Update app.py

app.py

@@ -1,26 +1,34 @@
 import gradio as gr
-from transformers import pipeline
+import requests
 
-generator = pipeline("text-generation", model="meta-llama/Llama-2-7b-chat-hf")
+API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.1"
+headers = {
+    "Authorization": f"Bearer hf_HmAOAKYrjUmRdocDHP"
+}
 
-def evaluate_response(prompt):
-    # Generate text from the prompt
-    outputs = generator(prompt, max_new_tokens=150, do_sample=True, temperature=0.7)
-    generated_text = outputs[0]['generated_text']
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    if response.status_code != 200:
+        return {"error": f"API error {response.status_code}: {response.text}"}
+    return response.json()
 
-    # Simple quality evaluation: check if response length > 10 words
-    word_count = len(generated_text.split())
-    quality = "Good" if word_count > 10 else "Poor"
+def process(prompt):
+    output = query({
+        "inputs": prompt,
+        "parameters": {
+            "max_new_tokens": 100,
+            "temperature": 0.7
+        }
+    })
+    if "error" in output:
+        return output["error"]
+    if isinstance(output, list) and "generated_text" in output[0]:
+        return output[0]["generated_text"].replace(prompt, "").strip()
+    return f"Unexpected output: {output}"
 
-    return generated_text, f"Response Quality: {quality}"
-
-iface = gr.Interface(
-    fn=evaluate_response,
-    inputs=gr.Textbox(lines=4, label="Enter your prompt"),
-    outputs=[gr.Textbox(label="Model Response"), gr.Textbox(label="Quality Analysis")],
-    title="Model Understanding Test",
-    description="Enter a prompt, get a model response, and see an automatic quality evaluation."
-)
-
-if __name__ == "__main__":
-    iface.launch()
+gr.Interface(
+    fn=process,
+    inputs=gr.Textbox(label="Prompt", lines=3),
+    outputs=gr.Textbox(label="Response", lines=6),
+    title="Hugging Face Mistral API Test"
+).launch()