Create app.py

app.py

@@ -0,0 +1,75 @@
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnableBranch
+from langchain_core.runnables.passthrough import RunnableAssign
+from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings
+
+import gradio as gr
+
+embedder = NVIDIAEmbeddings(model="nvolveqa_40k", model_type="query")
+chat_model = ChatNVIDIA(model="llama2_13b") | StrOutputParser()
+
+response_prompt = ChatPromptTemplate.from_messages([("system", "{system}"), ("user", "{input}")])
+
+def RPrint(preface=""):
+    def print_and_return(x, preface=""):
+        print(f"{preface}{x}")
+        return x
+    return RunnableLambda(partial(print_and_return, preface=preface))
+
+## "Help them out" system message
+good_sys_msg = (
+    "You are an NVIDIA chatbot. Please answer their question while representing NVIDIA."
+    "  Please help them with their question if it is ethical and relevant."
+)
+## Resist talking about this topic" system message
+poor_sys_msg = (
+    "You are an NVIDIA chatbot. Please answer their question while representing NVIDIA."
+    "  Their question has been analyzed and labeled as 'probably not useful to answer as an NVIDIA Chatbot',"
+    "  so avoid answering if appropriate and explain your reasoning to them. Make your response as short as possible."
+)
+
+
+def is_good_response(query):
+    ## TODO: embed the query and pass the embedding into your classifier
+    embedding = np.array([embedder.embed_query(query)])
+    ## TODO: return true if it's most likely a good response and false otherwise
+    return model1(embedding)
+
+
+chat_chain = (
+    { 'input'  : (lambda x:x), 'is_good' : is_good_response }
+    | RPrint()
+    | RunnableAssign(dict(
+        system = RunnableBranch(
+            ## Switch statement syntax. First lambda that returns true triggers return of result
+            ((lambda d: d['is_good'] < 0.5), RunnableLambda(lambda x: poor_sys_msg)),
+            ## ... (more branches can also be specified)
+            ## Default branch. Will run if none of the others do
+            RunnableLambda(lambda x: good_sys_msg)
+        )
+    )) | response_prompt | chat_model
+)
+
+
+
+
+################
+## Gradio components
+
+def chat_stream(message, history):
+    buffer = ""
+    for token in chat_chain.stream(message):
+        buffer += token
+        yield buffer
+
+chatbot = gr.Chatbot(value = [[None, "Hello! I'm your NVIDIA chat agent! Let me answer some questions!"]])
+demo = gr.ChatInterface(chat_stream, chatbot=chatbot).queue()
+
+try:
+    demo.launch(debug=True, share=True, show_api=False)
+    demo.close()
+except Exception as e:
+    demo.close()
+    print(e)
+    raise e