apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-06-08 15:05:17 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

- updated MAX-TOKEN according to openai document

Browse source 
- minior optimization of code style
- fixed issues `RuntimeError: fail to reduce message length`
This commit is contained in:
Azure Wang 2024-03-11 22:27:59 +08:00
parent 5e02f4c92a
commit 6487ae84b0
4 changed files with 20 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

2
metagpt/actions/research.py
View file

@ -134,7 +134,7 @@ class CollectLinks(Action):
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, 0)
logger.debug(prompt)
queries = await self._aask(prompt, [system_text])
try:

3
metagpt/config2.py
View file

@ -92,7 +92,7 @@ class Config(CLIParams, YamlModel):
"""
default_config_paths: List[Path] = [
METAGPT_ROOT / "config/config2.yaml",
Path.home() / ".metagpt/config2.yaml",
CONFIG_ROOT / "config2.yaml",
]
dicts = [dict(os.environ)]
@ -134,4 +134,3 @@ def merge_dict(dicts: Iterable[Dict]) -> Dict:
return result
config = Config.default()

33
metagpt/utils/token_counter.py
View file

@ -140,25 +140,24 @@ FIREWORKS_GRADE_TOKEN_COSTS = {
"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,
@ -179,7 +178,7 @@ TOKEN_MAX = {
}
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)
@ -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")

3
tests/mock/mock_llm.py
View file

@ -1,13 +1,14 @@
import json
from typing import Optional, Union
from metagpt.config2 import config
from metagpt.config2 import Config
from metagpt.configs.llm_config import LLMType
from metagpt.logs import logger
from metagpt.provider.azure_openai_api import AzureOpenAILLM
from metagpt.provider.openai_api import OpenAILLM
from metagpt.schema import Message
config = Config.default()
OriginalLLM = OpenAILLM if config.llm.api_type == LLMType.OPENAI else AzureOpenAILLM