Merge pull request #1438 from janhq/framework

docs: jan framework principles

docs/docs/about/about.md

@@ -1,18 +1,38 @@
 ---
 title: About Jan
 description: Jan is a ChatGPT-alternative that runs on your own computer, with a local API server.
-keywords: [Jan AI,  Jan, ChatGPT alternative, local AI, private AI, conversational AI, no-subscription fee, large language model ]
+keywords:
+  [
+    Jan AI,
+    Jan,
+    ChatGPT alternative,
+    local AI,
+    private AI,
+    conversational AI,
+    no-subscription fee,
+    large language model,
+  ]
 ---
 
-Jan believes in the need for an open source AI ecosystem, and are building the infra and tooling to allow open source AIs to compete on a level playing field with proprietary ones.
+Jan believes in the need for an **open source AI ecosystem**. We are focused on building the infra and tooling to allow open source AIs to compete on a level playing field with proprietary ones.
 
-Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life. 
+Jan's long-term technical endeavor is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.
+
+## Quicklinks
+
+- Core product vision for [Jan Framework](http://localhost:3001/docs/)
+- R&D and model training efforts [Discord](https://discord.gg/9NfUSyzp3y) (via our small data-center which is `free & open to all researchers who lack GPUs`!)
+- Current implementations of Jan Framework: [Jan Desktop](https://jan.ai/), [Nitro](https://nitro.jan.ai/)
 
 ## Why does Jan Exist?
 
 ### Mission
 
-Our mission is to allow humans and businesses to own their AI, with the right to tinker, repair and innovate. 
+Our current mission is to allow humans and businesses to **own their AI, with the right to tinker, repair and innovate**.
+
+:::tip
+Our life-long mission is to **eliminate work - so human can focus on creation, invention, and moral governance over robots**.
+:::
 
 ### Ideal Customer
 
@@ -22,16 +42,19 @@ Our ideal customer is an AI enthusiast or business who has experienced some limi
 
 Our ideal customer would use Jan to solve one of these problems.
 
-*Control*
+_Control_
+
 - Control (e.g. preventing vendor lock-in)
 - Stability (e.g. runs predictably every time)
 - Local-use (e.g. for speed, or for airgapped environments)
 
-*Privacy*
+_Privacy_
+
 - Data protection (e.g. personal data or company data)
 - Privacy (e.g. nsfw)
 
-*Customisability*
+_Customisability_
+
 - Tinkerability (e.g. ability to change model, experiment)
 - Niche Models (e.g. fine-tuned, domain-specific models that outperform OpenAI)
 
@@ -56,7 +79,8 @@ Jan is a seamless user experience that runs on your personal computer, that glue
 
 Jan is a startup with an open source business model. We believe in the need for an open source AI ecosystem, and are committed to building it.
 
-- [Jan: a Personal AI](https://github.com/janhq/jan) (AGPLv3)
+- [Jan Framework](https://github.com/janhq/jan) (AGPLv3)
+- [Jan Desktop Client & Local server](https://jan.ai) (AGPLv3, built on Jan Framework)
 - [Nitro: run Local AI](https://github.com/janhq/nitro) (AGPLv3)
 
