Agent Prompter

This node supplies an LLM agent with a set of tools and the conversation history, and prompts it with the user-provided query.

The conversation table is expected to have at least two string columns that define previous conversation. If this is the start of the conversation, the conversation table can be empty.

The agent always receives the full conversation table as context, which can lead to slower execution times for longer conversations, or execution failures if the context becomes too large for the LLM. If you experience such issues, you can truncate the conversation table by only keeping the last few messages, or use an LLM to summarize the conversation held so far.

Note: If you use the Credentials Configuration node and do not select the "Save password in configuration (weakly encrypted)" option for passing the API key for the LLM, the Credentials Configuration node will need to be reconfigured upon reopening the workflow, as the credentials flow variable was not saved and will therefore not be available to downstream nodes.

Options

Enable debug output

If checked, prints the output of LangChain's debug mode to the console.

Conversation settings

Message roles column

Select the column that specifies the alternating sender roles assigned to each message. Example values are 'Human' and 'AI'.

Messages column

Select the column containing the messages composing the conversation history.

Prompt Settings

New message

Specify the new message to be sent to the agent.

Input Ports

Icon

The agent to prompt.

Icon

The tools the agent can use.

Icon

Table containing the conversation history. Has to contain at least two string columns, which can be empty if this is the beginning of the conversation.

Output Ports

Icon

The conversation table extended by two rows. One row for the user's prompt and one row for the agent's response. Can be used as input in subsequent Agent Prompter executions to continue the conversation further.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

This node has no views

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.