txtai
CLIP
Our great sponsors
txtai | CLIP | |
---|---|---|
354 | 102 | |
6,725 | 21,480 | |
8.1% | 4.8% | |
9.3 | 2.2 | |
12 days ago | 3 months ago | |
Python | Jupyter Notebook | |
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.
txtai
-
Ask HN: What happened to startups, why is everything so polished?
I agree that in many cases people are puffing their feathers to try to be something they're not (at least not yet). Some believe in the fake it until you make it mentality.
With NeuML (https://neuml.com), the website is a simple HTML page. On social media, I'm honest about what NeuML is, that I'm in my 40s with a family and not striving to be the next Steve Jobs. I've been able to build a fairly successful open source project (txtai 6K stars https://github.com/neuml/txtai) and a revenue positive company. For me, authenticity and being genuine is most important. I would say that being genuine has been way more of an asset than liability.
-
Are we at peak vector database?
I'll add txtai (https://github.com/neuml/txtai) to the list.
There is still plenty of room for innovation in this space. Just need to focus on the right projects that are innovating and not the ones (re)working on problems solved in 2020/2021.
-
Show HN: Open-source Rule-based PDF parser for RAG
Nice project! I've long used Tika for document parsing given it's maturity and wide number of formats supported. The XHTML output helps with chunking documents for RAG.
Here's a couple examples:
- https://neuml.hashnode.dev/build-rag-pipelines-with-txtai
- https://neuml.hashnode.dev/extract-text-from-documents
Disclaimer: I'm the primary author of txtai (https://github.com/neuml/txtai).
-
RAG Using Unstructured Data and Role of Knowledge Graphs
If you're interested in graphs + RAG and want an alternate approach, txtai has a semantic graph component.
https://neuml.hashnode.dev/introducing-the-semantic-graph
https://github.com/neuml/txtai
Disclaimer: I'm the primary author of txtai
-
The Life and Death of Open Source Companies
My perspective as an open source developer of txtai (https://github.com/neuml/txtai).
When you get started in open source, it's a great way for a small team to get the word out. Conversely, when starting as proprietary software or SaaS, you're looking at advertising, websites, sales calls and so forth. If an open source company is lucky enough to be successful, the next phase is having users and perhaps even funding. When the team grows and/or others put their own money or career into the company, they want an outcome. It becomes hard to ignore that there are thousands of people using the software and inevitably it becomes an exercise on how to claw back from the group of "free" users. There is also the fear that a big company will undercut the open source company by offering the software as part of a cloud service. This is my opinion on how we got here with confusing licensing changes.
Most don't have the means to accept little to no income from their work. But there shouldn't be a "fixed pot" mentality. In order to be a successful open source company, one has to see the "free" users as beneficial. Think of it as a big wide open world and that while some will never pay, if you add value in other ways on top of your open source offerings, there will be significant income opportunities. Could be consulting projects, hosted/cloud/SaaS versions or specialized components.
One should also look at operations. There will be a new wave of companies, especially in the AI space, that are lean and using automation to build great things with a very limited amount of resources. Perhaps they don't even need funding and can build a profitable company without it. In those cases, they won't have those internal pressures and hence likely to be more competitive. Something to watch in 2024.
-
2023: The Year of AI
You can look at https://github.com/neuml/txtai. Biggest thing of 2023 was RAG with models like Mistral.
-
Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?
Since no one has mentioned it so far: I did just this recently with txtai in a few lines of code.
-
Build a search engine, not a vector DB
I agree that RAG doesn't have to be paired with vector search. Other types of search can work in some cases.
Where vector search excels is that it can encode a complex question as a vector and does a good job bringing back the top n results. Its not impossible to do some of this with keyword search (term expansion, stopwords and so forth). Vector search just makes it easy.