 ### Build in Public

docs/docs/docs/01-README.md

@@ -0,0 +1,98 @@
+---
+title: Overview
+slug: /docs
+---
+
+The following low-level docs are aimed at core contributors.
+
+We cover how to contribute to the core framework (aka the `Core SDK`).
+
+:::tip
+If you are interested to **build on top of the framework**, like creating assistants or adding app level extensions, please refer to [developer docs](/developer) instead.
+:::
+
+## Jan Framework
+
+At its core, Jan is a **cross-platform, local-first and AI native framework** that can be used to build anything.
+
+### Extensions
+
+Ultimately, we aim for a `VSCode` or `Obsidian` like SDK that allows **devs to build and customize complex and ethical AI applications for any use case**, in less than 30 minutes.
+
+In fact, the current Jan [Desktop Client](https://jan.ai/) is actually just a specific set of extensions & integrations built on top of this framework.
+
+![Desktop is Extensions](./assets/ExtensionCallouts.png)
+
+:::tip
+We encourage devs to fork, customize, and open source your improvements for the greater community.
+:::
+
+### Cross Platform
+
+Jan follows [Clean Architecture](https://blog.cleancoder.com/uncle-bob/2012/08/13/the-clean-architecture.html) to the best of our ability. Though leaky abstractions remain (we're a fast moving, open source codebase), we do our best to build an SDK that allows devs to **build once, deploy everywhere.**
+
+![Clean Architecture](./assets/CleanArchitecture.jpg)
+
+**Supported Runtimes:**
+
+- `Node Native Runtime`, good for server side apps
+- `Electron Chromium`, good for Desktop Native apps
+- `Capacitor`, good for Mobile apps (planned, not built yet)
+- `Python Runtime`, good for MLOps workflows (planned, not built yet)
+
+**Supported OS & Architectures:**
+
+- Mac Intel & Silicon
+- Windows
+- Linux (through AppImage)
+- Nvidia GPUs
+- AMD ROCm (coming soon)
+
+Read more:
+
+- [Code Entrypoint](https://github.com/janhq/jan/tree/main/core)
+- [Dependency Inversion](https://en.wikipedia.org/wiki/Dependency_inversion_principle)
+
+### Local First
+
+Jan's data persistence happens on the user's local filesystem.
+
+We implemented abstractions on top of `fs` and other core modules in an opinionated way, s.t. user data is saved in a folder-based framework that lets users easily package, export, and manage their data.
+
+Future endeavors on this front include cross device syncing, multi user experience, and more.
+
+Long term, we want to integrate with folks working on [CRDTs](https://www.inkandswitch.com/local-first/), e.g. [Socket Runtime](https://www.theregister.com/2023/04/11/socket_runtime/) to deeply enable local-first software.
+
+Read more:
+
+- [Folder-based wrappers entrypoint](https://github.com/janhq/jan/blob/main/core/src/fs.ts)
+- [Piping Node modules across infrastructures](https://github.com/janhq/jan/tree/main/core/src/node)
+
+:::caution
+Our local first approach at the moment needs a lot of work. Please don't hesitate to refactor as you make your way through the codebase.
+:::
+
+### AI Native
+
+We believe all software applications can be natively supercharged with AI primitives and embedded AI servers.
+
+Including:
+
+- OpenAI Compatible AI [types](https://github.com/janhq/jan/tree/main/core/src/types) and [core extensions](https://github.com/janhq/jan/tree/main/core/src/extensions) to support common functionality like making an inference call.
+- Multiple inference engines through [extensions, integrations & wrappers](https://github.com/janhq/jan/tree/main/extensions/inference-nitro-extension) _On this, we'd like to appreciate the folks at [llamacpp](https://github.com/ggerganov/llama.cpp) and [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) for. To which we'll continue to make commits & fixes back upstream._
+
+- [Code Entrypoint](https://github.com/janhq/jan/tree/main/core/src/api)
+
+## Fun Project Ideas
+
+Beyond the current Jan client and UX, the Core SDK can be used to build many other AI-powered and privacy preserving applications.
+
+- `Game engine`: For AI enabled character games, procedural generation games
+- `Health app`: For a personal healthcare app that improves habits
+- Got ideas? Make a PR into this docs page!
+
+If you are interested to tackle these issues, or have suggestions for integrations and other OSS tools we can use, please hit us up in [Discord](https://discord.gg/5rQ2zTv3be).
+
+:::caution
+Our open source license is copy left, which means we encourage forks to stay open source, and allow core contributors to merge things upstream.
+:::

docs/docs/docs/02-integrations/README.md

@@ -0,0 +1,9 @@
+---
+title: Integrations
+---
+
+Existing and upcoming 3rd party integrations on top of Jan Framework.
+
+From both the core development team, and core contributors.
+
+Suggestions? File an [issue here](https://github.com/janhq/jan/issues)

docs/docs/docs/02-integrations/langchain.md

@@ -0,0 +1,7 @@
+---
+title: Langchain
+---
+
+:::caution
+WIP
+:::

docs/docs/docs/02-integrations/llamacpp.md

@@ -0,0 +1,9 @@
+---
+title: LlamaCPP
+---
+
+## Quicklinks
+
+- Jan Framework [Extension Code](https://github.com/janhq/jan/tree/main/extensions/inference-nitro-extension)
+- ggerganov/llama.pp [Source URL](https://github.com/ggerganov/llama.cpp)
+- [Productized Wrapper](https://nitro.jan.ai/): a bit lower effort to use out of the box

