Go to file
Zeke Zhang cda9ee2b95
Update issue templates
first created issue tempalates
2023-03-21 22:27:44 +11:00
.core Merge branch 'main' into Major_Dev 2023-03-04 04:22:11 +11:00
.github/ISSUE_TEMPLATE Update issue templates 2023-03-21 22:27:44 +11:00
.locals fix: no translation .mo file find 2023-02-23 19:12:13 +11:00
batch-programs fix: trying to access __pycache__ when update language base 2023-02-21 02:55:30 +11:00
Documentation doc: update README.md 2023-03-04 04:15:24 +11:00
example_prompt trans: add example prompt for newly supported language 2023-02-21 04:15:14 +11:00
GPT fix: non stream mode cannot use gpt-3.5 2023-03-04 03:38:43 +11:00
modules Revert "Revert "Revert "fix: tokens not display if brain is not build yet""" 2023-03-04 03:18:53 +11:00
pages refactor: change function name 2023-02-26 17:27:14 +11:00
streamlit_toolkit fix: not able to find API key 2023-03-10 11:56:23 +11:00
.gitattributes Initial commit 2023-02-10 01:46:55 +11:00
.gitignore build: update gitignore 2023-02-23 21:29:30 +11:00
initial_file_creator.py fix: cannot create API-KEYS.txt 2023-02-23 20:40:22 +11:00
LICENSE Initial commit 2023-02-10 01:46:55 +11:00
README.md doc: update README.md 2023-03-04 04:15:24 +11:00
requirements.txt build: add tiktoken library 2023-03-04 01:53:25 +11:00
RUN.bat refactor: rename important batch files 2023-02-23 21:59:58 +11:00
Seanium_Brain.py chore: change default stream mode to true 2023-03-04 03:41:32 +11:00
SETUP.bat refactor: rename important batch files 2023-02-23 21:59:58 +11:00
update.bat chore: remove pause 2023-03-04 03:25:42 +11:00

🧠 GPT Brain

python

中文说明 | 日本語説明書 | English

Like this repo? please consider a star!

💡This project is inspired by youtuber All About AI's video on Second Brain. Please consider support him!

💡As I am not a professional programmer and am fairly new to Python, this project may contain bugs. If you encounter any issues, please suggest them in the Issues section.

Description

This program leverages the power of GPT-3 & 3.5 to provide a summary of the content of atomic notes, as well as answer questions related specifically to your notes. The program scans a designated directory, which is typically a vault containing multiple notes, and appends the contents of all the notes to a single file. This file then serves as the context for the user's query. The program is able to identify relationships between the contents of the notes, and generate a refined response that summarizes the key points.

Although the program is compatible with other note-taking software that uses markdown or txt, it is primarily designed with Obsidian in mind.

Feature

  • Use OpenAI GPT-3 and GPT-3.5 (ChatGPT) to generate response.
  • Use OpenAI embedding for semetic comparison of question and note content for enhanced searching.
  • Configurable prompts.
  • Customizable personal background information for more accurate answers.
  • Integration with Obsidian note local directory for easy note content updates.
  • Note content preview & content modification.
  • Section parsing using delimiters for targeted updates.
  • Obsidian YAML frontmatter filtering.
  • OpenAI API key management.
  • OpenAI Language model selection for different needs.
  • Basic & Advanced parameter sliders for OpenAI Language model configurations.

Todo

  • Support PDF format。
  • Support PDF OCR scan。
  • Support Word document。

Install

1. What you need

2. Set up the project for the first time

  1. Download the project
  2. Run SETUP.bat
  3. Enter your OpenAI API Key

3. Run

  • Execute RUN.bat

Demo

Main Page

screenshot1

Brain Memory

screenshot2