Chat

https://github.com/run-llama/llama_index/issues/14273#issuecomment-2181149146

hey i have the following question

what is the difference between OpenAI agent and ReAct agent & which to use
using PromptTemplates provided more controlled and consistent output compared to system prompts
in case of agent AzureOpenAI is very slow as compared OpenAI, there is about 10x delay in response generation. I have tried with both ReActAgent & OpenAIAgent

Plain Text

llm = AzureOpenAI(
    model=os.getenv("AOAI_COMPLETION_MODEL"),
    deployment_name=os.getenv("AOAI_DEPLOYMENT_NAME_COMPLETION"),
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    azure_endpoint=os.getenv("AOAI_ENDPOINT"),
    api_version=os.getenv("AOAI_API_VERSION"),
)

lastly how to use prompt template with chat engine

6 comments

LLogan M

React uses a prompting format to get the llm to pick tools to use

Openai agent just uses their tools api, no special prompting

Chat engines don't really have prompts. It's just chat history

The react agent has a prompt with the instructions for react, but in 99% of cases you don't want to change this (it's a huge prompt)

ppayload

@Logan M thanks for the response

Can u answer this also

in case of agent AzureOpenAI is very slow as compared OpenAI, there is about 10x delay in response generation. I have tried with both ReActAgent & OpenAIAgent

LLogan M

I have no idea on that one, thats up to azure and your azure deployment 👀

EEverett

Hey @Logan M , is the OpenAI Agent an Assitant Implementation, or just a Function callling agent.

BTW, @payload , A major difference for the React Agent is that it will perform much more LLM calls to support its advanced reasoning. Which is something to keep in mind. Generally React will perform better for use cases that require anything mildly complex or custom.

LLogan M

Its just a function calling agent

ppayload

Is there any configuration u are aware of to speed up azure openai

Add a reply

Find answers from the community

Chat