docs/docs/docs/02-integrations/ollama.md

@@ -0,0 +1,7 @@
+---
+title: Ollama
+---
+
+:::caution
+Requested, committed, but not started
+:::

docs/docs/docs/02-integrations/openai.md

@@ -0,0 +1,8 @@
+---
+title: OpenAI
+---
+
+## Quicklinks
+
+- Jan Framework [Extension Code](https://github.com/janhq/jan/tree/main/extensions/inference-openai-extension)
+- OpenAI API [Reference Docs](https://platform.openai.com/docs/api-reference)

docs/docs/docs/02-integrations/openrouter.md

@@ -0,0 +1,7 @@
+---
+title: OpenRouter
+---
+
+:::caution
+Requested, committed, but not started
+:::

docs/docs/docs/02-integrations/tensorrt.md

@@ -0,0 +1,8 @@
+---
+title: TensorRT-LLM
+---
+
+## Quicklinks
+
+- Jan Framework [Extension Code](https://github.com/janhq/jan/tree/main/extensions/inference-triton-trtllm-extension)
+- TensorRT [Source URL](https://github.com/NVIDIA/TensorRT-LLM)

docs/docs/docs/README.md

@@ -1,71 +0,0 @@
----
-title: Overview
-slug: /docs
----
-
-The following low-level docs are aimed at core contributors and cover how to contribute to the core SDK.
-
-:::tip
-If you are interested to **build on top of the SDK**, like creating assistants or adding app level extensions, please refer to [developer docs](/developer) instead.
-:::
-
-## Jan Framework
-
-At its core, Jan is a cross-platform, local-first and AI native framework that can be used to build anything. In fact, current features are all implemented as 3rd party extensions on top of this core SDK.
-
-Ultimately, we aim for a VSCode or Obsidian like framework that allows devs to build and customize complex AI applications for their specific needs, in less than 30 minutes.
-
-### Cross Platform
-
-Jan follows [Clean Architecture](https://blog.cleancoder.com/uncle-bob/2012/08/13/the-clean-architecture.html) to the best of our ability. Though leaky abstractions remain (we're a fast moving, open source codebase), we do our best to build an SDK that allows devs to **build once, deploy everywhere.**
-
-Currently, Jan supports:
-
-- `Node Native Runtime`, good for server side apps
-- `Electron Chromium`, good for Desktop Native apps
-- `Capacitor`, good for Mobile apps (planned, not built yet)
-- `Python Runtime`, good for MLOps workflows (planned, not built yet)
-
-Currently, Jan works across:
-
-- Mac Intel & Silicon
-- Windows
-- Ubuntu
-- Nvidia GPUs
-
-Read more:
-
-- [Code Entrypoint](https://github.com/janhq/jan/tree/main/core)
-- [Dependency Inversion](https://en.wikipedia.org/wiki/Dependency_inversion_principle)
-
-### Local First
-
-Jan's data persistence happens on the user's local filesystem.
-
-We implemented abstractions on top of `fs` and other core modules in an opinionated way, s.t. user data is saved in a folder-based framework that lets users easily package, export, and manage their data.
-
-Read more:
-
-- [Folder-based fs wrapper](https://github.com/janhq/jan/blob/main/core/src/fs.ts)
-- [Piping Node modules across infrastructures](https://github.com/janhq/jan/tree/main/core/src/node)
-
-### AI Native
-
-All software applications can be natively supercharged with an embedded AI server and AI abstractions.
-
-Including:
-
-- OpenAI Compatible AI [types](https://github.com/janhq/jan/tree/main/core/src/types) and [core extensions](https://github.com/janhq/jan/tree/main/core/src/extensions) to support common functionality like making an inference call.
-- A lightweight, embedded C++ [inference engine](https://github.com/janhq/jan/tree/main/extensions/inference-nitro-extension) that's immediately callable from code.
-
-- [Code Entrypoint](https://github.com/janhq/jan/tree/main/core/src/api)
-
-## Fun Project Ideas
-
-Beyond the current Jan client and UX, the Core SDK can be used to build many other AI-powered and privacy preserving applications.
-
-- `Game engine`: For AI enabled character games, procedural generation games
-- `Health app`: For a personal healthcare app that improves habits
-- Got ideas? Make a PR into this docs page!
-
-If you are interested to tackle these issues, or have suggestions for integrations and other OSS tools we can use, please hit us up in [Discord](https://discord.gg/5rQ2zTv3be).