCompletionRequest(BaseModel):
+    model: str = "zephyr-7b-beta"
+    messages: List[Message]
+    temperature: Optional[float] = 0.7
+    top_p: Optional[float] = 0.95
+    max_tokens: Optional[int] = 512
+    stream: Optional[bool] = False
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# OpenAI-compatible response message
+class Choice(BaseModel):
+    index: int
+    message: Message
+    finish_reason: Optional[str] = "stop"
 
-    messages.append({"role": "user", "content": message})
+# OpenAI-compatible full response
+class ChatCompletionResponse(BaseModel):
+    id: str
+    object: str = "chat.completion"
+    created: int
+    model: str
+    choices: List[Choice]
 
-    response = ""
+@app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
+async def chat_completions(request: ChatCompletionRequest):
+    # Build HuggingFace-style message list
+    messages = [{"role": m.role, "content": m.content} for m in request.messages]
 
-    for message in client.chat_completion(
+    # Generate chat completion
+    response_text = ""
+    for chunk in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        max_tokens=request.max_tokens,
+        temperature=request.temperature,
+        top_p=request.top_p,
+        stream=False,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+        response_text += chunk.choices[0].delta.content
 
+    # Build OpenAI-style response
+    chat_response = ChatCompletionResponse(
+        id=f"chatcmpl-{uuid.uuid4().hex}",
+        created=int(time.time()),
+        model=request.model,
+        choices=[
+            Choice(
+                index=0,
+                message=Message(role="assistant", content=response_text),
+            )
+        ]
+    )
+    return JSONResponse(content=chat_response.dict())
 
+# Run this file directly
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)