mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-06-08 15:05:17 +02:00
fix typo
This commit is contained in:
betterwang
parent
21d588ae0e
commit
ad88c5000d
5 changed files with 37 additions and 37 deletions
|
|
@ -14,9 +14,9 @@ from metagpt.logs import logger
|
|||
async def main():
|
||||
llm = LLM()
|
||||
# llm type check
|
||||
id_ques = "what's your name"
|
||||
logger.info(f"{id_ques}: ")
|
||||
logger.info(await llm.aask(id_ques))
|
||||
question = "what's your name"
|
||||
logger.info(f"{question}: ")
|
||||
logger.info(await llm.aask(question))
|
||||
logger.info("\n\n")
|
||||
|
||||
logger.info(
|
||||
|
|
|
|||
|
|
@ -75,7 +75,7 @@ class BaseLLM(ABC):
|
|||
local_calc_usage (bool): some models don't calculate usage, it will overwrite LLMConfig.calc_usage
|
||||
"""
|
||||
calc_usage = self.config.calc_usage and local_calc_usage
|
||||
model = model if model else self.model
|
||||
model = model or self.model
|
||||
usage = usage.model_dump() if isinstance(usage, BaseModel) else usage
|
||||
if calc_usage and self.cost_manager:
|
||||
try:
|
||||
|
|
@ -83,7 +83,7 @@ class BaseLLM(ABC):
|
|||
completion_tokens = int(usage.get("completion_tokens", 0))
|
||||
self.cost_manager.update_cost(prompt_tokens, completion_tokens, model)
|
||||
except Exception as e:
|
||||
logger.error(f"{self.__class__.__name__} updats costs failed! exp: {e}")
|
||||
logger.error(f"{self.__class__.__name__} updates costs failed! exp: {e}")
|
||||
|
||||
def get_costs(self) -> Costs:
|
||||
if not self.cost_manager:
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ from metagpt.provider.base_llm import BaseLLM, LLMConfig
|
|||
from metagpt.provider.llm_provider_registry import LLMType, register_provider
|
||||
from metagpt.provider.openai_api import log_and_reraise
|
||||
from metagpt.utils.cost_manager import CostManager
|
||||
from metagpt.utils.token_counter import DashScope_TOKEN_COSTS
|
||||
from metagpt.utils.token_counter import DASHSCOPE_TOKEN_COSTS
|
||||
|
||||
|
||||
def build_api_arequest(
|
||||
|
|
@ -167,7 +167,7 @@ class DashScopeLLM(BaseLLM):
|
|||
def __init_dashscope(self):
|
||||
self.model = self.config.model
|
||||
self.api_key = self.config.api_key
|
||||
self.token_costs = DashScope_TOKEN_COSTS
|
||||
self.token_costs = DASHSCOPE_TOKEN_COSTS
|
||||
self.aclient: AGeneration = AGeneration
|
||||
|
||||
# check support system_message models
|
||||
|
|
|
|||
|
|
@ -22,8 +22,8 @@ from metagpt.provider.llm_provider_registry import register_provider
|
|||
from metagpt.provider.openai_api import log_and_reraise
|
||||
from metagpt.utils.cost_manager import CostManager
|
||||
from metagpt.utils.token_counter import (
|
||||
QianFan_EndPoint_TOKEN_COSTS,
|
||||
QianFan_MODEL_TOKEN_COSTS,
|
||||
QIANFAN_ENDPOINT_TOKEN_COSTS,
|
||||
QIANFAN_MODEL_TOKEN_COSTS,
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -74,8 +74,8 @@ class QianFanLLM(BaseLLM):
|
|||
assert not (self.config.model and self.config.endpoint), "Only set `model` or `endpoint` in the config"
|
||||
assert self.config.model or self.config.endpoint, "Should set one of `model` or `endpoint` in the config"
|
||||
|
||||
self.token_costs = copy.deepcopy(QianFan_MODEL_TOKEN_COSTS)
|
||||
self.token_costs.update(QianFan_EndPoint_TOKEN_COSTS)
|
||||
self.token_costs = copy.deepcopy(QIANFAN_MODEL_TOKEN_COSTS)
|
||||
self.token_costs.update(QIANFAN_ENDPOINT_TOKEN_COSTS)
|
||||
|
||||
# self deployed model on the cloud not to calculate usage, it charges resource pool rental fee
|
||||
self.calc_usage = self.config.calc_usage and self.config.endpoint is None
|
||||
|
|
@ -103,8 +103,8 @@ class QianFanLLM(BaseLLM):
|
|||
|
||||
def _update_costs(self, usage: dict):
|
||||
"""update each request's token cost"""
|
||||
model_or_endpoint = self.config.model if self.config.model else self.config.endpoint
|
||||
local_calc_usage = True if model_or_endpoint in self.token_costs else False
|
||||
model_or_endpoint = self.config.model or self.config.endpoint
|
||||
local_calc_usage = model_or_endpoint in self.token_costs
|
||||
super()._update_costs(usage, model_or_endpoint, local_calc_usage)
|
||||
|
||||
def get_choice_text(self, resp: JsonBody) -> str:
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ TOKEN_COSTS = {
|
|||
QianFan Token Price https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7#tokens%E5%90%8E%E4%BB%98%E8%B4%B9
|
||||
Due to QianFan has multi price strategies, we unify `Tokens post-payment` as a statistical method.
