privateGPT
BrainChulo
Our great sponsors
privateGPT | BrainChulo | |
---|---|---|
1 | 10 | |
50,198 | 140 | |
- | 1.4% | |
- | 9.0 | |
about 1 month ago | 6 months ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
privateGPT
-
PrivateGPT exploring the Documentation
# install developer tools xcode-select --install # create python sandbox mkdir PrivateGTP cd privateGTP/ python3 -m venv . # actiavte local context source bin/activate # privateGTP uses poetry for python module management privateGTP> pip install poetry # sync privateGTP project privateGTP> git clone https://github.com/imartinez/privateGPT # enable MPS for model loading and processing privateGTP> CMAKE_ARGS="-DLLAMA_METAL=on" pip install --force-reinstall --no-cache-dir llama-cpp-python privateGTP> cd privateGPT # Import configure python dependencies privateGTP> poetry run python3 scripts/setup # launch web interface to confirm operational on default model privateGTP> python3 -m private_gpt # navigate safari browser to http://localhost:8001/ # To bulk import documentation needed to stop the web interface as vector database not in multi-user mode privateGTP> [control] + "C" # import some PDFs privateGTP> curl "https://docs.intersystems.com/irislatest/csp/docbook/pdfs.zip" -o /tmp/pdfs.zip privateGTP> unzip /tmp/pdfs.zip -d /tmp # took a few hours to process privateGTP> make ingest /tmp/pdfs/pdfs/ # launch web interface again for query documentation privateGTP> python3 -m private_gpt
BrainChulo
-
Alternative to LangChain for open LLMs?
On BrainChulo, weโre going 100% guidance mode, see for instance an implementation of Chain of Thoughts on top of a thin guidance wrapper: https://github.com/ChuloAI/BrainChulo/blob/main/app/guidance_tooling/guidance_agent/agent.py
-
Running local LLM for info retrieval of technical documents
Awesome resource! If I may suggest that you'd add one, some friends and I are working on data retrieval with llm project as well, with our differentiating marker being that we are trying to implement guidance in order to improve the agent efficiency. If you guys wanna take a look :) https://github.com/ChuloAI/BrainChulo
- LlamaCPP and LangChain Agent Quality
- Training a 13B LLaMA on information from documents.
-
Chat with Documents using Open source LLMs
Plug: https://github.com/iGavroche/BrainChulo - BrainChulo currently works on top of Ooba but uses its own UI interface. Its first goal is to provide a production-level way to do Retrieveal Augmentation on Open Source LLMs via vector stores and good prompt engineering.
-
What features would everyone like to see in oog?
Regarding this, I've joined a project that is doing some nice progress on this front. Still WIP but we're getting there, checkout BrainChulo :)
-
7B models use with Langchainn for Chatbox importing of txt or pdf's
This is exactly what BrainChulo aims to do. You should check it out: https://github.com/CryptoRUSHGav/BrainChulo/ and feel free to drop on the discord to give us your feedback, your use-case, or if you need help getting started.
- [Local Llama] Aggiunta di memoria a lungo termine a LLM personalizzati: domiamo Vicuna insieme!
-
adding models to oobabooga
The download script is broken. I posted a working version on my repo: https://github.com/CryptoRUSHGav/BrainChulo
-
Adding Long-Term Memory to Custom LLMs: Let's Tame Vicuna Together!
I'm hoping that many of you brilliant people can join me in our common quest to add long-term memory to our favorite camelid, Vicuna. The repository is called BrainChulo, and it's just waiting for your contributions.
What are some alternatives?
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
gpt4-pdf-chatbot-langchain - GPT4 & LangChain Chatbot for large PDF docs
anything-llm - The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
gpt4all - gpt4all: run open-source LLMs anywhere
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
h2ogpt - Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
outlines - Structured Text Generation
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
long_term_memory - A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.
langchain - ๐ฆ๐ Build context-aware reasoning applications
gpt-llama.cpp - A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.