Create app.py

app.py

@@ -0,0 +1,23 @@
+import os
+import gradio as gr
+from langchain.chat_models.fireworks import ChatFireworks
+from langchain.schema import HumanMessage, SystemMessage, AIMessage
+from langchain.memory import ConversationBufferMemory
+
+os.environ["FIREWORKS_API_KEY"] = "ku9UYtzjSAATlcAstO8yrB89MzvDqJL3lGIkNgnVZ7URxPxK"
+
+llm = ChatFireworks(
+    model="accounts/fireworks/models/llama-v2-13b-chat",
+    model_kwargs={"temperature": 0.2, "max_tokens": 64, "top_p": 1.0},
+)
+
+def predict(message, history):
+    history_langchain_format = []
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+    history_langchain_format.append(HumanMessage(content=message))
+    gpt_response = llm(history_langchain_format)
+    return gpt_response.content
+
+gr.ChatInterface(predict).launch()