ComfyUI Node: ChatGPT & Local LLM ♾️Mixlab

ChatGPT & Local LLM ♾️Mixlab:

ChatGPTOpenAI is a versatile node designed to facilitate seamless interaction with various AI models, including OpenAI's ChatGPT and other compatible models like ZhipuAI and LLaMA. This node allows you to generate contextual text responses based on user prompts and system-defined instructions. It is particularly useful for creating dynamic and interactive AI-driven content, making it an invaluable tool for AI artists and developers looking to integrate sophisticated conversational capabilities into their projects. By leveraging this node, you can easily manage session histories, customize system messages, and select from a range of AI models to suit your specific needs.

ChatGPT & Local LLM ♾️Mixlab Input Parameters:

api_key

The api_key parameter is a string that serves as your authentication token for accessing the AI model's API. This key is essential for verifying your identity and granting you access to the model's capabilities. Ensure that your API key is kept secure and is not shared publicly.

api_url

The api_url parameter is a string that specifies the endpoint URL for the API you are using. This URL directs the node to the appropriate server for processing your requests. If you are using a custom or Azure-based endpoint, make sure to provide the correct URL here.

prompt

The prompt parameter is a string that contains the user input or query that you want the AI model to respond to. This is the main content that drives the interaction and determines the context of the generated response. The prompt should be clear and concise to elicit the best possible answer from the model.

system_content

The system_content parameter is a string that defines the initial system message or instruction given to the AI model. This message sets the tone and context for the conversation, guiding the model on how to respond. The default value is "You are ChatGPT, a large language model trained by OpenAI. Answer as concisely as possible."

model

The model parameter allows you to select the AI model you wish to use for generating responses. Options include models like "gpt-3.5-turbo" and others from the llama_modes_list. The default model is typically the first one in the list. Choose the model that best fits your requirements for the task at hand.

seed

The seed parameter is an integer that sets the random seed for the model's response generation. This can be useful for ensuring reproducibility of results. The default value is 0, with a minimum of 0 and a maximum of 0xffffffffffffffff.

context_size

The context_size parameter is an integer that determines the number of previous messages to include in the session history for context. This helps the model maintain continuity in the conversation. The default value is 1, with a minimum of 0 and a maximum of 30.

ChatGPT & Local LLM ♾️Mixlab Output Parameters:

text

The text output parameter is a string that contains the generated response from the AI model. This is the main output that you will use in your application or project.

messages

The messages output parameter is a string that includes the entire conversation history, formatted as a list of messages. This can be useful for debugging or for maintaining a record of the interaction.

session_history

The session_history output parameter is a string that captures the updated session history, including the latest user prompt and the model's response. This helps in maintaining context for future interactions.

ChatGPT & Local LLM ♾️Mixlab Usage Tips:

• Ensure your api_key is valid and has the necessary permissions to access the chosen AI model.
• Use clear and concise prompts to get the most accurate and relevant responses from the model.
• Adjust the context_size parameter to include more or fewer previous messages based on the complexity of the conversation you are aiming to maintain.
• Experiment with different models to find the one that best suits your specific needs and provides the most satisfactory results.

ChatGPT & Local LLM ♾️Mixlab Common Errors and Solutions:

"API finished with unexpected reason: <reason>"

• Explanation: This error occurs when the API response does not end with the expected "stop" reason.
• Solution: Check the API documentation for possible finish reasons and ensure your prompt and system messages are well-formed.

"AuthenticationError"

• Explanation: This error indicates that there is an issue with your API key.
• Solution: Verify that your API key is correct and has the necessary permissions. If the problem persists, contact the API provider for support.

"HTTPError" or "OpenAIError"

• Explanation: These errors occur when there is an issue with the API request, such as network problems or server errors.
• Solution: Ensure your network connection is stable and retry the request. If the error persists, check the API provider's status page for any ongoing issues.

"API key is invalid or missing"

• Explanation: This error indicates that the provided API key is either incorrect or not provided.
• Solution: Double-check the API key for any typos and ensure it is correctly entered in the api_key parameter.