flask-socketio-llm-com VS CX_DB8

https://github.com/russellballestrini/flask-socketio-llm-com...

This project is a chatroom application that allows users to join different chat rooms, send messages, and interact with multiple language models in real-time. The backend is built with Flask and Flask-SocketIO for real-time web communication, while the frontend uses HTML, CSS, and JavaScript to provide an interactive user interface.

demo here supports communication with `vllm/openchat`:

* http://home.foxhop.net:5001

next year I'm focusing on learning more about AI, I bought a $3.5k computer with an nvidia RTX 4090 24G of memory, it arrived today, I plan to extend my playground chat app to use local models for text generation and image generation inference (https://github.com/russellballestrini/flask-socketio-llm-com...)

I'm going to be looking into fine tuning process in some way.

https://github.com/russellballestrini/flask-socketio-llm-com...

I'm building a similar app but uses python/socket.io

I was working on this stuff before it was cool, so in the sense of the precursor to LLMs (and sometimes supporting LLMs still) I've built many things:

1. Games you can play with word2vec or related models (could be drop in replaced with sentence transformer). It's crazy that this is 5 years old now: https://github.com/Hellisotherpeople/Language-games

2. "Constrained Text Generation Studio" - A research project I wrote when I was trying to solve LLM's inability to follow syntactic, phonetic, or semantic constraints: https://github.com/Hellisotherpeople/Constrained-Text-Genera...

3. DebateKG - A bunch of "Semantic Knowledge Graphs" built on my pet debate evidence dataset (LLM backed embeddings indexes synchronized with a graphDB and a sqlDB via txtai). Can create compelling policy debate cases https://github.com/Hellisotherpeople/DebateKG

4. My failed attempt at a good extractive summarizer. My life work is dedicated to one day solving the problems I tried to fix with this project: https://github.com/Hellisotherpeople/CX_DB8

I really missed out on this thread despite being likely one of the most important folks to post on it (I turned my time in Policy Debate into an NLP career - see DebateSum: https://huggingface.co/datasets/Hellisotherpeople/DebateSum and CX_DB8: https://github.com/Hellisotherpeople/CX_DB8)

For those who are interested in the intersection of AI and Debate Evidence, there's a lot more work being done right now. We have a follow-up dataset to DebateSum on its way to a paper at some conference called OpenCaseList: https://huggingface.co/datasets/Yusuf5/OpenCaselist which is basically DebateSum but 40x better in every way. This is also likely the largest and best quality argument mining dataset ever gathered.

Fun anecdote, when I tried to introduce automatic extractive summarization tools to the debate community, I had parent/judge/teacher groups who were FLIPPING out about this. They were not happy at the idea of automatic debating or computer assisted debating systems.

This has deep connections with my attempt to implement an effective queryable word-level grammatically correct extractive text summarizer (AKA: The way most people actually summarize documents) - https://github.com/Hellisotherpeople/CX_DB8

I will try to implement this with the necessary changes to actually make this work properly, where instead of generating a new answer, it simply highlights the most likely text spans.

Is there any path forward to make Haystack do word-level extractive summarization? e.g. like this: https://github.com/Hellisotherpeople/CX_DB8

or like this: https://huggingface.co/spaces/Hellisotherpeople/Unsupervised...

I am trying to find anything better than these two for this task. I feel like Haystack could be an option - but I am not sure.