Error: "Do I know you?"

[kamil-malinski]

Hi!

I tried your bot and I ended up getting an error when I message the bot:

  Error: Do I know you? #xxxxxxxxxx
       at assistantThreadIdUpsert (/root/bubby/packages/core/src/3rdparty/openai/assistant_thread.ts:46:11)
       at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
       at sendReplies (/root/bubby/packages/core/src/handlers/reply_to_chat.ts:31:20)
       at allReplies (/root/bubby/packages/core/src/3rdparty/telegram/webhook.ts:59:3)
       at <anonymous> (/root/bubby/packages/core/src/3rdparty/telegram/webhook.ts:26:5)
       at execute (/root/bubby/node_modules/.pnpm/[email protected]/node_modules/telegraf/lib/composer.js:501:17)
       at <anonymous> (/root/bubby/node_modules/.pnpm/[email protected]/node_modules/telegraf/lib/composer.js:502:21)
       at execute (/root/bubby/node_modules/.pnpm/[email protected]/node_modules/telegraf/lib/composer.js:501:17)
       at execute (/root/bubby/node_modules/.pnpm/[email protected]/node_modules/telegraf/lib/composer.js:501:17)
       at <anonymous> (/root/bubby/node_modules/.pnpm/[email protected]/node_modules/p-timeout/index.js:50:13)

Where do I configure the whitelist of users, that are allowed to use the bot?

Thanks!

Kamil

[daohoangson]

You will need to change this line before deploying your bot:

bubby/packages/core/src/3rdparty/openai/assistant_thread.ts

Lines 44 to 47 in e7db93b

	if (userId !== "552046506") {
	// https://t.me/daohoangson
	throw new AssistantError(`Do I know you? #${userId}`);
	}

.

[kamil-malinski]

thanks, it worked!

[daohoangson]

That's great to hear. How was the conversation with the bot?

[kamil-malinski]

the conversation works great! I really like your bot, thanks a lot! I have just a few suggestions:

• please add the initial prompt into a config variable so one doesn't have to edit the source file
• enable streaming of the response

by the way, how does the memory feature work? could you please explain it briefly?

Cheers

Kamil

[daohoangson]

please add the initial prompt into a config variable so one doesn't have to edit the source file

I see, that makes sense.

enable streaming of the response

That's not possible with OpenAI assistant API right now, maybe soon.

by the way, how does the memory feature work? could you please explain it briefly?

You can ask the bot to remember something and it will use function call to do that. The memory is persisted across threads / conversations. Something like this:

[kamil-malinski]

I see, thank you for the explanation!

maybe you could add "New thread." (and other commands?) as a command to the bot:

https://core.telegram.org/bots/features#commands

[daohoangson]

Yep, that makes sense.