pdfGPT
TensorRT-LLM
pdfGPT | TensorRT-LLM | |
---|---|---|
9 | 14 | |
6,733 | 6,797 | |
- | 8.3% | |
8.2 | 8.4 | |
4 months ago | about 18 hours ago | |
Python | C++ | |
MIT License | 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.
pdfGPT
-
Nvidia's Chat with RTX is a promising AI chatbot that runs locally on your PC
From "Artificial intelligence is ineffective and potentially harmful for fact checking" (2023) https://news.ycombinator.com/item?id=37226233 : pdfgpt, knowledge_gpt, elasticsearch
pdfGPT: https://github.com/bhaskatripathi/pdfGPT :
> PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities.
GH "pdfgpt" topic: https://github.com/topics/pdfgpt
knowledge_gpt: https://github.com/mmz-001/knowledge_gpt
From https://news.ycombinator.com/item?id=39112014 : paperai
neuml/paperai:
-
Artificial intelligence is ineffective and potentially harmful for fact checking
What about systems like pdfgpt and knowledge_gpt; that, in returning citations from the trained texts, might be useful for legal discovery with admissibility?
pdfgpt: https://github.com/bhaskatripathi/pdfGPT
-
Based on latest advancements in document transformers, what strategy would you use to parse utility bills?
PDFChatter (Universal Sentence Encoder + GPT-3.5): out of the box, this solution works quite well. However, the need for Q&A prompting (and 'black-box' nature of the solution) seems to disqualify it as an optimal solution.
- Ways to integrate PDF file content into my own Chatbot powered by GPT API
-
Best secure/offline ChatGPT implementation for processing documents?
I was recommended pdfGPT and it looks good. Before I start setting it up, is there anything I should know? Are there better solutions? And how secure would it or they be?
- Is there a way to run ChatPDF (tool that allows you to upload documents and process them with ChatGPT) locally so that I don't have to worry about stuff I don't want shared leaking?
-
PDF GPT allows you to chat with the contents of your PDF file
https://github.com/bhaskatripathi/pdfGPT/blob/main/app.py it's a 200 line python script, all you need to do is rewrite pdf_to_text function for whatever format your file is. gpt4 can do it.
TensorRT-LLM
-
Ollama v0.1.33 with Llama 3, Phi 3, and Qwen 110B
Yes, we are also looking at integrating MLX [1] which is optimized for Apple Silicon and built by an incredible team of individuals, a few of which were behind the original Torch [2] project. There's also TensorRT-LLM [3] by Nvidia optimized for their recent hardware.
All of this of course acknowledging that llama.cpp is an incredible project with competitive performance and support for almost any platform.
[1] https://github.com/ml-explore/mlx
[2] https://en.wikipedia.org/wiki/Torch_(machine_learning)
[3] https://github.com/NVIDIA/TensorRT-LLM
- FLaNK AI for 11 March 2024
-
FLaNK Stack 26 February 2024
NVIDIA GPU LLM https://github.com/NVIDIA/TensorRT-LLM
- FLaNK Stack Weekly 19 Feb 2024
-
Nvidia Chat with RTX
https://github.com/NVIDIA/TensorRT-LLM
It's quite a thin wrapper around putting both projects into %LocalAppData%, along with a miniconda environment with the correct dependnancies installed. Also for some reason the LLaMA 13b (24.5GB) and Ministral 7b (13.6GB) but only installed Ministral?
Ministral 7b runs about as accurate as I remeber, but responses are faster than I can read. This seems at the cost of context and variance/temperature - although it's a chat interface the implementation doesn't seem to take into account previous questions or answers. Asking it the same question also gives the same answer.
The RAG (llamaindex) is okay, but a little suspect. The installation comes with a default folder dataset, containing text files of nvidia marketing materials. When I tried asking questions about the files, it often cites the wrong file even if it gave the right answer.
-
Nvidia's Chat with RTX is a promising AI chatbot that runs locally on your PC
Yeah, seems a bit odd because the TensorRT-LLM repo lists Turing as supported architecture.
https://github.com/NVIDIA/TensorRT-LLM?tab=readme-ov-file#pr...
-
MK1 Flywheel Unlocks the Full Potential of AMD Instinct for LLM Inference
I support any progress to erode the Nvidia monopoly.
That said from what I'm seeing here the free and open source (less other aspects of the CUDA stack, of course) TensorRT-LLM[0] almost certainly bests this implementation using the Nvidia hardware they reference for comparison.
I don't have an A6000 but as an example with the tensorrt_llm backend for Nvidia Triton Inference Server (also free and open source) I get roughly 30 req/s with Mistral 7B on my RTX 4090 with significantly lower latency. Comparison benchmarks are tough, especially when published benchmarks like these are fairly scant on the real details.
TensorRT-LLM has only been public for a few months and if you peruse the docs, PRs, etc you'll see they have many more optimizations in the works.
In typical Nvidia fashion TensorRT-LLM runs on any Nvidia card (from laptop to datacenter) going back to Turing (five year old cards) assuming you have the VRAM.
You can download and run this today, free and "open source" for these implementations at least. I'm extremely skeptical of the claim "MK1 Flywheel has the Best Throughput and Latency for LLM Inference on NVIDIA". You'll note they compare to vLLM, which is an excellent and incredible project but if you look at vLLM vs Triton w/ TensorRT-LLM the performance improvements are dramatic.
Of course it's the latest and greatest ($$$$$$ and unobtanium) but one look at H100/H200 performance[3] and you can see what happens when the vendor has a robust software ecosystem to help sell their hardware. Pay the Nvidia tax on the frontend for the hardware, get it back as a dividend on the software.
I feel like MK1 must be aware of TensorRT-LLM but of course those comparison benchmarks won't help sell their startup.
[0] - https://github.com/NVIDIA/TensorRT-LLM
[1] - https://github.com/triton-inference-server/tensorrtllm_backe...
[2] - https://mkone.ai/blog/mk1-flywheel-race-tuned-and-track-read...
[3] - https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source...
-
FP8 quantized results are bad compared to int8 results
I have followed the instructions on https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama to convert the float16 Llama2 13B to FP8 and build a tensorRT-LLM engine.
- Optimum-NVIDIA - 28x faster inference in just 1 line of code !?
- Incoming: TensorRT-LLM version 0.6 with support for MoE, new models and more quantization
What are some alternatives?
unstructured - Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
ChatRTX - A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM
ChatPDF - Chat with any PDF. Easily upload the PDF documents you'd like to chat with. Instant answers. Ask questions, extract information, and summarize documents with AI. Sources included.
gpt-fast - Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
gpt4-pdf-chatbot-langchain - GPT4 & LangChain Chatbot for large PDF docs
optimum-nvidia
Parsr - Transforms PDF, Documents and Images into Enriched Structured Data
stable-fast - Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
OpenChatPaper - Yet another paper reading assistant based on OpenAI ChatGPT API. An open-source version that attempts to reimplement ChatPDF. A different dialogue version of another ChatPaper project.
tensorrtllm_backe
mychatGPT - GPT chat with your docs!
daytona - The Open Source Dev Environment Manager.