AI EMAIL: The AI Agent for Parsing Your Emails

I have recently released AI Email, an AI agent based on Chatgpt which is capable of connecting to yorìur GMAIl account and read your emails. You can find the codes on GitHub. The Web interafce is built using Gradio.

How Does It Work?

The Agent can be prompted with authors or topics of interest, and with topics/authors that the user is not interested about. The architecture comprises 4 main elents:
Emailer class to establish the connection to GMAIL account and read emails. It is also responible for modifying the emails (e.g. set as read and move to trash). For each email message, it returns a dictionary containing the email author, the topic/title, the date of receipt, and the content of the email.
Author/Topic Checker: a ChatGPT-based LLM that checks whether or not the author and content of the email message are within those of interest for the user.
Interest Scorer: another LLM that given the list of authors/topics of interest scores the emial message giving a probability score between 0 and 1, with 1 representing the highest interest.
Summarizer: if the email message is considered relavent by the Interest Scorer, the full email content is passed to the summarizer in order for it to provide the main key points of the email.

The emails that are not considered of interest will be directly sent to trash.

In order for the user to be aware of the behaviour of the agents, the Gradio web app will return a list of both the discarded messages and those considered of interest, with the corresponding summary.

SumMario: The AI Agent for Text Summarization and Information Retrieval

I have recently released SumMario, an AI agent based on Chatgpt which is capable of searching the internet for news, summarizing the news, summarizing Youtube video contents, and read txt, ppt, pdf files. You can find the codes on GitHub.

SumMario also acts as a personal assistant, being able to access its memory and keep conversating with the user about the stored data.

Here is a short demo of it for extracting daily news from the web and chatting about the obtained data.

SumMario example

How Does It Work?

SumMario relies on the lastest LLM technology like ChatGPT. It is a web-based agent, developed using Gradio, and LangChain for the integration of GPT agents.

SumMario is made of 3 different agents: SuperAgentDataRetriever, and ConversationalAgent.

The SuperAgent is the higher level AI agent responsible for managing the DataRetriever and the ConversationalAgent. Basically, it uses the other two agents as tools and, given specific prompts as system message and the user message, it is able to select which agent to choose to complete a task.

The ConversationalAgent is a basic Chatbot based on GPT. It’s purpose is to use directly LLM knowledge and reasoning skills to complete the user’s requirements. It has no access to external tools but only to its stored memory.

The DataRetriever, instead, is an AI agent with access to tools. The tools include GoogleWebSearch, WebPageSummarizer, VideoSummarizer, FileReader. Given the user’s query, the DataRetirever is thus able to select the proper tool and extract text from the source, it being a web page, a Youtube video, or a local file (pdf, ppt, word).

Each tool of the DataRetriever stores extracted text from the sources in a local temporary txt file. This file is accessible to the SuperAgent too, which, on instruction of the SuperAgent, can open the temporary txt file and help the DataRetriever complete the user’s defined task.