|
||||
"""
|
||||
QianFan_MODEL_TOKEN_COSTS = {
|
||||
QIANFAN_MODEL_TOKEN_COSTS = {
|
||||
"ERNIE-Bot-4": {"prompt": 0.017, "completion": 0.017},
|
||||
"ERNIE-Bot-8k": {"prompt": 0.0034, "completion": 0.0067},
|
||||
"ERNIE-Bot": {"prompt": 0.0017, "completion": 0.0017},
|
||||
|
|
@ -66,35 +66,35 @@ QianFan_MODEL_TOKEN_COSTS = {
|
|||
"Yi-34B-Chat": {"prompt": 0.0, "completion": 0.0},
|
||||
}
|
||||
|
||||
QianFan_EndPoint_TOKEN_COSTS = {
|
||||
"completions_pro": QianFan_MODEL_TOKEN_COSTS["ERNIE-Bot-4"],
|
||||
"ernie_bot_8k": QianFan_MODEL_TOKEN_COSTS["ERNIE-Bot-8k"],
|
||||
"completions": QianFan_MODEL_TOKEN_COSTS["ERNIE-Bot"],
|
||||
"eb-instant": QianFan_MODEL_TOKEN_COSTS["ERNIE-Bot-turbo"],
|
||||
"ai_apaas": QianFan_MODEL_TOKEN_COSTS["EB-turbo-AppBuilder"],
|
||||
"ernie_speed": QianFan_MODEL_TOKEN_COSTS["ERNIE-Speed"],
|
||||
"bloomz_7b1": QianFan_MODEL_TOKEN_COSTS["BLOOMZ-7B"],
|
||||
"llama_2_7b": QianFan_MODEL_TOKEN_COSTS["Llama-2-7B-Chat"],
|
||||
"llama_2_13b": QianFan_MODEL_TOKEN_COSTS["Llama-2-13B-Chat"],
|
||||
"llama_2_70b": QianFan_MODEL_TOKEN_COSTS["Llama-2-70B-Chat"],
|
||||
"chatglm2_6b_32k": QianFan_MODEL_TOKEN_COSTS["ChatGLM2-6B-32K"],
|
||||
"aquilachat_7b": QianFan_MODEL_TOKEN_COSTS["AquilaChat-7B"],
|
||||
"mixtral_8x7b_instruct": QianFan_MODEL_TOKEN_COSTS["Mixtral-8x7B-Instruct"],
|
||||
"sqlcoder_7b": QianFan_MODEL_TOKEN_COSTS["SQLCoder-7B"],
|
||||
"codellama_7b_instruct": QianFan_MODEL_TOKEN_COSTS["CodeLlama-7B-Instruct"],
|
||||
"xuanyuan_70b_chat": QianFan_MODEL_TOKEN_COSTS["XuanYuan-70B-Chat-4bit"],
|
||||
"qianfan_bloomz_7b_compressed": QianFan_MODEL_TOKEN_COSTS["Qianfan-BLOOMZ-7B-compressed"],
|
||||
"qianfan_chinese_llama_2_7b": QianFan_MODEL_TOKEN_COSTS["Qianfan-Chinese-Llama-2-7B"],
|
||||
"qianfan_chinese_llama_2_13b": QianFan_MODEL_TOKEN_COSTS["Qianfan-Chinese-Llama-2-13B"],
|
||||
"chatlaw": QianFan_MODEL_TOKEN_COSTS["ChatLaw"],
|
||||
"yi_34b_chat": QianFan_MODEL_TOKEN_COSTS["Yi-34B-Chat"],
|
||||
QIANFAN_ENDPOINT_TOKEN_COSTS = {
|
||||
