EdgeChains
pingora
EdgeChains | pingora | |
---|---|---|
12 | 8 | |
298 | 19,682 | |
7.7% | 8.4% | |
9.4 | 8.7 | |
5 days ago | 13 days ago | |
JavaScript | Rust | |
MIT License | Apache License 2.0 |
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.
EdgeChains
-
HonoJS: Small, simple, and ultrafast web framework for the Edges
We build a WASM compiler to compile our prompts and chains into webassembly. Honojs was a critical part of it.
https://github.com/arakoodev/EdgeChains/
- looking for someone to codereview an opensource Typescript+webassembly framework for Generative AI apps
-
Overview: AI Assembly Architectures
EdgeChains: github.com/arakoodev/EdgeChains
-
Stanford DSPy: The framework for programming with foundation models
would love your thoughts on this as well - https://github.com/arakoodev/edgechains
got frustrated in the same way with "Black Box Prompting - every library hides prompts/chains in layers of libraries...while it should have been declarative.
EdgeChains - allows u to specify ur prompt and chain in jsonnet. This why i think Generative AI needs declarative orchestration and not previous generations. https://github.com/arakoodev/edgechains#why-do-you-need-decl...
-
Show HN: Chat with your data using LangChain, Pinecone, and Airbyte
when will you have pgvector as a destination ? we (https://github.com/arakoodev/edgechains) work with a lot of enterprises and they would not move away from using redis or pgvector even as their vector store. Is there a way where we can leverage that ?
Second, for a LOT of enterprises, they want to use non-openai embedding models (minilm, GTE, BGE), will you support that. For e.g. in Edgechains we natively support BGE and minilm. Would you be able to support that ?
-
Chunking 2M+ files a day for Code Search using Syntax Trees
oh really ? Thats awfully kind. I'll take that in for EdgeChains as well.
https://github.com/arakoodev/EdgeChains/issues/172
-
Langchain Is Pointless
Promptfile is written in markdown, which is unsuited for templates and config management.
I have an attempt in the same domain, would love feedback
We didnt invent a new markup - we used jsonnet which is used in large scale kubernetes and has a grammar that has been well tested for config mgmt.
https://github.com/arakoodev/EdgeChains/blob/main/Examples/r...
Prompts live outside the code.
- Calling ChatGPT API from Spring Boot
pingora
- Pingora Restart Without Downtime
-
HonoJS: Small, simple, and ultrafast web framework for the Edges
This is also called a framework:
https://github.com/cloudflare/pingora
Pingora is actually fast and small (it does not require a JS engine). Way faster and smaller than Hono.
If you want something to be really fast: do not use RegExes.
- Pingora 0.1.0 – First Public Release
-
Cloudflare Makes Pingora Rust Framework Open-Source
So it looks like they are intending this more as a framework that you build your own custom proxy on top of for your team/company. So you just extend the conf for your custom filters and then you add the wrapper systemd Service.
I might try wrapping it in an envoy style service as a weekend project and just dockerizing it, seems pretty straightforward.
They have a recommended systemd config: https://github.com/cloudflare/pingora/blob/8797329225018c4d0...
And their conf support: https://github.com/cloudflare/pingora/blob/8797329225018c4d0...
-
Pingora: HTTP Server and Proxy Library, in Rust, by Cloudflare, Released
cert it via cron that uses the graceful upgrade functionality should work
https://github.com/cloudflare/pingora/blob/main/docs/quick_s...
- Pingora: A library for building fast, reliable and evolvable network services
What are some alternatives?
autogen - A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
plane - A distributed system for running WebSocket services at scale.
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
rustls - A modern TLS library in Rust
AgentVerse - 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
coexist - Unobtrusively server-render JS pages from non-JS frameworks.
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
middleware - monorepo for Hono third-party middleware/helpers/wrappers
awesome-ai-agents - A list of AI autonomous agents
aici - AICI: Prompts as (Wasm) Programs
langchain - 🦜🔗 Build context-aware reasoning applications
blog - Using Cloudflare Workers to proxy dev.to posts and cache at edge