The AIAssistant class, an alternative to the OpenAI Assistant API, is designed for those who prefer using large language models (LLMs) other than those provided by OpenAI. It facilitates the creation of AI Assistants with several key benefits:

  • Visibility into Citations: It offers transparent access to the sources and citations used by the AI, enhancing the understanding and trustworthiness of its responses.

  • Debugging Capabilities: Users have the ability to delve into and debug the AIโ€™s processes, allowing for a deeper understanding and fine-tuning of its performance.

  • Customizable Prompts: The class provides the flexibility to modify and tailor prompts according to specific needs, enabling more precise and relevant interactions.

  • Chain of Thought Integration: It supports the incorporation of a โ€˜chain of thoughtโ€™ approach, which helps in breaking down complex queries into simpler, sequential steps, thereby improving the clarity and accuracy of responses.

It is ideal for those who value customization, transparency, and detailed control over their AI Assistantโ€™s functionalities.

Arguments

name
string

Name for your AI assistant

instructions
string

How the Assistant and model should behave or respond

assistant_id
string

Load existing AI Assistant. If you pass this, you donโ€™t have to pass other arguments.

thread_id
string

Existing thread id if exists

yaml_path
str

Embedchain pipeline config yaml path to use. This will define the configuration of the AI Assistant (such as configuring the LLM, vector database, and embedding model)

data_sources
list
default: "[]"

Add data sources to your assistant. You can add in the following format: [{"source": "https://example.com", "data_type": "web_page"}]

collect_metrics
boolean
default: "True"

Anonymous telemetry (doesnโ€™t collect any user information or userโ€™s files). Used to improve the Embedchain package utilization. Default is True.

Usage

For detailed guidance on creating your own AI Assistant, click the link below. It provides step-by-step instructions to help you through the process:

Guide to Creating Your AI Assistant

Learn how to build a customized AI Assistant using the AIAssistant class.