Skip to content

Reference architecture/design to delineate the various types of information a Large Language Model (LLM) utilizes to generate responses.

Notifications You must be signed in to change notification settings

opdev/context-window-architecture

Repository files navigation

Context Window Architecture

Overview

[Provide a brief overview of your project here. Describe its purpose, goals, and any key features.]

Prerequisites

Before you begin, ensure you have met the following requirements:

  • Python: Make sure you have Python installed on your system. You can download it from python.org.
  • Dependencies: Install any necessary project dependencies. You can typically do this by running:
    pip install -r requirements.txt
    (If you don't have a requirements.txt file, you should create one!)
  • Run prerequisite scripts: Execute the following scripts located in the prereqs folder to set up necessary components:
    • python prereqs/setup_sqldb.py
    • python prereqs/setup_vectordb.py

Installation

  1. Clone the repository:
    git clone [URL_OF_YOUR_REPOSITORY]
    cd [REPOSITORY_NAME]
  2. Set up a virtual environment (recommended):
    python -m venv venv
    source venv/bin/activate  # On Windows use `venv\Scripts\activate`
  3. Install dependencies:
    pip install -r requirements.txt

Usage

[Explain how to use your project. Provide examples or code snippets if applicable.]

Contributing

[Explain how others can contribute to your project. This might include information on:]

  • Reporting bugs
  • Suggesting enhancements
  • Submitting pull requests

License

[Specify the license for your project, e.g., MIT, Apache 2.0, GPLv3. If you don't have one, consider adding one.]

Shoulders of Giants

Context Window Architecture would not be possible if not for all of the great research, development, and thought leadership of others. Please see SHOULDERS.md to see a list of them.

About

Reference architecture/design to delineate the various types of information a Large Language Model (LLM) utilizes to generate responses.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages