h2ogpt VS quivr

As others have said you want RAG.

The most feature complete implementation I've seen is h2ogpt[0] (not affiliated).

The code is kind of a mess (most of the logic is in an ~8000 line python file) but it supports ingestion of everything from YouTube videos to docx, pdf, etc - either offline or from the web interface. It uses langchain and a ton of additional open source libraries under the hood. It can run directly on Linux, via docker, or with one-click installers for Mac and Windows.

It has various model hosting implementations built in - transformers, exllama, llama.cpp as well as support for model serving frameworks like vLLM, HF TGI, etc or just OpenAI.

You can also define your preferred embedding model along with various other parameters but I've found the out of box defaults to be pretty sane and usable.

[0] - https://github.com/h2oai/h2ogpt

Here's the links: https://github.com/h2oai/h2ogpt/blob https://github.com/h2oai/h2ogpt/blob/main/docs/README_LangChain.md

Take a look at h2ogpt. It's open and local with API (incoming and outgoing) and impressive feature set, including RAG from docs, images, and web search.

I've stumbled upon h2ogptas a potential starting point. Are there better solutions or repositories that can meet these requirements?

Any recommendations for an open source repos that support web based chat ui where you can upload docs,pds,links,etc? So far i found https://github.com/openchatai/OpenChat but it doesnt support llama, claude, etc. Theres also https://github.com/h2oai/h2ogpt but their gradio UI is overly complicated (meant for technical people) and not user friendly.

I'm also working on the finetuning of models for Q&A and I've finetuned llama-7b, falcon-40b, and oasst-pythia-12b using HuggingFace's SFT, H2OGPT's finetuning script and lit-gpt.

Github link: https://github.com/h2oai/h2ogpt

quite a number of AI tools written in Python do not work for me and usually because of the same error: RuntimeError: Failed to import transformers.models.auto because of the following error (look up to see its traceback): No module named 'tokenizers.tokenizers' This time it's https://github.com/h2oai/h2ogpt

privateGPT or h2ogpt

3. Quivr | GitHub | tutorial

I used Ollama (with Mistral 7B) and Quivr to get a local RAG up and running and it works fine, but was surprised to find there are no easy user-friendly ways to do it. Most other local LLM UIs don't implement this use case (I looked here), even though it is one of the most useful local LLM use-cases I can think of: search and summarize information from sensitive / confidential documents.

In my opinion LLM based document search tools such as OSS Quivr may be better suited for documentation search for startups.

A highly customed Quivr with one of the 'Open Source LLMs' may provides great 'semantic search' for product documentation.

https://github.com/StanGirard/quivr

Hey thanks for creating this, will try later if i have time. Meanwhile, do you try some of other second brain app such as this, and how was the comparison? The one i mentioned was trending on github so i think its decent (been playing with it since last week or so, also). But i already starred your repo so i can come back later.