"list index out of range" error
Opened this issue · 2 comments
Hi and thank you very much !
I added an admin ID and write to the bot directly - I get answers, everything is fine. ChatML preset.
Then I write to the bot directly from another user who is not in the list of admins and telegram_users.txt is empty, then the bot starts responding ("X typing" during generating), but I don't see any response.
The script gives the error ERROR:root:thread_get_messagelist index out of range('list index out of range',) and continues to work.
Where could I make a mistake?
Or is it necessary to use only group chat for different users ?
full log
Dec 16 19:38:22 openchat run.sh[5771]: INFO:root:### TelegramBotWrapper INIT DONE ###
Dec 16 19:38:22 openchat run.sh[5771]: INFO:root:### !!! READY !!! ###
Dec 16 19:38:22 openchat run.sh[5771]: INFO:aiogram.dispatcher.dispatcher:Start polling.
Dec 16 19:39:30 openchat run.sh[5771]: llama_print_timings: load time = 21282.28 ms
Dec 16 19:39:30 openchat run.sh[5771]: llama_print_timings: sample time = 211.07 ms / 86 runs ( 2.45 ms per token, 407.44 tokens per second)
Dec 16 19:39:30 openchat run.sh[5771]: llama_print_timings: prompt eval time = 46708.79 ms / 1087 tokens ( 42.97 ms per token, 23.27 tokens per second)
Dec 16 19:39:30 openchat run.sh[5771]: llama_print_timings: eval time = 20697.02 ms / 85 runs ( 243.49 ms per token, 4.11 tokens per second)
Dec 16 19:39:30 openchat run.sh[5771]: llama_print_timings: total time = 67857.71 ms
Dec 16 19:39:30 openchat run.sh[5771]: Llama.generate: prefix-match hit
Dec 16 19:39:33 openchat run.sh[5771]: llama_print_timings: load time = 21282.28 ms
Dec 16 19:39:33 openchat run.sh[5771]: llama_print_timings: sample time = 29.15 ms / 12 runs ( 2.43 ms per token, 411.69 tokens per second)
Dec 16 19:39:33 openchat run.sh[5771]: llama_print_timings: prompt eval time = 1117.42 ms / 32 tokens ( 34.92 ms per token, 28.64 tokens per second)
Dec 16 19:39:33 openchat run.sh[5771]: llama_print_timings: eval time = 1610.27 ms / 11 runs ( 146.39 ms per token, 6.83 tokens per second)
Dec 16 19:39:33 openchat run.sh[5771]: llama_print_timings: total time = 2788.88 ms
Dec 16 19:39:34 openchat run.sh[5771]: ERROR:root:thread_get_messagelist index out of range('list index out of range',)
Dec 16 19:39:51 openchat run.sh[5771]: Llama.generate: prefix-match hit
Dec 16 19:39:59 openchat run.sh[5771]: llama_print_timings: load time = 21282.28 ms
Dec 16 19:39:59 openchat run.sh[5771]: llama_print_timings: sample time = 86.89 ms / 36 runs ( 2.41 ms per token, 414.30 tokens per second)
Dec 16 19:39:59 openchat run.sh[5771]: llama_print_timings: prompt eval time = 2698.25 ms / 24 tokens ( 112.43 ms per token, 8.89 tokens per second)
Dec 16 19:39:59 openchat run.sh[5771]: llama_print_timings: eval time = 5428.98 ms / 35 runs ( 155.11 ms per token, 6.45 tokens per second)
Dec 16 19:39:59 openchat run.sh[5771]: llama_print_timings: total time = 8316.26 ms
Dec 16 19:40:00 openchat run.sh[5771]: ERROR:root:thread_get_messagelist index out of range('list index out of range',)
if block exeption in thread_get_message :
ERROR:asyncio:Task exception was never retrieved
future: <Task finished name='Task-7' coro=<Dispatcher._process_polling_updates() done, defined at /usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/dispatcher.py:410> exception=IndexError('list index out of range')>
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/dispatcher.py", line 418, in _process_polling_updates
for responses in itertools.chain.from_iterable(await self.process_updates(updates, fast)):
File "/usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/dispatcher.py", line 236, in process_updates
return await asyncio.gather(*tasks)
File "/usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/handler.py", line 117, in notify
response = await handler_obj.handler(*args, **partial_data)
File "/usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/dispatcher.py", line 257, in process_update
return await self.message_handlers.notify(update.message)
File "/usr/local/lib/python3.10/dist-packages/aiogram/dispatcher/handler.py", line 117, in notify
response = await handler_obj.handler(*args, **partial_data)
File "/data/llm_telegram_bot/main.py", line 361, in thread_get_message
reply = await self.send_message(text=answer, chat_id=chat_id)
File "/usr/local/lib/python3.10/dist-packages/backoff/_async.py", line 151, in retry
ret = await target(*args, **kwargs)
File "/data/llm_telegram_bot/main.py", line 230, in send_message
text = await utils.prepare_text(text, user, "to_user")
File "/data/llm_telegram_bot/source/utils.py", line 67, in prepare_text
+ cfg.translate_html_tag[0]
IndexError: list index out of range
<|im_start|>system
There some error in file "/llm telegram_bot/source/utils.py", line 67, and i 've been delete code of function prepare_text , because llm can chat without translate.