Create app.py

app.py

@@ -0,0 +1,41 @@
+import gradio
+import os
+from litellm import completion
+os.environ["OPENROUTER_API_KEY"] = "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"
+
+def inference(message, history):
+    try:
+        flattened_history = [item for sublist in history for item in sublist]
+        full_message = " ".join(flattened_history + [message])
+        messages_litellm = [{"role": "user", "content": full_message}] # litellm message format
+        partial_message = ""
+        for chunk in litellm.completion(model="openrouter/meta-llama/llama-2-13b-chat",
+                                        api_base="10.213.21.138:56928",
+                                        messages=messages_litellm,
+                                        max_new_tokens=512,
+                                        temperature=.7,
+                                        top_k=100,
+                                        top_p=.9,
+                                        repetition_penalty=1.18,
+                                        stream=True):
+            partial_message += chunk['choices'][0]['delta']['content'] # extract text from streamed litellm chunks
+            yield partial_message
+    except Exception as e:
+        print("Exception encountered:", str(e))
+        yield f"An Error occured please 'Clear' the error and try your question again"
+
+gr.ChatInterface(
+    inference,
+    chatbot=gr.Chatbot(height=400),
+    textbox=gr.Textbox(placeholder="Enter text here...", container=False, scale=5),
+    description=f"""
+    CURRENT PROMPT TEMPLATE: {model_name}.
+    An incorrect prompt template will cause performance to suffer.
+    Check the API specifications to ensure this format matches the target LLM.""",
+    title="Simple Chatbot Test Application",
+    examples=["Define 'deep learning' in once sentence."],
+    retry_btn="Retry",
+    undo_btn="Undo",
+    clear_btn="Clear",
+    theme=theme,
+).queue().launch()