gollum
shelby_as_a_service
gollum | shelby_as_a_service | |
---|---|---|
4 | 4 | |
37 | 6 | |
- | - | |
6.0 | 9.3 | |
8 days ago | 6 months ago | |
Go | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
gollum
-
From slow to SIMD: A Go optimization story
I did a similar optimization via https://github.com/viterin/vek as the SIMD version. Some somewhat unscientific calculations showed a 10x improvement staying in float32: https://github.com/stillmatic/gollum/blob/07a9aa35d2517af8cf...
TBH my takeaway was that it was more useful to use smaller vectors as a representation
-
Agency: Pure Go LangChain Alternative
I like Go a lot for working with OpenAI etc, it's 'just' API calls and Go is great at that. I've opensourced some bits here: https://github.com/stillmatic/gollum -- in particular, function dispatch (given a prompt, return an arbitrary Go struct) is really nice, as is a very fast in-memory KNN index.
-
Introducing TypeChat from Microsoft
I've written a version of this in Golang: https://github.com/stillmatic/gollum/blob/main/dispatch.go
```go
-
FANN: Vector Search in 200 Lines of Rust
I have gotten 10x speedups with SIMD on modern hardware. Goroutines make this actually fairly tricky, as you essentially have to process all the events and then sort the entire array, which is usually the bottleneck. The heap adds a small amount of complexity but is significantly more efficient, feels like good ROI.
https://github.com/stillmatic/gollum/blob/main/vectorstore.g...
shelby_as_a_service
-
Introducing TypeChat from Microsoft
It’s logit bias. You don’t even need another library to do this. You can do it with three lines of python.
Here’s an example of one of my implementations of logit bias.
https://github.com/ShelbyJenkins/shelby-as-a-service/blob/74...
- Easy-to-Deploy Q&A Bot for Discord/Slack
- Documentation Accessible to GPT: Easy-to-Deploy Q&A Bot for Discord/Slack
-
Understanding LangChain Basic Concepts
Sort of. I’ve found it’s value , currently, is not in its intended purpose to build “chains” of tools. The moment you have to do something non-standard you have to build from scratch which is more difficult with all of the abstraction involved.
Where I do find it useful is the many tools it saves me from having to build from scratch. I don’t need to build a page scraper or an embedding service with retries are two things I use it for the bot I built for my companies slack and discord. In theory I could see using it more in my project eventually. https://github.com/ShelbyJenkins/shelby-as-a-service
What are some alternatives?
CopilotKit - Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps. [Moved to: https://github.com/CopilotKit/CopilotKit]
TypeChat - TypeChat is a library that makes it easy to build natural language interfaces using types.
ts-patch - Augment the TypeScript compiler to support extended functionality
ai-agents-laravel - Build AI Agents for popular LLMs quick and easy in Laravel
voy - 🕸️🦀 A WASM vector similarity search written in Rust
CopilotKit - A framework for building custom AI Copilots 🤖 in-app AI chatbots, in-app AI Agents, & AI-powered Textareas.
Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
zod-gpt - Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models.