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 PostgreSQL, leveraging pgvector and pgml
- Open-source, with support for open models
- Designed for high performance and scalability
Korvus utilizes Postgres' advanced features to perform complex RAG operations natively within the database.
We're also the developers of PostgresML, so we're big advocates of in-database machine learning. This approach eliminates the need for external services and API calls, potentially reducing latency by orders of magnitude compared to traditional microservice architectures. It's how our founding team built and scaled the ML platform at Instacart.
We're eager to get feedback from the community and welcome contributions. Check out our GitHub repo for more details, and feel free to hit us up in our Discord!
Report
@cassandra_pgml Cheers to the team behind this! Wishing you all the best on this new adventure. What are you most excited about with this launch?
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!
Korvus
DepsHub
ToyPal
Korvus
ToyPal
Serand
Korvus