apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-05-11 16:52:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

update token counter

Browse source
This commit is contained in:
geekan 2023-07-14 02:30:44 +08:00
parent d1c004d37e
commit 07b400187c
1 changed files with 27 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

42
metagpt/utils/token_counter.py
View file

@ -13,38 +13,50 @@ from metagpt.schema import RawMessage
TOKEN_COSTS = {
"gpt-3.5-turbo": {"prompt": 0.002, "completion": 0.002},
"gpt-3.5-turbo-0301": {"prompt": 0.002, "completion": 0.002},
"gpt-3.5-turbo": {"prompt": 0.0015, "completion": 0.002},
"gpt-3.5-turbo-0301": {"prompt": 0.0015, "completion": 0.002},
"gpt-3.5-turbo-0613": {"prompt": 0.0015, "completion": 0.002},
"gpt-3.5-turbo-16k": {"prompt": 0.003, "completion": 0.004},
"gpt-3.5-turbo-16k-0613": {"prompt": 0.003, "completion": 0.004},
"gpt-4-0314": {"prompt": 0.03, "completion": 0.06},
"gpt-4": {"prompt": 0.03, "completion": 0.06},
"gpt-4-32k": {"prompt": 0.06, "completion": 0.12},
"gpt-4-32k-0314": {"prompt": 0.06, "completion": 0.12},
"gpt-4-0613": {"prompt": 0.06, "completion": 0.12},
"text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
}
def count_message_tokens(messages: list[RawMessage], model="gpt-3.5-turbo-0301"):
"""Returns the number of tokens used by a list of messages."""
def count_message_tokens(messages, model="gpt-3.5-turbo-0613"):
"""Return the number of tokens used by a list of messages."""
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
print("Warning: model not found. Using cl100k_base encoding.")
encoding = tiktoken.get_encoding("cl100k_base")
if model == "gpt-3.5-turbo":
print("Warning: gpt-3.5-turbo may change over time. Returning num tokens assuming gpt-3.5-turbo-0301.")
return count_message_tokens(messages, model="gpt-3.5-turbo-0301")
elif model == "gpt-4":
print("Warning: gpt-4 may change over time. Returning num tokens assuming gpt-4-0314.")
return count_message_tokens(messages, model="gpt-4-0314")
if model in {
"gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k-0613",
"gpt-4-0314",
"gpt-4-32k-0314",
"gpt-4-0613",
"gpt-4-32k-0613",
}:
tokens_per_message = 3
tokens_per_name = 1
elif model == "gpt-3.5-turbo-0301":
tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
tokens_per_name = -1 # if there's a name, the role is omitted
elif model == "gpt-4-0314":
tokens_per_message = 3
tokens_per_name = 1
elif "gpt-3.5-turbo" in model:
print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
return count_message_tokens(messages, model="gpt-3.5-turbo-0613")
elif "gpt-4" in model:
print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
return count_message_tokens(messages, model="gpt-4-0613")
else:
raise NotImplementedError(f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""")
raise NotImplementedError(
f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
)
num_tokens = 0
for message in messages:
num_tokens += tokens_per_message