Korvus is an open-source RAG (Retrieval-Augmented Generation) pipeline that consolidates the entire RAG workflow - from embedding generation to text generation - into a single SQL query, significantly reducing architectural complexity and latency.
Search SDK to unify RAG pipeline in a single database query
Korvus is an open-source RAG (Retrieval-Augmented Generation) pipeline that consolidates the entire RAG workflow - from embedding generation to text generation - into a single SQL query, significantly reducing architectural complexity and latency.
Hey there product hunters, We built Korvus, an open-source RAG (Retrieval-Augmented Generation) pipeline that consolidates the entire RAG workflow - from embedding generation to text generation - into a single SQL query, significantly reducing architectural complexity and latency. Here are the spark notes: - Full RAG pipeline (embedding generation, vector search, reranking, and text generation) in one SQL query - SDKs for Python, JavaScript, and Rust (more languages planned) - Built on PostgreSQ
Gratz on the launch, good job by you and your team. Can I self host the database using pgml?
Gratz on the launch!!Wishing you a journey full of achievements and success.
Congrats on the launch! I encountered a similar issue while working on DepsHub (to convert codebase into embeddings and perform searches afterward), so it's great to see someone attempting to address this problem at scale. Is it possible to self-host? How challenging would it be to convert existing embeddings table to use this tool?
Congrats on the launch @cassandra_pgml! Korvus sounds amazing, especially integrating the whole RAG workflow into one SQL query. Do you guys have plans to support other databases besides PostgreSQL in the future? Thanks!
Check the similar products section on this page, or browse the category pages linked in the tags above. Each category page shows all products for a given year, sorted by engagement.
A measure of community engagement at launch. Higher means more people noticed and interacted with the product. It's a traction signal, not a quality rating.
Discussion threads divided by interest score. Above 0.30 is strong. Below 0.15 suggests the product got clicks but not conversation.
Categories come from the product's launch tags. Most products appear in 2-3 categories. The primary category is listed first.