How to use memory to record conversation context in AgentInitialize

[syzjbs]

When using AgentInitialize with the openai functions agent, I added ConversationBufferMemory
As a memory node, I have tried many configurations for ConversationBufferMemory, otherwise my flow would not function properly. Either it can run normally, but it cannot record the context, and my two consecutive Q&A sessions cannot be related.

I would like to inquire about how to configure AgentInitialize (or other agents that can use openai-functions), and record my context.

Thank you for your help

[YamonBot]

hello. We are also implementing a part that decomposes the agent's structured response and operates it. I think you can use LangChain’s Outputpaser for this. In other words, this is a method of parsing values ​​in a specific format using an output parser and storing them in the DB. However, since Langflow seems to output the response message directly, additional research is needed on this issue.

[syzjbs]

Thank you for providing the idea. I will refer to this idea for further learning and experimentation

[Cristhianzl]

Hi! 👋

We are using other channels as our official means of communication with users. We apologize for the delayed response.
For faster assistance, please direct your questions to our Discord channel or open a GitHub issue, as we are much more active on these platforms.

Langflow Discord Server

Thank you for your understanding.

Best regards,
The Langflow Team