gollum
CopilotKit
gollum | CopilotKit | |
---|---|---|
4 | 14 | |
37 | 1,113 | |
- | - | |
6.0 | 10.0 | |
8 days ago | 6 months ago | |
Go | TypeScript | |
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...
CopilotKit
-
[D] Needle in a haystack experiment: Assistants API RAG beats GPT 4-Turbo & Llama Index at 4% of the cost
I recently added a new document-oriented react hook to CopilotKit, made specifically to accommodate (potentially long-form) documents and wanted to get the best performance.
- I turned OpenAI's API into a library of React Components
- CopilotKit: AI react components built on top of Open AI's Assistants API
- SR: I built an Open-source library of plug & play react AI-Copilot Components. ~1hr to integration.
- CopilotKit: Open-Source React Library for easily integrating an embedded AI-copilot
- Show HN: CopilotTextarea/> = an open-source, AI-infused react <textarea>
- Add Plug and Play Copilot Features to Any React App – CopilotKit (Open Source)
- Show HN: CopilotTextarea: textarea for react with Copilot autocompletions
- Show HN: CopilotKit adds CopilotTextarea (built with slateJS)
- Show HN: CopilotTextarea: <Textarea/> W GPT Completions Like Gmail/GitHub. OSS
What are some alternatives?
ts-patch - Augment the TypeScript compiler to support extended functionality
zod-gpt - Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models.
ai-agents-laravel - Build AI Agents for popular LLMs quick and easy in Laravel
voy - 🕸️🦀 A WASM vector similarity search written in Rust
LLM-OpenAPI-minifier - Making openapi spec swagger documents friendly for GPT and other LLMs.
TypeChat - TypeChat is a library that makes it easy to build natural language interfaces using types.
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​.
shelby_as_a_service - Production-ready LLM Agents. Just add API keys