"completions_pro": QIANFAN_MODEL_TOKEN_COSTS["ERNIE-Bot-4"],
|
||||
"ernie_bot_8k": QIANFAN_MODEL_TOKEN_COSTS["ERNIE-Bot-8k"],
|
||||
"completions": QIANFAN_MODEL_TOKEN_COSTS["ERNIE-Bot"],
|
||||
"eb-instant": QIANFAN_MODEL_TOKEN_COSTS["ERNIE-Bot-turbo"],
|
||||
"ai_apaas": QIANFAN_MODEL_TOKEN_COSTS["EB-turbo-AppBuilder"],
|
||||
"ernie_speed": QIANFAN_MODEL_TOKEN_COSTS["ERNIE-Speed"],
|
||||
"bloomz_7b1": QIANFAN_MODEL_TOKEN_COSTS["BLOOMZ-7B"],
|
||||
"llama_2_7b": QIANFAN_MODEL_TOKEN_COSTS["Llama-2-7B-Chat"],
|
||||
"llama_2_13b": QIANFAN_MODEL_TOKEN_COSTS["Llama-2-13B-Chat"],
|
||||
"llama_2_70b": QIANFAN_MODEL_TOKEN_COSTS["Llama-2-70B-Chat"],
|
||||
"chatglm2_6b_32k": QIANFAN_MODEL_TOKEN_COSTS["ChatGLM2-6B-32K"],
|
||||
"aquilachat_7b": QIANFAN_MODEL_TOKEN_COSTS["AquilaChat-7B"],
|
||||
"mixtral_8x7b_instruct": QIANFAN_MODEL_TOKEN_COSTS["Mixtral-8x7B-Instruct"],
|
||||
"sqlcoder_7b": QIANFAN_MODEL_TOKEN_COSTS["SQLCoder-7B"],
|
||||
"codellama_7b_instruct": QIANFAN_MODEL_TOKEN_COSTS["CodeLlama-7B-Instruct"],
|
||||
"xuanyuan_70b_chat": QIANFAN_MODEL_TOKEN_COSTS["XuanYuan-70B-Chat-4bit"],
|
||||
"qianfan_bloomz_7b_compressed": QIANFAN_MODEL_TOKEN_COSTS["Qianfan-BLOOMZ-7B-compressed"],
|
||||
"qianfan_chinese_llama_2_7b": QIANFAN_MODEL_TOKEN_COSTS["Qianfan-Chinese-Llama-2-7B"],
|
||||
"qianfan_chinese_llama_2_13b": QIANFAN_MODEL_TOKEN_COSTS["Qianfan-Chinese-Llama-2-13B"],
|
||||
"chatlaw": QIANFAN_MODEL_TOKEN_COSTS["ChatLaw"],
|
||||
"yi_34b_chat": QIANFAN_MODEL_TOKEN_COSTS["Yi-34B-Chat"],
|
||||
}
|
||||
|
||||
"""
|
||||
DashScope Token price https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
|
||||
Different model has different detail page. Attention, some model are free for a limited time.
|
||||
"""
|
||||
DashScope_TOKEN_COSTS = {
|
||||
DASHSCOPE_TOKEN_COSTS = {
|
||||
"qwen-turbo": {"prompt": 0.0011, "completion": 0.0011},
|
||||
"qwen-plus": {"prompt": 0.0028, "completion": 0.0028},
|
||||
"qwen-max": {"prompt": 0.0, "completion": 0.0},
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue