Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
logger
🐤 A minimal viable logger for Prompt/LLM Engineering. Use your IDE as Logging UI - a fast, simple, extensible, zero dependency Node.js logging tool that starts simple in development and is easily extended for production! (by smol-ai)
-
technical-blogs
Technical blogs around data collaboration, data management, and building collaborative applications.
Bit of self-promotion, but Milvus (https://milvus.io) is another open-source vector database option as well (not sure why it isn't listed here). We also have milvus-lite for folks who don't want to stand up a service.
pip install milvus-lite
I think sidecar vector datbases that work with existing dbs will emerge as more prevalent than the pure vector DB. I also think the vector & graph combo on highly interconnected data will have additional benefits for those building a wide range of LLM applications. A good example is the VectorLink architecture with TerminusDB [1] which is based on Hierarchical Navigable Small World graphs written in Rust.
[1] https://github.com/terminusdb-labs/terminusdb-semantic-index...
I think sidecar vector datbases that work with existing dbs will emerge as more prevalent than the pure vector DB. I also think the vector & graph combo on highly interconnected data will have additional benefits for those building a wide range of LLM applications. A good example is the VectorLink architecture with TerminusDB [1] which is based on Hierarchical Navigable Small World graphs written in Rust.
[1] https://github.com/terminusdb-labs/terminusdb-semantic-index...
> You can add instrumentation for observability around that like you would any other code.
i built my own last weekend. https://github.com/smol-ai/logger
dumps things to json files, or to a log store. all you need for prompt engineering and monitoring really! no VC needed, no DataDog of AI yet
Oh, I should probably mention a blog I wrote describing how it works: https://github.com/terminusdb/technical-blogs/blob/main/blog...
Is the emerging architecture made out to be more complicated than what most of the companies are currently building? Perhaps! But this is most likely the general direction where things will start trending towards as the auxiliary ecosystem matures.
Shameless plug: For fellow Ruby-ists we're building an orchestration layer for building LLM applications, inspired by the original, Langchain.rb: https://github.com/andreibondarev/langchainrb