Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
LLM for Long Text Summary (Comprehensive Bulleted Notes)
| Date | Stars |
|---|---|
| 2026-07-31 | 623 |
| 2026-08-01 | 623 |
| 2026-08-02 | 623 |
| 2026-08-06 | 623 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Bulleted Notes Book Summaries _Built With: Python 3.11.9_ ## Introduction This project creates bulleted notes summaries of books and other long texts, particularly epub and pdf which have ToC metadata available. When the ebooks contain approrpiate metadata, we are able to easily automate the extraction of chapters from most books, and split them into ~2000 token chunks, with fallbacks in case we are unable to access a document outline. ### Why 2000 tokens? [*Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models*](https://huggingface.co/papers/2402.14848) (2024-02-19; Mosh Levy, Alon Jacoby, Yoav Goldberg) suggests that reasoning capacity drops off pretty sharply from 250 to 1000 tokens, starting to flatten out between 2000-3000 tokens.  This corresponds my own experience while summarizing many long documents using local llm. You can check the [depreciated walkthroughs and rankings](notes/depreciated/) for more background on how I got here. ### Comparison with RAG Similar to Retrieval Augmented Generation (RAG), we split the document into many parts, so they fit into the context. The difference is that RAG systems try to determine what is the best chunk to ask their question to. Instead, we ask the same questions to *every part of the document*. Its very important towards unlocking the full capabilities of LLM without relying on a multitude of 3rd party apps. ## Contents - [Setup](#setup) - [Python Environment](#python-environment) - [Install Dependencies](#install-dependencies) - [Download Models](#download-models) - [Update Config File](#update-config-file-_configyaml) - [Usage](#usage) - [Convert E-book to chunked CSV or TXT](#convert-e-book-to-chunked-csv-or-txt) - [Generate Summary](#generate-summary) - [Semi-Manual with Prototypes](#semi-manual-with-prototypes) - [Models](#models) - [Ollama](#ollama) - [HuggingFace](#huggingface) - [Check your Document Outline](#check-your-ebook-for-document-outline) - [Firefox](#firefox) - [Brave](#brave) - [Disclaimer](#disclaimer) - [Inspiration](#inspiration) - [Resources](#resources) ## Setup ### Python Environment Before starting, ensure you have Python 3.11.9 installed. If not, you can use conda or pyenv to manage Python versions: **Using conda:** 1. Install Anaconda from: https://www.anaconda.com/download/success 2. Create a new environment: `conda create -n book_summary python=3.11.9` 3. Activate the environment: `conda activate book_summary` **Using pyenv:** 1. Install pyenv: https://github.com/pyenv/pyenv#installation 2. Install Python 3.11.9: `pyenv install 3.11.9` 3. Set local version: `pyenv local 3.11.9` ### Install Dependencies ``` pip install -r requirements.txt ``` - [Install Ollama](https://github.com/ollama/ollama?tab=readme-ov-file#ollama) ### Download Models #### 1. **Download a copy of Mistral Instruct v0.2 Bulleted Notes Fine-Tune** `ollama pull cognitivetech/obook_summary:q6_k` #### 2. **Download up a title model** ##### a) *Download a preconfigured model* `ollama pull cognitivetech/obook_title:q4_k_m` For your convenience Mistral 7b 0.3 is packaged with the necessary message history for title creation. ***or*** ##### b) *Append this* [message history](Modelfile) *to the Modelfile of your choice* #### 3. **Download a general-purpose model** `ollama pull gemma2` ### Update Config File `_config.yaml` Ensure the defaults are set accordingly! > This is an area subject to change which may differ from the documentation. **Make sure you have the models on your system as noted in `summary`, `general`, and `title` in the current [_config.yaml](./_config.yaml).** I have to clean up this aspect of the code, but I'm still working on that. ```yaml defaults: prompt: bnotes summary: cognitivetech/obook_summary:q6_k # default model for summaries general: gemma2 # default model for basic summary title: cognit
Excerpt of 12,878 characters
Read on GitHub
239
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b93311b380c85368, topic:llm, topic:gpt