Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fixbug#979 : RuntimeError: fail to reduce message length #986

Merged
merged 2 commits into from
Mar 15, 2024
Merged

fixbug#979 : RuntimeError: fail to reduce message length #986

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6487ae8
- updated MAX-TOKEN according to openai document
azurewtl Mar 11, 2024
73d0d29
- change reserved parameter back to `config.llm.max_token`
azurewtl Mar 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion metagpt/actions/research.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ def gen_msg():
break

model_name = config.llm.model
prompt = reduce_message_length(gen_msg(), model_name, system_text, 4096)
prompt = reduce_message_length(gen_msg(), model_name, system_text, config.llm.max_token)
logger.debug(prompt)
queries = await self._aask(prompt, [system_text])
try:
Expand Down
2 changes: 1 addition & 1 deletion metagpt/config2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ def default(cls):
"""
default_config_paths: List[Path] = [
METAGPT_ROOT / "config/config2.yaml",
Path.home() / ".metagpt/config2.yaml",
CONFIG_ROOT / "config2.yaml",
]

dicts = [dict(os.environ)]
Expand Down
33 changes: 16 additions & 17 deletions metagpt/utils/token_counter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,25 +140,24 @@
"mixtral-8x7b": {"prompt": 0.4, "completion": 1.6},
}

# https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
TOKEN_MAX = {
"gpt-3.5-turbo": 4096,
"gpt-3.5-turbo-0301": 4096,
"gpt-3.5-turbo-0613": 4096,
"gpt-3.5-turbo-16k": 16384,
"gpt-3.5-turbo-16k-0613": 16384,
"gpt-35-turbo": 4096,
"gpt-35-turbo-16k": 16384,
"gpt-3.5-turbo-1106": 16384,
"gpt-4-0314": 8192,
"gpt-4": 8192,
"gpt-4-32k": 32768,
"gpt-4-32k-0314": 32768,
"gpt-4-0613": 8192,
"gpt-4-turbo-preview": 128000,
"gpt-4-0125-preview": 128000,
"gpt-4-turbo-preview": 128000,
"gpt-4-1106-preview": 128000,
"gpt-4-vision-preview": 128000,
"gpt-4-1106-vision-preview": 128000,
"gpt-4": 8192,
"gpt-4-0613": 8192,
"gpt-4-32k": 32768,
"gpt-4-32k-0613": 32768,
"gpt-3.5-turbo-0125": 16385,
"gpt-3.5-turbo": 16385,
"gpt-3.5-turbo-1106": 16385,
"gpt-3.5-turbo-instruct": 4096,
"gpt-3.5-turbo-16k": 16385,
"gpt-3.5-turbo-0613": 4096,
"gpt-3.5-turbo-16k-0613": 16385,
"text-embedding-ada-002": 8192,
"glm-3-turbo": 128000,
"glm-4": 128000,
Expand All @@ -179,7 +178,7 @@
}


def count_message_tokens(messages, model="gpt-3.5-turbo-0613"):
def count_message_tokens(messages, model="gpt-3.5-turbo-0125"):
"""Return the number of tokens used by a list of messages."""
try:
encoding = tiktoken.encoding_for_model(model)
Expand Down Expand Up @@ -209,8 +208,8 @@ def count_message_tokens(messages, model="gpt-3.5-turbo-0613"):
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 "gpt-3.5-turbo" == 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")
print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0125.")
return count_message_tokens(messages, model="gpt-3.5-turbo-0125")
elif "gpt-4" == 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")
Expand Down
Loading