Upload app.py

app.py

@@ -1,64 +1,104 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+from openai import OpenAI
+
+
+def predict(message, history, system_prompt, model, api_url, api_key):
+    # Format history with a given chat template
+    msgs = [{"role": "system", "content": system_prompt}]
+    for user, assistant in history:
+        msgs.append({"role": "user", "content": user})
+        msgs.append({"role": "system", "content": assistant})
+
+    msgs.append({"role": "user", "content": message})
+    try:
+        client = OpenAI(api_key=api_key, base_url=api_url)
+        response = client.chat.completions.create(
+            model=model,
+            messages=msgs,
+            temperature=0.3,
+            stream=False,
+        ).to_dict()["choices"][0]["message"]["content"]
+
+    except Exception as e:
+        response = f"{e}"
+
+    return response
+
+
+def deepseek(message, history, model, api_key, system_prompt):
+    response = predict(
+        message,
+        history,
+        system_prompt,
+        model,
+        "https://api.deepseek.com",
+        api_key,
+    )
+    outputs = []
+    for new_token in response:
+        outputs.append(new_token)
+        yield "".join(outputs)
+
+
+def kimi(message, history, model, api_key, system_prompt):
+    response = predict(
+        message,
+        history,
+        system_prompt,
+        model,
+        "https://api.moonshot.cn/v1",
+        api_key,
+    )
+    outputs = []
+    for new_token in response:
+        outputs.append(new_token)
+        yield "".join(outputs)
+
+
+if __name__ == "__main__":
+    with gr.Blocks() as demo:  # Create Gradio interface
+        with gr.Tab("DeepSeek"):
+            with gr.Accordion(label="⚙️ Settings", open=False) as ds_acc:
+                ds_model = gr.Dropdown(
+                    choices=["deepseek-chat", "deepseek-r1"],
+                    value="deepseek-chat",
+                    label="Select a model",
+                )
+                ds_key = gr.Textbox(
+                    "sk-78bc040108044779828597256dacc7bd",
+                    type="password",
+                    label="API key",
+                )
+                ds_sys = gr.Textbox(
+                    "You are a useful assistant. first recognize user request and then reply carfuly and thinking",
+                    label="System prompt",
+                )
+            gr.ChatInterface(
+                deepseek,
+                title="DeepSeek API 部署实例",
+                additional_inputs=[ds_model, ds_key, ds_sys],
+            )
+
+        with gr.Tab("Kimi"):
+            with gr.Accordion(label="⚙️ Settings", open=False) as kimi_acc:
+                kimi_model = gr.Dropdown(
+                    choices=["moonshot-v1-32k"],
+                    value="moonshot-v1-32k",
+                    label="Select a model",
+                )
+                kimi_key = gr.Textbox(
+                    "sk-r1r5DEgoqaZn0CP6PfJ8u7DfKCmf28kK64cimXCsFs8JUj8a",
+                    type="password",
+                    label="API key",
+                )
+                kimi_sys = gr.Textbox(
+                    "You are a useful assistant. first recognize user request and then reply carfuly and thinking",
+                    label="System prompt",
+                )
+            gr.ChatInterface(
+                kimi,
+                title="KimiChat API 部署实例",
+                additional_inputs=[kimi_model, kimi_key, kimi_sys],
+            )
+
+    demo.queue().launch()