Prompt

from llama_index.memory import ChatMemoryBuffer

memory = ChatMemoryBuffer.from_defaults(token_limit=1500)

chat_engine = index.as_chat_engine(
    chat_mode="context",
    memory=memory,
    system_prompt=(
        "You are a chatbot, able to have normal interactions, as well as talk"
        " about an essay discussing Paul Grahams life."
    ),
)

from llama_index.callbacks import (
    CallbackManager,
    LlamaDebugHandler,
    CBEventType,
)

from llama_index import ServiceContext
from llama_index.llms import OpenAI

llm = OpenAI(model="gpt-3.5-turbo", temperature=0)
llama_debug = LlamaDebugHandler(print_trace_on_end=True)
callback_manager = CallbackManager([llama_debug])

service_context = ServiceContext.from_defaults(
    callback_manager=callback_manager, llm=llm
)

Your code for chat engine comes in here
# after runniong the query try with this
# Print info on llm inputs/outputs - returns start/end events for each LLM call
event_pairs = llama_debug.get_llm_inputs_outputs()
print(event_pairs[0][0])
print(event_pairs[0][1].payload.keys())
print(event_pairs[0][1].payload["response"])

system_prompt = ("You are a chatbot that answers questions about "{company name}" models.\n"
                  "Instruction: Always follow these rules while generating response:\n"
                  "1. ALWAYS answer query ONLY if answer can be found in the context.\n"
                  "2. If answer is not present in the context, Just SAY: Unable to help"
                  "you at the moment\n"
                  "3. If URLs are present in the source/metadata, ADD them in the response.")