ComfyUI Node: LLM Chat

LLM Chat:

LF_LLMChat is a node designed to facilitate interaction with a local Language Model (LLM) by processing chat data. This node is particularly useful for AI artists who want to integrate conversational AI into their projects, enabling dynamic and context-aware dialogues. The primary function of LF_LLMChat is to parse and manage chat histories, extracting key elements such as the last message, the last user message, and the last LLM message. This allows for a seamless and organized way to handle chat data, making it easier to create engaging and interactive experiences. By leveraging this node, you can enhance your projects with sophisticated conversational capabilities, ensuring that the dialogue flows naturally and contextually.

LLM Chat Input Parameters:

KUL_CHAT

This parameter represents the chat data in JSON format. It is essential for the node's execution as it contains the entire conversation history that the node will process. The chat data should include messages with roles (e.g., user, llm) and content. The default value is an empty string, and it is crucial to provide valid JSON data to avoid errors. This parameter impacts the node's ability to extract and return meaningful chat information, making it a critical input for the node's functionality.

LLM Chat Output Parameters:

chat_history_json

This output provides the entire chat history in JSON format. It is useful for storing or further processing the complete conversation data.

last_message

This output returns the content of the last message in the chat history. It helps in understanding the most recent interaction in the conversation.

last_user_message

This output gives the content of the last message sent by the user. It is important for identifying the user's most recent input, which can be used to generate appropriate responses.

last_llm_message

This output provides the content of the last message sent by the LLM. It is essential for understanding the LLM's most recent response in the conversation.

all_messages

This output returns a JSON string containing all the messages' content from the chat history. It is useful for analyzing the entire conversation in a simplified format.

LLM Chat Usage Tips:

• Ensure that the KUL_CHAT input parameter is provided in a valid JSON format to avoid errors during execution.
• Use the last_user_message and last_llm_message outputs to maintain context in your conversations, allowing for more coherent and contextually relevant interactions.
• Leverage the all_messages output to analyze the entire conversation history, which can be useful for debugging or improving the dialogue flow.

LLM Chat Common Errors and Solutions:

It looks like the chat is empty!

• Explanation: This error occurs when the KUL_CHAT input parameter is either empty or not in a valid JSON format.
• Solution: Ensure that you provide a valid JSON string containing the chat data in the KUL_CHAT input parameter.

Invalid config format

• Explanation: This error indicates that the configuration data provided is not in a valid JSON format.
• Solution: Verify that the configuration data is correctly formatted as JSON before providing it to the node.

You must choose a character

• Explanation: This error occurs when the configuration data does not specify a character for the conversation.
• Solution: Ensure that the configuration data includes a valid character identifier.

Character with id <id> not found in dataset

• Explanation: This error indicates that the specified character ID does not exist in the provided dataset.
• Solution: Check the dataset to ensure that the character ID is correct and exists within the dataset.

It looks like the chat with <character_name> is empty

• Explanation: This error occurs when the chat data for the specified character is empty or not found.
• Solution: Ensure that the chat data for the specified character is correctly provided and not empty.