fast_vector_similarity
n8n
fast_vector_similarity | n8n | |
---|---|---|
7 | 299 | |
323 | 41,209 | |
- | 3.2% | |
7.2 | 10.0 | |
9 months ago | 1 day ago | |
Rust | TypeScript | |
- | Apache 2.0 with Commons Clause |
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.
fast_vector_similarity
-
SentenceTransformers: Python framework for sentence, text and image embeddings
Yes, check out my library for vector similarity that has various other measures which are more discriminative:
https://github.com/Dicklesworthstone/fast_vector_similarity
pip install fast_vector_similarity
-
Show HN: Neum AI β Open-source large-scale RAG framework
Got it. I'd encourage you to expose more of that functionality at the level of your application if possible. I think there is a lot of potential in using more than just cosine similarity, especially when there are lots of candidates and you really want to sharpen up the top few recommendations to the best ones. You might find this open-source library I made recently useful for that:
https://github.com/Dicklesworthstone/fast_vector_similarity
I've had good results from starting with cosine similarity (using FAISS) and then "enriching" the top results from that with more sophisticated measures of similarity from my library to get the final ranking.
-
Some Reasons to Avoid Cython
You can see how I did something similar in my library here:
https://github.com/Dicklesworthstone/fast_vector_similarity/...
Basically you use ndarray instead of numpy, try to vectorize anything you can, and for the for loops that canβt be vectorized, you can use rayon to do them in parallel.
- FLaNK Stack Weekly 28 August 2023
- Fast Vector Similarity Library, Useful for Working With Llama2 Embedding Vectors
-
Show HN: Fast Vector Similarity Using Rust and Python
Yeah, like the other commenter said, everything is in this file here:
https://github.com/Dicklesworthstone/fast_vector_similarity/...
If you also make your project using Rust and Maturin, you can literally just copy and paste that into your project because it's totally generic, and if the repo is public, GitHub will just run it all for you for free.
The only thing is you need to create an account on PyPi (pip) and add 2-Factor Auth so you can generate an API key. Then you go into the repo settings and go to secrets, and create a Github Actions secret with the name PYPI_API_TOKEN and make the value your PyPi token. That's it! It will not only compile all the wheels for you but even upload the project to PyPi for you using the settings found in your pyproject.toml file, like this:
https://github.com/Dicklesworthstone/fast_vector_similarity/...
n8n
-
Ask HN: Is there a visual data mapper for JSON transformation?
I believe you can achieve that with n8n. Used in past (and still running) for some data transformation and little more. Possibly similar case what are you describing.
https://n8n.io/
- Dify, a visual workflow to build/test LLM applications
-
Helm 101: Creating Helm Charts
A startup, "DevOps Solutions" adopts Helm to streamline their Kubernetes deployments. You're a consultant tasked with creating a basic Helm Chart for n8n. It should be customizable for different environments using values.
- IFTTT is killing its pay-what-you-want Legacy Pro plan
-
A Year of Self-Hosting: 6 Open-Source Projects That Surprised Me in 2023
n8n.io - a powerful workflow automation tool
-
Open Source alternatives to tools you Pay for
N8N - Open Source Alternative to Zapier
- Ask YC: tracking events platform and no-code workflow
-
Your privacy is optional
N8N - anything that I would have used Zapier or IFTTT for I now use N8N. It is a bit harder to use but more powerful.
-
To whoever uses Supabase as their backend: what's your full no-code / low-code stack?
I'm using Weweb as my front end and Supabase as my back end. I'm also looking into n8n.io to run some of the backend logic that I'm either unsure how to code myself within Supabase or unsure if Supabase can perform those back-end tasks and workflows. Curious what stack or tools other Supabase users are using?
-
Show HN: Keep β GitHub Actions for your monitoring tools
This is similar to something I saw before: https://n8n.io
What are some alternatives?
simsimd
Node RED - Low-code programming for event-driven applications
swiss_army_llama - A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
Huginn - Create agents that monitor and act on your behalf. Your agents are standing by!
np-sims - numpy ufuncs for vector similarity
Airflow - Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
QTVR - Tools for QTVR 1 files
StackStorm - StackStorm (aka "IFTTT for Ops") is event-driven automation for auto-remediation, incident responses, troubleshooting, deployments, and more for DevOps and SREs. Includes rules engine, workflow, 160 integration packs with 6000+ actions (see https://exchange.stackstorm.org) and ChatOps. Installer at https://docs.stackstorm.com/install/index.html
llama_embeddings_fastap
budibase - Budibase is an open-source low code platform that helps you build internal tools in minutes π
DoctorGPT - π»ππ‘ DoctorGPT provides advanced LLM prompting for PDFs and webpages.
Home Assistant - :house_with_garden: Open source home automation that puts local control and privacy first.