JSLT
h2ogpt
Our great sponsors
JSLT | h2ogpt | |
---|---|---|
6 | 28 | |
605 | 10,398 | |
0.8% | 5.3% | |
4.7 | 10.0 | |
3 months ago | 4 days ago | |
Java | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
JSLT
- FLaNK Stack Weekly for 24April2023
-
Process: Continuously and incrementally writing short design documents
I follow that approach in this open-source repo, and since PRs come from volunteers I've sometimes just updated the docs afterwards myself. But in a work situation you could be strict about it.
-
I've been programming in Java for 20 years. What would be some advanced java projects?
I made this language. It was a lot of fun, and has been very useful.
-
Declarative Data Transformations
If you're working in Java I would look at JSLT for the JSON transforms. (Disclaimer: I created JSLT, for a similar use case.)
- NTNU CCIS leter etter unge talenter. Kan du finne ut hva tallene betyr? 115 52 52 48 58 47 47 52 115 112 109 116 114 51 112 110 50 112 52 46 121 122 #cybersecurity #Jul #hack
-
Seeking a JSON file converter
You could use a transformation language like JSLT to write a transform, then apply it to all files. Not sure if that's suitable for you.
h2ogpt
-
Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?
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
-
chatgpt alternative
Here's the links: https://github.com/h2oai/h2ogpt/blob https://github.com/h2oai/h2ogpt/blob/main/docs/README_LangChain.md
-
Went down the rabbit hole of 100% local RAG, it works but are there better options?
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.
-
[SEEKING ADVICE] Looking for Existing Repos (Open-Source, VM-Hosted, & GPU-Compatible)
I've stumbled upon h2ogptas a potential starting point. Are there better solutions or repositories that can meet these requirements?
- H2Oai GPT CPU
-
Open source Q&A chatbot UI Recommendation?
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.
-
My experience on starting with fine tuning LLMs with custom data
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.
-
H2O.ai Introduces h2oGPT: A Suite of Open-Source Code Repositories for Democratizing Large Language Models (LLMs)
Github link: https://github.com/h2oai/h2ogpt
-
tokenizers error is driving me nuts
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
-
LLM for PDFs
privateGPT or h2ogpt
What are some alternatives?
Jolt - JSON to JSON transformation library written in Java.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
JsonPath - Java JsonPath implementation
privateGPT - Interact with your documents using the power of GPT, 100% privately, no data leaks [Moved to: https://github.com/zylon-ai/private-gpt]
fastjson - FASTJSON 2.0.x has been released, faster and more secure, recommend you upgrade.
llama_index - LlamaIndex is a data framework for your LLM applications
sawmill - Sawmill is a JSON transformation Java library
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
JsonSurfer - A streaming JsonPath processor in Java
local_llama - This repo is to showcase how you can run a model locally and offline, free of OpenAI dependencies.
MapNeat - MapNeat is a JVM library written in Kotlin that provides an easy to use DSL (Domain Specific Language) for transforming JSON to JSON, XML to JSON, POJO to JSON in a declarative way.
h2o-llmstudio - H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/