apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-05-05 13:52:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "Feat add qianfan api support"

Browse source
This commit is contained in:
better629 2024-02-08 07:32:34 +08:00 • committed by GitHub
parent 351b3ae8df
commit 5a2084cda8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 319 additions and 574 deletions
Download patch file Download diff file Expand all files Collapse all files

4
metagpt/utils/cost_manager.py
View file

@ -29,7 +29,6 @@ class CostManager(BaseModel):
total_budget: float = 0
max_budget: float = 10.0
total_cost: float = 0
token_costs: dict[str, dict[str, float]] = TOKEN_COSTS
def update_cost(self, prompt_tokens, completion_tokens, model):
"""
@ -47,8 +46,7 @@ class CostManager(BaseModel):
return
cost = (
prompt_tokens * self.token_costs[model]["prompt"]
+ completion_tokens * self.token_costs[model]["completion"]
prompt_tokens * TOKEN_COSTS[model]["prompt"] + completion_tokens * TOKEN_COSTS[model]["completion"]
) / 1000
self.total_cost += cost
logger.info(

53
metagpt/utils/token_counter.py
View file

@ -38,59 +38,6 @@ 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 = {
"ERNIE-Bot-4": {"prompt": 0.017, "completion": 0.017},
"ERNIE-Bot-8k": {"prompt": 0.0034, "completion": 0.0067},
"ERNIE-Bot": {"prompt": 0.017, "completion": 0.017},
"ERNIE-Bot-turbo": {"prompt": 0.0011, "completion": 0.0011},
"EB-turbo-AppBuilder": {"prompt": 0.0011, "completion": 0.0011},
"ERNIE-Speed": {"prompt": 0.00056, "completion": 0.0011},
"BLOOMZ-7B": {"prompt": 0.00056, "completion": 0.00056},
"Llama-2-7B-Chat": {"prompt": 0.00056, "completion": 0.00056},
"Llama-2-13B-Chat": {"prompt": 0.00084, "completion": 0.00084},
"Llama-2-70B-Chat": {"prompt": 0.0049, "completion": 0.0049},
"ChatGLM2-6B-32K": {"prompt": 0.00056, "completion": 0.00056},
"AquilaChat-7B": {"prompt": 0.00056, "completion": 0.00056},
"Mixtral-8x7B-Instruct": {"prompt": 0.0049, "completion": 0.0049},
"SQLCoder-7B": {"prompt": 0.00056, "completion": 0.00056},
"CodeLlama-7B-Instruct": {"prompt": 0.00056, "completion": 0.00056},
"XuanYuan-70B-Chat-4bit": {"prompt": 0.0049, "completion": 0.0049},
"Qianfan-BLOOMZ-7B-compressed": {"prompt": 0.00056, "completion": 0.00056},
"Qianfan-Chinese-Llama-2-7B": {"prompt": 0.00056, "completion": 0.00056},
"Qianfan-Chinese-Llama-2-13B": {"prompt": 0.00084, "completion": 0.00084},
"ChatLaw": {"prompt": 0.0011, "completion": 0.0011},
"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"],
}
TOKEN_MAX = {
"gpt-3.5-turbo": 4096,
"gpt-3.5-turbo-0301": 4096,