update app.py

app.py

@@ -1,63 +1,37 @@
 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 health Chatbot and your name is Hutano Health. You were trained on the MedQuad dataset that is a high quality dataset.", 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)",
-        ),
-    ],
+import requests
+
+# Define the Hugging Face API endpoint and your API token
+API_URL = "https://z94ka3s1dsuof4va.us-east-1.aws.endpoints.huggingface.cloud"
+API_TOKEN = "hf\_XgrSWzAWKtqKXgSFLZMZsQeSSjCcMbqUIt"  # Replace with your actual API token
+
+# Function to query the Hugging Face model
+def query_huggingface_model(input_text):
+    headers = {"Authorization": f"Bearer {API_TOKEN}"}
+    payload = {"inputs": input_text}
+    response = requests.post(API_URL, headers=headers, json=payload)
+    
+    if response.status_code == 200:
+        return response.json()
+    else:
+        return {"error": f"Request failed with status code {response.status_code}"}
+
+# Define a function to process the input and return the model's output
+def generate_response(input_text):
+    response = query_huggingface_model(input_text)
+    if "error" in response:
+        return response["error"]
+    else:
+        return response[0]['generated_text']
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your text here..."),
+    outputs="text",
+    title="LLaMA-2-7B Guanaco Dolly Mini Model",
+    description="Generate responses using the LLaMA-2-7B Guanaco Dolly Mini model from Hugging Face."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()