You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

106 lines
3.4 KiB

Add Dockerfile + concept of a DATA_DIR - Add a Dockerfile so people can run this bot in a docker container - Stuck with recommendation of running with python3.9 for now - Will later test with 3.11 + supply fixes if I get this working ... - Added a DATA_DIR env param to use to choose the directory to write data we want persistent across docker container restarts to be written to - We default to CWD like the code does today - we just explicitly pass it to functions / classes Test: - `docker build -t gpt3discord .` ``` crl-m1:GPT3Discord cooper$ docker image ls REPOSITORY TAG IMAGE ID CREATED SIZE gpt3discord latest 6d2832af2450 69 seconds ago 356MB ``` - Try run it ... I would guess if I had correct tokens things would work ... - To do so I plan to bind mount over /bin/.env on my docker container when I run this ... ``` crl-m1:GPT3Discord cooper$ docker run gpt3discord None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. Downloading: 100%|██████████| 1.04M/1.04M [00:02<00:00, 516kB/s] Downloading: 100%|██████████| 456k/456k [00:01<00:00, 319kB/s] Downloading: 100%|██████████| 1.36M/1.36M [00:03<00:00, 443kB/s] Downloading: 100%|██████████| 665/665 [00:00<00:00, 740kB/s] Traceback (most recent call last): File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 413, in static_login data = await self.request(Route("GET", "/users/@me")) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 366, in request raise HTTPException(response, data) discord.errors.HTTPException: 401 Unauthorized (error code: 0): 401: Unauthorized The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/bin/gpt3discord", line 79, in <module> asyncio.get_event_loop().run_until_complete(main()) File "/usr/local/lib/python3.9/asyncio/base_events.py", line 647, in run_until_complete return future.result() File "/bin/gpt3discord", line 63, in main await bot.start(os.getenv("DISCORD_TOKEN")) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 658, in start await self.login(token) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 514, in login data = await self.http.static_login(token.strip()) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 417, in static_login raise LoginFailure("Improper token has been passed.") from exc discord.errors.LoginFailure: Improper token has been passed. Wrote PID to file the file bot.pid The debug channel and guild IDs are 755420092027633774 and 907974109084942396 Improper token has been passed. Removing PID file Unclosed client session client_session: <aiohttp.client.ClientSession object at 0xffff721a2dc0> Unclosed connector connections: ['[(<aiohttp.client_proto.ResponseHandler object at 0xffff718fe0a0>, 170230.336548951)]'] connector: <aiohttp.connector.TCPConnector object at 0xffff721a2fd0> ```
1 year ago
from pathlib import Path
import aiofiles
from transformers import GPT2TokenizerFast
class UsageService:
Add Dockerfile + concept of a DATA_DIR - Add a Dockerfile so people can run this bot in a docker container - Stuck with recommendation of running with python3.9 for now - Will later test with 3.11 + supply fixes if I get this working ... - Added a DATA_DIR env param to use to choose the directory to write data we want persistent across docker container restarts to be written to - We default to CWD like the code does today - we just explicitly pass it to functions / classes Test: - `docker build -t gpt3discord .` ``` crl-m1:GPT3Discord cooper$ docker image ls REPOSITORY TAG IMAGE ID CREATED SIZE gpt3discord latest 6d2832af2450 69 seconds ago 356MB ``` - Try run it ... I would guess if I had correct tokens things would work ... - To do so I plan to bind mount over /bin/.env on my docker container when I run this ... ``` crl-m1:GPT3Discord cooper$ docker run gpt3discord None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. Downloading: 100%|██████████| 1.04M/1.04M [00:02<00:00, 516kB/s] Downloading: 100%|██████████| 456k/456k [00:01<00:00, 319kB/s] Downloading: 100%|██████████| 1.36M/1.36M [00:03<00:00, 443kB/s] Downloading: 100%|██████████| 665/665 [00:00<00:00, 740kB/s] Traceback (most recent call last): File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 413, in static_login data = await self.request(Route("GET", "/users/@me")) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 366, in request raise HTTPException(response, data) discord.errors.HTTPException: 401 Unauthorized (error code: 0): 401: Unauthorized The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/bin/gpt3discord", line 79, in <module> asyncio.get_event_loop().run_until_complete(main()) File "/usr/local/lib/python3.9/asyncio/base_events.py", line 647, in run_until_complete return future.result() File "/bin/gpt3discord", line 63, in main await bot.start(os.getenv("DISCORD_TOKEN")) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 658, in start await self.login(token) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 514, in login data = await self.http.static_login(token.strip()) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 417, in static_login raise LoginFailure("Improper token has been passed.") from exc discord.errors.LoginFailure: Improper token has been passed. Wrote PID to file the file bot.pid The debug channel and guild IDs are 755420092027633774 and 907974109084942396 Improper token has been passed. Removing PID file Unclosed client session client_session: <aiohttp.client.ClientSession object at 0xffff721a2dc0> Unclosed connector connections: ['[(<aiohttp.client_proto.ResponseHandler object at 0xffff718fe0a0>, 170230.336548951)]'] connector: <aiohttp.connector.TCPConnector object at 0xffff721a2fd0> ```
1 year ago
def __init__(self, data_dir: Path):
self.usage_file_path = data_dir / "usage.txt"
