txtai might be a bit more popular than Typesense. We know about 76 links to it since March 2021 and only 58 links to Typesense. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Txtai is an all-in-one embeddings database for semantic search, LLM orchestration and language model workflows. - Source: dev.to / 4 months ago
Ideal For: Projects requiring quick setup and robust search capabilities. GitHub Repository. - Source: dev.to / 4 months ago
Excellent project. As mentioned in another comment, I've put together an embeddings database using the arxiv dataset (https://huggingface.co/NeuML/txtai-arxiv) recently. For those interested in the literature search space, a couple other projects I've worked on that may be of interest. Annotateai (https://github.com/neuml/annotateai) - Semantic search and workflows for medical/scientific papers. Built on txtai... - Source: Hacker News / 4 months ago
If you're looking for a lightweight open-source framework designed to handle the patterns mentioned in this article: https://github.com/neuml/txtai Disclaimer: I'm the author of the framework. - Source: Hacker News / 4 months ago
I fully agree. Postgres has solved many of the problems that many are re-solving with GenAI related databases. With txtai (https://github.com/neuml/txtai), I've went all in with Postgres + pgvector. Projects can start small with a SQLite backend then switch the persistence to Postgres. With this, you get all the years of battle-tested production experience from Postgres... - Source: Hacker News / 5 months ago
You might want to look at https://typesense.org/ for that. - Source: Hacker News / 18 days ago
We use https://typesense.org/ for regular search, but it now has support for doing hybrid search, curious if anyone has tried it yet? - Source: Hacker News / 5 months ago
Took me a little poking around to figure out what the underlying search engine was: it's https://typesense.org/ hosted in a Docker container. - Source: Hacker News / 7 months ago
We all make mistakes at times, and we've all made a typo here and there at some point in our lives. Typesense is here to change all that, with a typo-tolerant, in-memory, fuzzy search engine. The latest release has a new mode, better typo tolerance, support for new references and synonyms, new search parameters, and AI search improvements. Check out all the breaking changes and major updates in the Typesense... - Source: dev.to / 8 months ago
Alternatives to both are https://www.meilisearch.com/ https://typesense.org/ and maybe https://github.com/Sygil-Dev/whoosh-reloaded. - Source: Hacker News / 9 months ago
Milvus - Vector database built for scalable similarity search Open-source, highly scalable, and blazing fast.
Algolia - Algolia's Search API makes it easy to deliver a great search experience in your apps & websites. Algolia Search provides hosted full-text, numerical, faceted and geolocalized search.
Weaviate - Welcome to Weaviate
Meilisearch - Ultra relevant, instant, and typo-tolerant full-text search API
Vespa.ai - Store, search, rank and organize big data
ElasticSearch - Elasticsearch is an open source, distributed, RESTful search engine.