Create app.py

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import os
+import re
+from dotenv import load_dotenv
+from cerebras.cloud.sdk import Cerebras
+
+# Load environment variables from .env file
+load_dotenv()
+
+client = Cerebras(
+    api_key=os.environ.get("CEREBRAS_API_KEY")
+)
+
+def clean_response(text):
+    lines = []
+    for line in text.splitlines():
+        # Remove bullets like *, #, •, - from the beginning (not numbered lists)
+        line = re.sub(r"^\s*[*#•\-]+\s*", "", line)
+        # Remove markdown bold formatting
+        line = re.sub(r"\*\*(.*?)\*\*", r"\1", line)
+        line = re.sub(r"__(.*?)__", r"\1", line)
+        lines.append(line)
+    return "\n".join(lines)
+
+def chat(prompt, _):
+    try:
+        stream = client.chat.completions.create(
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are a helpful assistant."
+                },
+                {
+                    "role": "user",
+                    "content": prompt
+                }
+            ],
+            model="gpt-oss-120b",
+            stream=True,
+            max_completion_tokens=65536,
+            temperature=1,
+            top_p=1,
+            reasoning_effort="medium"
+        )
+        
+        response_text = ""
+        for chunk in stream:
+            if chunk.choices[0].delta.content:
+                response_text += chunk.choices[0].delta.content
+        
+        return clean_response(response_text)
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+gr.Interface(
+    fn=chat,
+    inputs=[gr.Textbox(label="Ask something"), gr.Radio(["English"], visible=False)],
+    outputs=gr.Textbox(label="Response")
+).launch()