458 Photos and videos
RAG goes with more than just Vector Search. You can use the results of a SQL query, web search, agent search, you name it.
Read more below: neuml.hashnode.dev/rag-is-mo…
1
2
9
TxtAI's RAG pipeline makes it simple to pair knowledge with LLMs. Build an embeddable knowledge base, generate context and supply that to an LLM for fact-driven answers.
neuml.github.io/txtai/pipeli…
1
2
49
With TxtAI's minimal install, you can add a web extractor that reads web pages, converts them to Markdown and automatically splits content into sections.
All with only 4 packages and a 19MB install size!
gist.github.com/davidmezzett…
1
2
41
💫 Let's say you frequently work in Jupyter notebooks and would like to add some AI automation. Then check out ncoder. It's an easy and lightweight way to add an AI agent to your notebook workflows.
github.com/neuml/ncoder
1
2
50
🏎️💨 Want a fast model that can route requests by topic? Then check this one out.
huggingface.co/NeuML/domain-…
1
3
42
TxtAI's minimal package provides an a la carte install. This example ONLY adds llama-cpp and turbovec. No Torch, Hugging Face Hub or other libraries for this tiny install.
gist.github.com/davidmezzett…
1
3
94
Read the latest NeuML newsletter! Lots to cover since the last one in January.
neuml.substack.com/p/issue-5…
1
2
43
turbovec is a fast rising and impressive vector index library built on the TurboQuant algorithm. Support for it was just added to TxtAI and will be available next release!
github.com/RyanCodrai/turbov…
Paper: arxiv.org/abs/2504.19874
TxtAI Issue: github.com/neuml/txtai/issue…
1
1
8
687
Want a simple-to-use RAG application, then check this Streamlit-based TxtAI RAG app out!
github.com/neuml/rag
1
2
83
TxtAI 9.10 is out! TxtAI continues to invest heavily in local and edge device AI!
This release adds support for generating vectors via LiteRT for edge device use cases. It also adds support for training small models via Knowledge Distillation.
github.com/neuml/txtai/relea…
1
2
74
If you're looking for a medical version of all-mini-lm then check out this model: huggingface.co/blog/NeuML/bi…
1
2
57
✅ Training tiny models requires a different playbook. Check out this example article that covers how to progressively distill knowledge into a tiny 250K parameter model.
colab.research.google.com/gi…
1
5
110
📝 Interested in helping set the direction of TxtAI? Then fill out this survey!
forms.gle/k9PFXLftAuorLNFUA
1
2
85
🚀 Want a vector model that's less than 1M parameters can be as small as less than 1 MB? Want to run it on Mobile? Check this model out then. It's our export of the popular BERT Hash series!
huggingface.co/NeuML/bert-ha…
1
2
75
🔥 The next version of TxtAI will support running LiteRT vector models (formerly known as TensorFlow Lite). Check out this version of the popular all-MiniLM model!
huggingface.co/NeuML/all-Min…
1
4
105
Why care about TxtAI's zero dependency install? Well Transformers and Torch bring in a lot of dependencies. That's great if you need them but if you just want to run say a llama.cpp focused solution or only use the Textractor pipeline, it's a lot of unnecessary transitive dependencies and increases the overall image size. Problem solved!
1
3
115
🚀 TxtAI 9.9 is out! This release brings a big and important change: the zero dependency build. Previously, the base install required Transformers and Torch which brought the install up to at least 4GB. Now with providers like llama.cpp and LiteRT, a base install can be under 100MB with full GPU support!
Release Notes: github.com/neuml/txtai/relea…
GitHub: github.com/neuml/txtai
1
2
102