autofaiss
examples
autofaiss | examples | |
---|---|---|
3 | 5 | |
748 | 380 | |
1.7% | 6.8% | |
5.6 | 6.8 | |
7 days ago | 3 months ago | |
Python | Jupyter Notebook | |
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.
autofaiss
-
You Don't Need LangChain;
I might be wrong here. I just know some product quantization techniques, but you can reduce the index by a lot! However, from my research, the more size you reduce, the more retrieval quality is also reduced.
Quoting from https://github.com/criteo/autofaiss
-
Cheapest Vector Database
Autofaiss - https://github.com/criteo/autofaiss can be configured to make extremely tiny and efficient indexes.
-
Vector database built for scalable similarity search
Don't start with mullivus if you're learning. Too much yak shaving. Try https://github.com/criteo/autofaiss.
Also, TBH, it is a lot cheaper to run a simple faiss index.
examples
- FLaNK Stack Weekly for 07August2023
-
Vector database built for scalable similarity search
As another commenter noted, Milvus is overkill and a "bit much" if you're learning/playing.
A good intro to the field with progression towards a full Milvus implementation could be starting with towhee[0] (which is also supported by Milvus).
towhee has an example to do exactly what you want with CLIP[1].
[0] - https://towhee.io/
[1] - https://github.com/towhee-io/examples/tree/main/image/text_i...
-
Ask HN: Any good self-hosted image recognition software?
Usually this is done in three steps. The first step is using a neural network to create a bounding box around the object, then generating vector embeddings of the object, and then using similarity search on vector embeddings.
The first step is accomplished by training a detection model to generate the bounding box around your object, this can usually be done by finetuning an already trained detection model. For this step the data you would need is all the images of the object you have with a bounding box created around it, the version of the object doesnt matter here.
The second step involves using a generalized image classification model thats been pretrained on generalized data (VGG, etc.) and a vector search engine/vector database. You would start by using the image classification model to generate vector embeddings (https://frankzliu.com/blog/understanding-neural-network-embe...) of all the different versions of the object. The more ground truth images you have, the better, but it doesn't require the same amount as training a classifier model. Once you have your versions of the object as embeddings, you would store them in a vector database (for example Milvus: https://github.com/milvus-io/milvus).
Now whenever you want to detect the object in an image you can run the image through the detection model to find the object in the image, then run the sliced out image of the object through the vector embedding model. With this vector embedding you can then perform a search in the vector database, and the closest results will most likely be the version of the object.
Hopefully this helps with the general rundown of how it would look like. Here is an example using Milvus and Towhee https://github.com/towhee-io/examples/tree/3a2207d67b10a246f....
Disclaimer: I am a part of those two open source projects.
-
Deep Dive into Real-World Image Search Engine with Python
I have shown how to Build an Image Search Engine in Minutes in the previous tutorial. Here is another one for how to optimize the algorithm, feed it with large-scale image datasets, and deploy it as a micro-service.
-
Build an Image Search Engine in Minutes
The full tutorial is at https://github.com/towhee-io/examples/blob/main/image/reverse_image_search/build_image_search_engine.ipynb
What are some alternatives?
vespa - AI + Data, online. https://vespa.ai
towhee - Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
sqlite-vss - A SQLite extension for efficient vector search, based on Faiss!
milvus-lite - A lightweight version of Milvus wrapped with Python.
gorilla-cli - LLMs for your CLI
typesense-instantsearch-semantic-search-demo - A demo that shows how to build a semantic search experience with Typesense's vector search feature and Instantsearch.js
anomalib - An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
EverythingApacheNiFi - EverythingApacheNiFi
pgvector - Open-source vector similarity search for Postgres
harlequin - The SQL IDE for Your Terminal.