dify VS greptimedb

> https://github.com/langgenius/dify/blob/main/LICENSE

everyone is apparently a license pioneer

Xorbits Inference (Xinference) is an open-source platform to streamline the operation and integration of a wide array of AI models. With Xinference, you’re empowered to run inference using any open-source LLMs, embedding models, and multimodal models either in the cloud or on your own premises, and create robust AI-driven applications. It provides a RESTful API compatible with OpenAI API, Python SDK, CLI, and WebUI. Furthermore, it integrates third-party developer tools like LangChain, LlamaIndex, and Dify, facilitating model integration and development.

If you are looking to develop QnA or chat based apps then check out https://dify.ai. Do a quick check and see if it fit your requirements. You can integrate it with your app using the apis it provides

As an AI newbie, I used to find coding apps from scratch an absolute nightmare! The learning curve was steep as a ski slope, debugging took endless hours, and developing even a simple AI app nearly drove me insane! But since discovering Dify, it has totally revolutionized my life by enabling app development without any coding skills!

GreptimeAI, built upon the open-source time-series database GreptimeDB, offers an observability solution for Large Language Model (LLM) applications, currently supporting both LangChain and OpenAI's ecosystem. GreptimeAI enables you to understand cost, performance, traffic and security aspects in real-time, helping teams enhance the reliability of LLM applications.

Continuing to work hard on a new MetricEngine in GreptimeDB. BTW, If you have a keen interest in Rust or database development, GreptimeDB might be a good starting point. Check it out for some good first issues here.

Since the very first day of GreptimeDB going open-source, it embraced the automated software building process with GitHub Actions, and leading to the inaugural Release Pipeline.

Born from the open-source project GreptimeDB, GreptimeCloud serves as a fully-managed, serverless cloud backend for Prometheus, offering integrated support for remote read/write protocols and PromQL as one of our primary query languages.

Recently, while working on our GreptimeDB project, we encountered an issue with calling asynchronous Rust code in a synchronous context.

To explore data stored in GreptimeDB through PromQL, GreptimeDB needs to provide the ability to parse the query into AST (abstract syntax tree), and retrieve data from memory or disk via logical and physical plans. Since there is no ready-to-use PromQL Rust Parser, our team decides to develop it by ourselves. We’re glad to announce that promql-parser v0.1.0 is now available.

This is truly a fantastic combination -- implement the logic in Rust and use it in Python. GreptimeDB also implements a similar functionality that allows writing Python script to do post-process of SQL query results, with the help of RustPython and Arrow. Maybe this combination can bring a sweet point between performance and efficiency.

docs: https://docs.greptime.com/user-guide/coprocessor-and-scripti...

code: https://github.com/GreptimeTeam/greptimedb/tree/develop/src/...