In the end, yes this is a better search system. And thinking about this step is a good point. I would go a step further and say it's also worth thinking about the RAG framework. Lots of examples use a OpenAI/Langchain/Chroma stack. But it's also worth evaluating RAG framework options. There might be frameworks that are easier to integrate and perform better for your use case.
Disclaimer: I am the author of txtai (https://github.com/neuml/txtai).
-
Integrate LLM Frameworks
With that in mind, txtai now has the capability to easily integrate additional LLM frameworks. While local models through Hugging Face Transformers continues to be the default choice, these additional LLM frameworks broaden the number of options available.
-
Is anyone using self hosted LLM day to day and training it like a new employee
Cool use case, glad to see txtai [1] is helping (I'm the main dev for txtai).
Since you're using txtai, this article I just wrote yesterday might be helpful: https://neuml.hashnode.dev/build-rag-pipelines-with-txtai
Looks like you've received a lot of great ideas here already though!
CLIP
-
Show HN: Memories, FOSS Google Photos alternative built for high performance
Biggest missing feature for all these self hosted photo hosting is the lack of a real search. Being able to search for things like "beach at night" is a time saver instead of browsing through hundreds or thousands of photos. There are trained neural networks out there like https://github.com/openai/CLIP which are quite good.
Does it have search by keywords/semantics? That would be my main need. For example if I need to find photos of cacti I could just search for that.
OpenAI open sourced CLIP a couple of years ago: https://github.com/openai/CLIP and I was planning to write something myself to index my vast photo library but got too lazy and gave up.
-
Zero-Shot Prediction Plugin for FiftyOne
In computer vision, this is known as zero-shot learning, or zero-shot prediction, because the goal is to generate predictions without explicitly being given any example predictions to learn from. With the advent of high quality multimodal models like CLIP and foundation models like Segment Anything, it is now possible to generate remarkably good zero-shot predictions for a variety of computer vision tasks, including:
-
A History of CLIP Model Training Data Advances
(Github Repo | Most Popular Model | Paper | Project Page)
-
How to Build a Semantic Search Engine for Emojis
Whenever I’m working on semantic search applications that connect images and text, I start with a family of models known as contrastive language image pre-training (CLIP). These models are trained on image-text pairs to generate similar vector representations or embeddings for images and their captions, and dissimilar vectors when images are paired with other text strings. There are multiple CLIP-style models, including OpenCLIP and MetaCLIP, but for simplicity we’ll focus on the original CLIP model from OpenAI. No model is perfect, and at a fundamental level there is no right way to compare images and text, but CLIP certainly provides a good starting point.
-
COMFYUI SDXL WORKFLOW INBOUND! Q&A NOW OPEN! (WIP EARLY ACCESS WORKFLOW INCLUDED!)
in the modal card it says: pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).
-
Stability Matrix v1.1.0 - Portable mode, Automatic updates, Revamped console, and more
Command: "C:\StabilityMatrix\Packages\stable-diffusion-webui\venv\Scripts\python.exe" -m pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary
-
[D] LLM or model that does image -> prompt?
CLIP might work for your needs.
-
Where can this be used? I have seen some tutorials to run deepfloyd on Google colab. Any way it can be done on local?
pip install deepfloyd_if==1.0.2rc0 pip install xformers==0.0.16 pip install git+https://github.com/openai/CLIP.git --no-deps pip install huggingface_hub --upgrade
-
Can anybody advise open-sourced neural net model to tag/recognize photos on a harddrive?
I recommend https://laion.ai/blog/large-openclip/ or https://github.com/openai/CLIP .
What are some alternatives?
open_clip - An open source implementation of CLIP.
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
DALLE2-pytorch - Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
disco-diffusion
tika-python - Tika-Python is a Python binding to the Apache Tikaâ„¢ REST services allowing Tika to be called natively in the Python community.
BLIP - PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
faiss - A library for efficient similarity search and clustering of dense vectors.
segment-anything - The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
paperai - 📄 🤖 Semantic search and workflows for medical/scientific papers