# If the usage.txt file doesn't currently exist in the directory, create it and write 0.00 to it.
Add Dockerfile + concept of a DATA_DIR - Add a Dockerfile so people can run this bot in a docker container - Stuck with recommendation of running with python3.9 for now - Will later test with 3.11 + supply fixes if I get this working ... - Added a DATA_DIR env param to use to choose the directory to write data we want persistent across docker container restarts to be written to - We default to CWD like the code does today - we just explicitly pass it to functions / classes Test: - `docker build -t gpt3discord .` ``` crl-m1:GPT3Discord cooper$ docker image ls REPOSITORY TAG IMAGE ID CREATED SIZE gpt3discord latest 6d2832af2450 69 seconds ago 356MB ``` - Try run it ... I would guess if I had correct tokens things would work ... - To do so I plan to bind mount over /bin/.env on my docker container when I run this ... ``` crl-m1:GPT3Discord cooper$ docker run gpt3discord None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. Downloading: 100%|██████████| 1.04M/1.04M [00:02<00:00, 516kB/s] Downloading: 100%|██████████| 456k/456k [00:01<00:00, 319kB/s] Downloading: 100%|██████████| 1.36M/1.36M [00:03<00:00, 443kB/s] Downloading: 100%|██████████| 665/665 [00:00<00:00, 740kB/s] Traceback (most recent call last): File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 413, in static_login data = await self.request(Route("GET", "/users/@me")) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 366, in request raise HTTPException(response, data) discord.errors.HTTPException: 401 Unauthorized (error code: 0): 401: Unauthorized The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/bin/gpt3discord", line 79, in <module> asyncio.get_event_loop().run_until_complete(main()) File "/usr/local/lib/python3.9/asyncio/base_events.py", line 647, in run_until_complete return future.result() File "/bin/gpt3discord", line 63, in main await bot.start(os.getenv("DISCORD_TOKEN")) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 658, in start await self.login(token) File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 514, in login data = await self.http.static_login(token.strip()) File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 417, in static_login raise LoginFailure("Improper token has been passed.") from exc discord.errors.LoginFailure: Improper token has been passed. Wrote PID to file the file bot.pid The debug channel and guild IDs are 755420092027633774 and 907974109084942396 Improper token has been passed. Removing PID file Unclosed client session client_session: <aiohttp.client.ClientSession object at 0xffff721a2dc0> Unclosed connector connections: ['[(<aiohttp.client_proto.ResponseHandler object at 0xffff718fe0a0>, 170230.336548951)]'] connector: <aiohttp.connector.TCPConnector object at 0xffff721a2fd0> ```
1 year ago
if not self.usage_file_path.exists():
with self.usage_file_path.open("w") as f:
f.write("0.00")
f.close()
self.tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
async def get_price(
self,
tokens_used,
prompt_tokens=None,
completion_tokens=None,
embeddings=False,
chatgpt=False,
gpt4=False,
):
tokens_used = int(tokens_used)
if chatgpt:
price = (tokens_used / 1000) * 0.002
return price
elif gpt4:
price = (prompt_tokens / 1000) * 0.03 + (completion_tokens / 1000) * 0.06
return price
elif not embeddings:
price = (tokens_used / 1000) * 0.02
else:
price = (tokens_used / 1000) * 0.0004
return price
async def update_usage(
self,
tokens_used,
prompt_tokens=None,
completion_tokens=None,
embeddings=False,
chatgpt=False,
gpt4=False,
):
tokens_used = int(tokens_used)
if chatgpt:
price = (tokens_used / 1000) * 0.002
elif gpt4:
price = (prompt_tokens / 1000) * 0.03 + (completion_tokens / 1000) * 0.06
elif not embeddings:
price = (tokens_used / 1000) * 0.02
else:
price = (tokens_used / 1000) * 0.0004
usage = await self.get_usage()
print(
f"Cost -> Old: {str(usage)} | New: {str(usage + float(price))}, used {str(float(price))} credits"
)
# Do the same as above but with aiofiles
async with aiofiles.open(self.usage_file_path, "w") as f:
await f.write(str(usage + float(price)))
await f.close()
async def set_usage(self, usage):
async with aiofiles.open(self.usage_file_path, "w") as f:
await f.write(str(usage))
await f.close()
async def get_usage(self):
async with aiofiles.open(self.usage_file_path, "r") as f:
usage = float((await f.read()).strip())
await f.close()
return usage
1 year ago
def count_tokens(self, text):
res = self.tokenizer(text)["input_ids"]
return len(res)
async def update_usage_image(self, image_size):
# 1024×1024 $0.020 / image
# 512×512 $0.018 / image
# 256×256 $0.016 / image
if image_size == "1024x1024":
price = 0.02
elif image_size == "512x512":
price = 0.018
elif image_size == "256x256":
price = 0.016
else:
raise ValueError("Invalid image size")
usage = await self.get_usage()
async with aiofiles.open(self.usage_file_path, "w") as f:
await f.write(str(usage + float(price)))
await f.close()
1 year ago
@staticmethod
def count_tokens_static(text):
tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
res = tokenizer(text)["input_ids"]
return len(res)