def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
tools: Optional[list[PromptMessageTool]] = None) -> int:
"""
Get number of tokens for given prompt messages
:param model: model name
:param credentials: model credentials
:param prompt_messages: prompt messages
:param tools: tools for tool calling
:return:
"""
@property
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
"""
Map model invoke error to unified error
The key is the error type thrown to the caller
The value is the error type thrown by the model,
which needs to be converted into a unified error type for the caller.
:return: Invoke error mapping
"""
3. 添加预定义模型配置
claude-3-5-sonnet-20240620 模型示例代码:
model: claude-3-5-sonnet-20240620
label:
en_US: claude-3-5-sonnet-20240620
model_type: llm
features:
- agent-thought
- vision
- tool-call
- stream-tool-call
- document
model_properties:
mode: chat
context_size: 200000
parameter_rules:
- name: temperature
use_template: temperature
- name: top_p
use_template: top_p
- name: top_k
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
en_US: Only sample from the top K options for each subsequent token.
required: false
- name: max_tokens
use_template: max_tokens
required: true
default: 8192
min: 1
max: 8192
- name: response_format
use_template: response_format
pricing:
input: '3.00'
output: '15.00'
unit: '0.000001'
currency: USD