search

gpsandhu23 / TARS

Personal AI helper
0 stars 0 forks source link

Sweep: Can you please write the README.md file based on your understanding of the project #41

Closed gpsandhu23 closed 6 months ago

gpsandhu23 commented 6 months ago

Can you please update the README.md file for this project

Checklist - [X] Modify `README.md` ✓ https://github.com/gpsandhu23/TARS/commit/fff1b70fe412128e6666bd58730faaa22bcc7108 [Edit](https://github.com/gpsandhu23/TARS/edit/sweep/can_you_please_write_the_readmemd_file_b/README.md)
sweep-ai[bot] commented 6 months ago

🚀 Here's the PR! #43

See Sweep's progress at the progress dashboard!
💎 Sweep Pro: I'm using GPT-4. You have unlimited GPT-4 tickets. (tracking ID: 9beb224cc1)
Install Sweep Configs: Pull Request

[!TIP] I can email you next time I complete a pull request if you set up your email here!

Actions (click)

Step 1: 🔎 Searching

I found the following snippets in your repository. I will now analyze these snippets and come up with a plan.

Some code snippets I think are relevant in decreasing order of relevance (click to expand). If some file is missing from here, you can mention the path in the ticket description. https://github.com/gpsandhu23/TARS/blob/fa727fb8370204b1019f258eaaa9792322902691/README.md#L1-L1 https://github.com/gpsandhu23/TARS/blob/fa727fb8370204b1019f258eaaa9792322902691/TARS/graphs/custom_tools.py#L1-L331 https://github.com/gpsandhu23/TARS/blob/fa727fb8370204b1019f258eaaa9792322902691/TARS/surfaces/web/web.py#L1-L43

Step 2: ⌨️ Coding

Replace the existing README content with an updated, comprehensive README file.

Update with the full contents of README.md:

# TARS AI Agent to help with stuff like email, Slack, Twitter, etc. # TARS - Your AI Assistant TARS is an AI-powered assistant that helps you manage your digital life across email, Slack, Twitter, and more. It leverages advanced language models and a extensible tool system to understand your requests and take appropriate actions on your behalf. ## Key Features - Natural language interaction via Slack, web interface, and other surfaces - Intelligent email management - summarization, classification, response suggestions - Integration with Slack for managing messages and notifications - Customizable tools for extending TARS' capabilities ## Architecture Overview TARS consists of the following main components: - **Agent**: The core intelligence that understands user requests and determines the appropriate actions to take. Implemented using the `AgentManager` class in `graphs/agent.py`. - **Tools**: Modular functions that the agent can use to perform specific tasks, such as fetching emails, posting Slack messages, reading images, etc. Defined in `graphs/custom_tools.py`. - **Surfaces**: Interfaces for users to interact with TARS, currently supporting Slack and a web interface. Implemented in the `surfaces/` directory. ## Setup and Installation 1. Clone the repository: `git clone https://github.com/yourusername/TARS.git` 2. Install the required dependencies: `pip install -r requirements.txt` 3. Set up the necessary API credentials: - Gmail API: Follow the instructions in `retrievers/gmail.py` to set up Gmail API access. - Slack API: Set the `SLACK_BOT_TOKEN` and `SLACK_USER_TOKEN` environment variables with your Slack app credentials. - OpenAI API: Set the `OPENAI_API_KEY` environment variable with your OpenAI API key. 4. Run the web interface: `streamlit run surfaces/web/web.py` ## Usage Examples Here's an example of how to interact with TARS via the web interface: 1. Go to `http://localhost:8501` in your web browser. 2. Type in a request, such as "Summarize my unread emails from the past day". 3. Click the "Send" button to submit your request. 4. TARS will process your request and display the response in the chat interface. ## Contributing We welcome contributions to help improve TARS! To get started: 1. Fork the repository and create a new branch for your feature or bug fix. 2. Make your changes, following the existing code style and conventions. 3. Write tests to cover your changes and ensure that the existing tests still pass. 4. Submit a pull request describing your changes and why they should be merged. ## Directory Structure - `graphs/`: Contains the core agent logic and tool definitions. - `retrievers/`: Modules for retrieving data from external sources (Gmail, Google Calendar, etc.) - `surfaces/`: User interface implementations (Slack, web).

Step 3: 🔁 Code Review

I have finished reviewing the code for completeness. I did not find errors for sweep/can_you_please_write_the_readmemd_file_b.

🎉 Latest improvements to Sweep:
  • New dashboard launched for real-time tracking of Sweep issues, covering all stages from search to coding.
  • Integration of OpenAI's latest Assistant API for more efficient and reliable code planning and editing, improving speed by 3x.
  • Use the GitHub issues extension for creating Sweep issues directly from your editor.

💡 To recreate the pull request edit the issue title or description. Something wrong? Let us know.

This is an automated message generated by Sweep AI.