Open Source Python Vector Search Engines

Jina is a framework that empowers anyone to build cross-modal and multi-modal applications on the cloud. It uplifts a PoC into a production-ready service. Jina handles the infrastructure complexity, making advanced solution engineering and cloud-native technologies accessible to every developer. Build applications that deliver fresh insights from multiple data types such as text, image, audio, video, 3D mesh, PDF with Jina AI’s DocArray. Polyglot gateway that supports gRPC, Websockets, HTTP, GraphQL protocols with TLS. Intuitive design pattern for high-performance microservices. Seamless Docker container integration: sharing, exploring, sandboxing, versioning and dependency control via Jina Hub. Fast deployment to Kubernetes, Docker Compose and Jina Cloud. Improved engineering efficiency thanks to the Jina AI ecosystem, so you can focus on innovating with the data applications you build.

Vector AI is a framework designed to make the process of building production-grade vector-based applications as quick and easily as possible. Create, store, manipulate, search and analyze vectors alongside json documents to power applications such as neural search, semantic search, personalized recommendations etc. Image2Vec, Audio2Vec, etc (Any data can be turned into vectors through machine learning). Store your vectors alongside documents without having to do a db lookup for metadata about the vectors. Enable searching of vectors and rich multimedia with vector similarity search. The backbone of many popular A.I use cases like reverse image search, recommendations, personalization, etc. There are scenarios where vector search is not as effective as traditional search, e.g. searching for skus. Vector AI lets you combine vector search with all the features of traditional search such as filtering, fuzzy search, and keyword matching to create an even more powerful search.

UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space! It comes with a set of homonymous pre-trained networks available on HuggingFace portal and extends the transfromers package to support Mid-fusion Models. Late-fusion models encode each modality independently, but into one shared vector space. Due to independent encoding late-fusion models are good at capturing coarse-grained features but often neglect fine-grained ones. This type of models is well-suited for retrieval in large collections. The most famous example of such models is CLIP by OpenAI. Early-fusion models encode both modalities jointly so they can take into account fine-grained features. Usually, these models are used for re-ranking relatively small retrieval results. Mid-fusion models are the golden midpoint between the previous two types. Mid-fusion models consist of two parts – unimodal and multimodal.

vectordb is a Pythonic vector database offers a comprehensive suite of CRUD (Create, Read, Update, Delete) operations and robust scalability options, including sharding and replication. It's readily deployable in a variety of environments, from local to on-premise and cloud. vectordb delivers exactly what you need - no more, no less. It's a testament to effective Pythonic design without over-engineering, making it a lean yet powerful solution for all your needs. vectordb capitalizes on the powerful retrieval prowess of DocArray and the scalability, reliability, and serving capabilities of Jina. Here's the magic: DocArray serves as the engine driving vector search logic, while Jina guarantees efficient and scalable index serving. This synergy culminates in a robust, yet user-friendly vector database experience, that's vectordb for you.

txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. Traditional search systems use keywords to find data. Semantic search applications have an understanding of natural language and identify results that have the same meaning, not necessarily the same keywords. Backed by state-of-the-art machine learning models, data is transformed into vector representations for search (also known as embeddings). Innovation is happening at a rapid pace, models can understand concepts in documents, audio, images and more. Machine-learning pipelines to run extractive question-answering, zero-shot labeling, transcription, translation, summarization and text extraction. Cloud-native architecture that scales out with container orchestration systems (e.g. Kubernetes). Applications range from similarity search to complex NLP-driven data extractions to generate structured databases. The following applications are powered by txtai.

AnnLite is a lightweight and embeddable library for fast and filterable approximate nearest neighbor search (ANNS). It allows to search for nearest neighbors in a dataset of millions of points with a Pythonic API. A simple API is designed to be used with Python. It is easy to use and intuitive to set up to production. The library uses a highly optimized approximate nearest neighbor search algorithm (HNSW) to search for nearest neighbors. The library allows you to search for nearest neighbors within a subset of the dataset. Smooth integration with neural search ecosystem including Jina and DocArray, so that users can easily expose search API with gRPC and/or HTTP. The library is easy to install and use. It is designed to be used with Python. To support search with filters, the annlite must be created with colums parameter, which is a series of fields you want to filter by.

Easy build your personal search engine with Aquila Network. Aquila X is the gateway to Aquila Network and it's applications. AquilaX is a smart bookmarking tool. You can keep your bookmarks and search through it's contents. Choose to keep all your data in a local server or in the cloud. This is an open source software and thus is auditable.

Cherche allows the creation of efficient neural search pipelines using retrievers and pre-trained language models as rankers. Cherche's main strength is its ability to build diverse and end-to-end pipelines from lexical matching, semantic matching, and collaborative filtering-based models. Cherche provides modules dedicated to summarization and question answering. These modules are compatible with Hugging Face's pre-trained models and fully integrated into neural search pipelines. Search is fully compatible with the collaborative filtering library Implicit. It is advantageous if you have a history associated with users and you want to retrieve / re-rank documents based on user preferences.

DocArray is a library for nested, unstructured, multimodal data in transit, including text, image, audio, video, 3D mesh, etc. It allows deep-learning engineers to efficiently process, embed, search, recommend, store, and transfer multimodal data with a Pythonic API. Door to multimodal world: super-expressive data structure for representing complicated/mixed/nested text, image, video, audio, 3D mesh data. The foundation data structure of Jina, CLIP-as-service, DALL·E Flow, DiscoArt etc. Data science powerhouse: greatly accelerate data scientists’ work on embedding, k-NN matching, querying, visualizing, evaluating via Torch/TensorFlow/ONNX/PaddlePaddle on CPU/GPU. Data in transit: optimized for network communication, ready-to-wire at anytime with fast and compressed serialization in Protobuf, bytes, base64, JSON, CSV, DataFrame. Perfect for streaming and out-of-memory data. One-stop k-NN: Unified and consistent API for mainstream vector databases.

One line to host them all. Bootstrap your multimodal search case in minutes. NOW gives the world access to multimodal neural search with just one command. NOW supports various formats for uploading your dataset to your search application. You may either choose a demo dataset hosted by NOW, or use your own custom dataset, to build an application. NOW can support your custom data in the form of a DocumentArray, as a path to a local folder, or S3 bucket. You can choose a demo dataset to get started quickly. The demo datasets are hosted by NOW which can be easily used to build a search application. There is a large variety of datasets, including images, text, and audio. Perhaps your data is stored in an S3 bucket, which is an option NOW also supports. In this case, NOW asks for the URI to the S3 bucket, as well as the credentials and region thereof. A final step in loading your data is to choose the fields of your data that you would like to use for search and filter respectively.

A tensor-based search and analytics engine that seamlessly integrates with your applications, websites, and workflows. Marqo is a versatile and robust search and analytics engine that can be integrated into any website or application. Due to horizontal scalability, Marqo provides lightning-fast query times, even with millions of documents. Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. It can seamlessly handle image-to-image, image-to-text and text-to-image search and analytics. Marqo adapts and stores your data in a fully schemaless manner. It combines tensor search with a query DSL that provides efficient pre-filtering. Tensor search allows you to go beyond keyword matching and search based on the meaning of text, images and other unstructured data. Be a part of the tribe and help us revolutionize the future of search. Whether you are a contributor, a user, or simply have questions about Marqo, we got your back.