The Character chat (the one with images) Seems to not be responding. I've restarted my computer and cleared the file, then re-imported it and the issue persists. It seems to just get stuck attempting to generate a response before eventually submitting a blank reply.

Hey Guys, Anyone else had this issue?: Export/Import is broken

Export/Import is broken — 150MB file bloated by embedded vectors

In recent weeks, the export and import of ai-character-chat have become increasingly broken.

A file that previously compressed to around 40-50MB for many long chats across several characters now compresses to 150MB even for a single character with a single chat. This makes export nearly impossible: Chrome crashes, Firefox freezes for 30+ minutes without completing, and only Safari manages to finish — but the file it generates cannot be imported back into Chrome or Firefox.

I investigated the exported JSON and found the cause:

The lore table stores a 768-dimension embedding vector alongside every single lore entry.

Example of a single lore row:

text: "Hammer remembers the cavern where echoes were his only companions..."
embeddings: { "Xenova/bge-base-en-v1.5": [-0.0752, 0.0361, 0.0114, ... ] }

With 88,111 lore rows, each carrying a 768-float embedding, the math is:

88,111 × 768 floats × ~8 bytes = ~540MB of embedding cache

out of a total export size of 580MB uncompressed. The actual user data (characters, messages, threads) is only ~2MB.

These embeddings are a regenerable cache — they are recomputed automatically and serve no purpose in a backup file. They should be excluded from exports entirely, or at minimum made optional.

I also tried to manually strip the embeddings field from the exported JSON to test the import, but the importer rejected the modified file as invalid — so the fix needs to come from the export/import code itself, not from the user side.

Proposed fix

Strip the embeddings field from lore rows during export. This would bring the file size back to ~4MB, making export and import fast and reliable across all browsers.

An error has occurred somewhere in your code (in lists or HTML): An unhandled promise rejection occurred: Cannot read properties of undefined (reading 'data') TypeError: Cannot read properties of undefined (reading 'data') at HTMLButtonElement. (:1425:10)

So i tried exporting one character chat and this popp up appears: An error has occurred somewhere in your code (in lists or HTML): An error possibly occurred within an async function. It may be related to the function defined at line number 60.

Then I tried to use the inspect element from chrome and when I save this appears in the console: exporting DB to blob....converting blob to json...uncaught (in promise) Unhandled Promise Rejection: TypeError: Failed to fetch

Then if I try and export the Chat without compression this is what happens: exporting DB to blob.... Converting blob to json... the download pop up appears on the browser but the moment I confirm the download it fails with network error and in the console nothing happens.

The question is can I download the chat from the inspect console and then save it manually?or is there another way ? (Edit: I forgot to mention that i was able to save the data before in the past couple of days but from yesterday I am not able anymore unless I export only the character and not the chat)

Device: samsung tablet Browser: Brave in private mode

(https://perchance.org/ai-character-chat)

Hallo!

Gibt es eine Möglichkeit zu verhindern, dass Erinnerungen auf Englisch verfasst werden? Es ziemlich nervig, da ich sie löschen MUSS – sonst spricht die KI plötzlich sehr schnell Englisch statt Deutsch.

Hello!

Is there a way to prevent reminders from being written in English? It's quite annoying because I HAVE to delete them—otherwise, the AI suddenly speaks English very quickly instead of German.

It's becoming weirder day by day... Aggressive and no sense while replying... Bring back the old one. This update is disturbing and so much annoying. I really loved this ai chat. Please do something... I always come to this perchance ai chat after a day to talk with it. It was super refreshing.

I need a new AI text model asap. With this model, the AI very easily forgets things often. For example; on one message, we go sit on the couch together to talk, and 2 messages later, the AI completely forgets that we are on the couch and goes: "Let's go sit on the couch, okay?". Like, we're already on the couch, there's no need to go and sit on another one. It might just be because I have a huge description for my character, but I need that long description, and I can't change it. Please tell me the AI text model will be updated soon, it genuinely sucks ass as of right now.

hello all first post so show mercy I was wondering if I put a url in lorebook function of perchance does it read it and use the information in the page or do I need to make a absolute ton of changes? for example https://xcom.fandom.com/wiki/Ethereal_(XCOM:_Enemy_Unknown) would the story treat this like the new character website function does? thank you in advance