falkor

I see openai just released an update for that https://cookbook.openai.com/examples/how_to_stream_completions#4-how-to-get-token-usage-data-for-streamed-chat-completion-response and seems like it was already done via this [PR](https://github.com/langchain-ai/langchainjs/pull/5586)

@chungyau97 via embed chat would be fine for me. @Jaredude can you elaborate further about the override config, maybe provide some simple example? Not sure I'm following you.. Thanks

@Jaredude thank you so much Can you please provide a very basic example how to provide dynamic param (e.g. 'customer_id') via this chatflowconfig entity? It is not so clear from...

@Jaredude awesome 😎 One last question, how about the log? Would I be able to differ that somehow via the provided param (e.g. customer_id)?

@Jaredude another question please, How about Pinecone's namespace? Do you think it's doable to send an overrideConfig param which will override the Pinecone's namespace? For example: "overrideConfig": { ... "vars":...

I mean chat_messages table. Assuming I have one bot which serves multiple customers, I'd like to differ those chat-messages by some unique ID @Jaredude

@Jaredude that's a very interesting feature you're talking about. I wonder if for the bare minimum we would just store the overrideConfig json as part of additional new column we'll...

@Jaredude appreciate your comment, so I think I'll work on storing the overrideConfig and the customer logger would be a different feature.

> @Jaredude appreciate your comment, so I think I'll work on storing the overrideConfig and the customer logger would be a different feature. @Jaredude https://github.com/FlowiseAI/Flowise/pull/1709 please review

This issue has been solved via PR https://github.com/FlowiseAI/FlowiseChatEmbed/pull/129