Skip to content

AI Retrieval Augmented Generation on Obsidian notes

Notifications You must be signed in to change notification settings

Normandabald/obsidisearch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Obsidisearch

This is a Python app that provides an interface for a personal Obsidian notebook. The app allows a user to ask a question, and the app will answer it using the information in the notebook.

Installation

To install the app, follow these steps:

  1. Clone the repository to your local machine.
  2. Create a virtual environment by running python -m pipenv obsidisearch.
  3. Activate the virtual environment by running python -m pipenv shell.
  4. Edit the config.yaml file with the required options

Usage

To use the app, follow these steps:

  1. Start the app by running python obsidisearch.py within the virtual environment.
  2. Enter a question when prompted.
  3. The app will provide an answer based on the information in the notebook.
  4. The app will create a data file in the persistence_directory directory. This file will be used to store the information that the app has learned from the notebook. If you want to reset the app or have added new notes, simply delete this file and restart the app.

Configuration

The config.yaml file contains the following options:

  • openai_api_key: Your OpenAI API key.
  • obisidian_directory: The directory path where your Obsidian notes are stored.
  • persistence_directory: The directory path where the app will store its data.
  • use_chat_model: Whether to use a chat model or not.
  • openai_model: The OpenAI model to use for generating answers.
  • temperature: The temperature to use when generating answers.
  • prompt: The prompt to use when generating answers.

About

AI Retrieval Augmented Generation on Obsidian notes

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages