Create app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from openai import OpenAI
+
+BASE_URL = "https://w0xtwbf2fdxe1q-8000.proxy.runpod.net/v1"
+API_KEY="SOMEHOW"
+
+
+# Create an OpenAI client to interact with the API server
+client = OpenAI(
+    base_url=BASE_URL,
+    api_key=API_KEY
+)
+
+
+def predict(message, history):
+    # Convert chat history to OpenAI format
+    history_openai_format = [{
+        "role": "system",
+        "content": "Tu es un excellent assistant IA développé par WAY2CALL pour faire des évaluations en JSON des audios transcrits."
+    }]
+    for human, assistant in history:
+        history_openai_format.append({"role": "user", "content": human})
+        history_openai_format.append({
+            "role": "assistant",
+            "content": assistant
+        })
+    history_openai_format.append({"role": "user", "content": message})
+
+    # Create a chat completion request and send it to the API server
+    stream = client.chat.completions.create(
+        model="CONCREE/meta-adia-llm-instruct",  # Model name to use
+        messages=history_openai_format,  # Chat history
+        temperature=0.1,  # Temperature for text generation
+        stream=True,  # Stream response
+    )
+
+    # Read and return generated text from response stream
+    partial_message = ""
+    for chunk in stream:
+        partial_message += (chunk.choices[0].delta.content or "")
+        yield partial_message
+
+
+# Create and launch a chat interface with Gradio
+gr.ChatInterface(predict).queue().launch()