privateGPT
PrivateGPT4Linux
privateGPT | PrivateGPT4Linux | |
---|---|---|
1 | 23 | |
50,198 | 15 | |
- | - | |
- | 4.1 | |
about 1 month ago | 7 days ago | |
Python | Shell | |
Apache License 2.0 | GNU General Public License v3.0 only |
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
PrivateGPT4Linux
- PrivateGPT: Interact with your documents using the power of GPT, 100% privately, no data leaks
-
Need guidance in this sea of information on how to set up a local AI
I found things like this dataset and LocalAI and I followed the article to get PrivateGPT and the GPT4ALL groovy.bin but I'm completely lost and it feels like the more I research the internet or ask BingAI for answers, the more questions I get instead. At this stage I don't know what goes where, if there's a difference between source documents and datasets, should I run this from my 2tb SSD? Should I have the data on my 8tb HDD? Will all this even work on my PC?
-
Several newb questions
No, as the same as the last question, It does not have access to anything except the model data itself. However, there are some approaches that can let LLMs have access LOCAL documents, which means if you can have a program that extracts data from the database into a local folder which contains TEXT files. This could also work for 2(I didn't mention it in 2 because online datas are REALLY big. It would take the model hours to give an answer. If the database is not large then there might be a shot. Check https://github.com/imartinez/privateGPT(Must be GPT4all compatible models sadly).
-
What solution would best suite a SaaS - for reading and answering data from PDF files uploaded by users
I've been doing exactly this with an open source repository called PrivateGPT imartinez/privateGPT: Interact privately with your documents using the power of GPT, 100% privately, no data leaks (github.com)
- How to run an open source AI model, offline, on my own computer?
- Check out my script which installs privateGPT for Linux!
-
are there anytools or frameworks similar to "langchain" or "llamaindexbut implemented or designed in a language other than python?
Not really, you will probably need to change the data location and the LLM provider in the example code to get it running. But you don't have to implement that yourself there are a couple projects that already do that like privateGPT. I use it for searching datasheets, got it up an running in a few hours and I'm pretty happy with it so far.
-
Intern tasked to make a "local" version of chatGPT for my work
PrivateGPT can do that.
- I've made privateGPT work for Linux check it out (documents)
- I've made privateGPT work for Linux check it out
What are some alternatives?
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
anything-llm - The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
gpt4all - gpt4all: run open-source LLMs anywhere
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
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/
Voyager - An Open-Ended Embodied Agent with Large Language Models
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
llm - An ecosystem of Rust libraries for working with large language models
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
llm-chain - `llm-chain` is a powerful rust crate for building chains in large language models allowing you to summarise text and complete complex tasks