vearch
txtai
Our great sponsors
vearch | txtai | |
---|---|---|
2 | 354 | |
1,884 | 6,725 | |
2.4% | 8.1% | |
9.6 | 9.3 | |
7 days ago | 12 days ago | |
Go | 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.
vearch
- An AI Native database for embedding vectors
-
Any database implementation from vector data search?
https://github.com/vearch/vearch this is one of the implementation
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!
What are some alternatives?
sentence-transformers - Multilingual Sentence & Image Embeddings with BERT
tika-python - Tika-Python is a Python binding to the Apache Tikaβ’ REST services allowing Tika to be called natively in the Python community.
transformers - π€ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
faiss - A library for efficient similarity search and clustering of dense vectors.
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
paperai - π π€ Semantic search and workflows for medical/scientific papers
Milvus - A cloud-native vector database, storage for next generation AI applications
codequestion - π Semantic search for developers
openai-cookbook - Examples and guides for using the OpenAI API
llmsherpa - Developer APIs to Accelerate LLM Projects
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Tribuo - Tribuo - A Java machine learning library