A fast open source source vector search and clustering engine. API bindings for multiple languages. Tries to be simple to use and extensible; if you're using it with C++ you only need to import one header file. Tries to be hardware agnostic; supports half-precision and quarter-precision with 16-bit floats and 8-bit integers, respectively. Can scan very large indices without loading the entire file into memory; implicitly supports serializing indices to disk. Heterogeneous lookups, renaming/relabeling, and on-the-fly deletions. Supports semantic search. Supports exact and approximate search.

Krita is a professional FREE and open source painting program. It is made by artists that want to see affordable art tools for everyone. Has an intuitive user interface that stays out of your way. The docks and panels can be moved and customized for your specific workflow. Once you have your setup, you can save it as your own workspace. You can also create your own shortcuts for commonly used tools. Over 100 professionally made brushes, stabilizers for them in case your hand isn't the steadiest, built-in vector drawing tools, customizable and constructable brushes, wrap-around mode for seamless textures, and a resource manager to import and export tools and packs from other users.

Supports 2d animation. Multiple layers and audio support, thousands of frames on the video timeline, onion skinning for tweening, drag-and-drop of frames, shortcuts, and performance tweaking.

Source code: https://invent.kde.org/graphics/krita

This framework provides an easy method to compute dense vector representations for sentences, paragraphs, and images. The models are based on transformer networks like BERT / RoBERTa / XLM-RoBERTa etc. and achieve state-of-the-art performance in various tasks. Text is embedded in vector space such that similar text are closer and can efficiently be found using cosine similarity. We provide an increasing number of state-of-the-art pretrained models for more than 100 languages, fine-tuned for various use-cases. Further, this framework allows an easy fine-tuning of custom embeddings models, to achieve maximal performance on your specific task. CUDA enabled.

Seems to lend itself to research coding. The real winner here is that you can generate embeddings and vectors for arbitrary text, which would make it ideal for writing a utility that could do only this without a lot of heavy lifting.

Comes with pre-trained models for over 100 languages. Has documentation and examples for building your own models.

ObjectBox Python is a lightweight yet powerful on-device database & vector database. Store Python objects and vectors directly with an easy-to-use CRUD API while enjoying exceptional speed and efficiency. And because it's an embedded database, there's no setup required. Its advanced vector search empowers AI applications including RAG, generative AI, and similarity searches. Designed for high performance, the ObjectBox database runs locally on-device. As an offline-first solution, ObjectBox makes sure your app reliably works offline as well as online.

ACID compliant. Claims to be scalable and sustainable (i.e., it doesn't need a lot of horsepower to run). Queries can be filtered, even across relations.

Embeddings databases are a union of vector indexes (sparse and dense), graph networks and relational databases. This enables vector search with SQL, topic modeling, retrieval augmented generation and more. Embeddings databases can stand on their own and/or serve as a powerful knowledge source for large language model (LLM) prompts.

Features

• Vector search with SQL, object storage, topic modeling, graph analysis and multimodal indexing
• Create embeddings for text, documents, audio, images and video
• Pipelines powered by language models that run LLM prompts, question-answering, labeling, transcription, translation, summarization and more
• Workflows to join pipelines together and aggregate business logic. txtai processes can be simple microservices or multi-model workflows.
• Build with Python or YAML. API bindings available for JavaScript, Java, Rust and Go.
• Run local or scale out with container orchestration

Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-native database, all accessible through GraphQL, REST, and various language clients.

With Weaviate, you can turn your text, images and more into a searchable vector database using state-of-the-art ML models. Weaviate typically performs a 10-NN neighbor search out of millions of objects in single-digit milliseconds. You can use Weaviate to conveniently vectorize your data at import time, or alternatively you can upload your own vectors (say, if you download a model from OpenAI or HuggingFace). Weaviate powers lightning-fast vector searches, but it is capable of much more. Some of its other superpowers include recommendation, summarization, and integrations with neural search frameworks.

Milvus is an open-source vector database built to power embedding similarity search and AI applications. Milvus makes unstructured data search more accessible, and provides a consistent user experience regardless of the deployment environment.

Millisecond search on trillion vector datasets. Rich APIs designed for data science workflows. Consistent user experience across laptop, local cluster, and cloud. Embed real-time search and analytics into virtually any application. Component-level scalability makes it possible to scale up and down on demand. Milvus can autoscale at a component level according to the load type, making resource scheduling much more efficient.

A database that tries to make it easy to build an LLM-like search database. Super-simple API for loading data and querying it.

You can do everything in your code or run it as a server (chroma run --path /path/to/datastore/on/disk) and use an HTTP client to interact with it.