quivr VS localGPT

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.

I think local LLMs are great for tinkerers, and with quantization can run on most modern PCs. I am not comfortable sending over my personal data over to OpenAI/Anthropic, so I've been playing around with https://github.com/PromtEngineer/localGPT/, GPT4All, etc. which keep the data all local.

Sliding window chunking, RAG, etc. seem more sophisticated than the other document LLM tools, so I would love to try this out if you ever add the ability to run LLMs locally!

localGPT can parse PDF into embeddings, see <https://github.com/PromtEngineer/localGPT>.

This is going so fast that it feels like a new thing pops up every day. LocalGPT seems to have gotten a lot of traction though: https://github.com/PromtEngineer/localGPT

i am currently trying to use localGPT (https://github.com/PromtEngineer/localGPT) for a project and i encountered a problem.

I tinker a lot with electronics. I have put datasheets for components, documentation for development boards, documentation for software libraries, etc into a database with localGPT.

There are a bunch of other methods to improve quality and performance like tree-of-thought-llm, connecting a LLM to a database or have it review its own output.

Check out local gpt on git hub. I tried but it had slow response for me. Other developers are fine. https://github.com/PromtEngineer/localGPT