NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
DeepSeek connects to a Nagent workspace with an API key. Once it is connected, agents can call 4 DeepSeek actions, such as "Create Anthropic Message", "Create Chat Completion" and "Get User Balance". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against DeepSeek, with input parameters and output schema.
DEEPSEEK_CREATE_ANTHROPIC_MESSAGETool to create a model response using DeepSeek's Anthropic-compatible API format with support for system prompts, tool calling, streaming, and thinking mode. Use when you need to generate chat completions using the Anthropic Messages API format. Requires base_url='https://api.deepseek.com/anthropic' or metadata base_url ending with '/anthropic'. Supports extended thinking, function calling with tools, and streaming responses. Note: Images and documents are not supported in content blocks.
Input parameters
Model identifier. Use 'deepseek-chat' or 'deepseek-reasoner'. Unsupported model names automatically default to 'deepseek-chat'.
Array of tool definitions for function calling. Each tool has a name, description, and input_schema.
Nucleus sampling parameter. Controls diversity via cumulative probability.
Whether to incrementally stream the response using server-sent events. If true, response will be streamed.
System prompt providing context or instructions to the model. Can be a string or array of content blocks.
Array of input messages with alternating user/assistant roles. Each message must have a role ('user' or 'assistant') and content (text only; images/documents not supported).
Configuration for extended thinking mode.
Maximum number of tokens to generate before stopping.
Randomness in response generation. Range 0.0-2.0. Lower values make output more deterministic.
How the model should use provided tools. Can be 'auto', 'any', 'none', or a ToolChoiceConfig object specifying a specific tool.
Custom text sequences that will cause the model to stop generating.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DEEPSEEK_CREATE_CHAT_COMPLETIONTool to create a chat completion using DeepSeek models (deepseek-chat or deepseek-reasoner). Use when you need to generate AI responses to chat conversations. Supports streaming, tool/function calling, and various parameters to control generation behavior (temperature, max_tokens, etc.).
Input parameters
Up to 16 sequences where the API will stop generating further tokens.
The model to use for generation. Choose 'deepseek-chat' for general use or 'deepseek-reasoner' for reasoning tasks.
A list of tools (max 128) the model may call. Each tool defines a function the model can invoke.
Nucleus sampling parameter. The model considers tokens with top_p probability mass.
If true, partial message deltas will be sent as server-sent events.
If true, returns log probabilities of the output tokens.
A list of messages comprising the conversation. Must contain at least one message.
Configuration for thinking mode.
The maximum number of tokens to generate in the chat completion.
What sampling temperature to use, between 0 and 2. Higher values make output more random.
Controls which (if any) function is called. Options: 'none', 'auto', 'required', or specify a particular function.
Number of most likely tokens to return at each position (0-20). Requires logprobs=true.
Configuration for streaming options.
Configuration for response format.
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DEEPSEEK_GET_USER_BALANCETool to get user's current account balance including granted and topped-up balances with detailed breakdown by currency (CNY or USD). Use when you need to check if the user has sufficient balance for API calls or to view detailed balance information.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DEEPSEEK_LIST_MODELSTool to list currently available DeepSeek models and provides basic information about each one such as the owner and availability. Use when you need to discover which models are available for API calls.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 4 DeepSeek actions on Nagent, including "Create Anthropic Message", "Create Chat Completion" and "Get User Balance". Create Anthropic Message: Create a model response using DeepSeek's Anthropic-compatible API format with support for system prompts, tool calling, streaming, and thinking mode. Each action is listed on this page with its input parameters and its output.
DeepSeek connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Create Anthropic Message takes 3 required inputs: model, messages and max_tokens. It also takes 8 optional inputs: tools, top_p, stream, system, thinking, temperature, tool_choice and stop_sequences. It returns data, error and successful.