diff --git a/knowledge base/ai/README.md b/knowledge base/ai/README.md index 5bd4356..9595345 100644 --- a/knowledge base/ai/README.md +++ b/knowledge base/ai/README.md @@ -18,7 +18,7 @@ TODO ## Further readings - [Useful AI]: tools, courses, and more, curated and reviewed by experts. -- [ChatGPT], [Claude], [Copilot], [Duck AI], [Gemini] +- LLMs: [ChatGPT], [Claude], [Copilot], [Duck AI], [Gemini] ### Sources diff --git a/knowledge base/ai/huggingface.md b/knowledge base/ai/huggingface.md new file mode 100644 index 0000000..6cb8ea4 --- /dev/null +++ b/knowledge base/ai/huggingface.md @@ -0,0 +1,67 @@ +# Hugging Face + +AI community trying to democratize _good_ machine learning. + +1. [TL;DR](#tldr) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + + + + + + + +## Further readings + +- [Website] +- [Codebase] +- [Blog] +- [Learning material] + +### Sources + +- [Documentation] + + + + + + + +[Blog]: https://huggingface.co/blog +[Codebase]: https://github.com/huggingface +[Documentation]: https://huggingface.co/docs +[Learning material]: https://huggingface.co/learn +[Website]: https://huggingface.co/ + + diff --git a/knowledge base/ai/lmstudio.md b/knowledge base/ai/lmstudio.md new file mode 100644 index 0000000..90fd8da --- /dev/null +++ b/knowledge base/ai/lmstudio.md @@ -0,0 +1,67 @@ +# LMStudio + +Allows running LLMs locally. + + + +1. [TL;DR](#tldr) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + +
+ Setup + +```sh +brew install --cask 'lm-studio' +``` + +
+ + + + + +## Further readings + +- [Website] +- [Codebase] +- [Blog] + +### Sources + +- [Documentation] + + + + + + + +[Blog]: https://lmstudio.ai/blog +[Codebase]: https://github.com/lmstudio-ai +[Documentation]: https://lmstudio.ai/docs/ +[Website]: https://lmstudio.ai/ + + diff --git a/knowledge base/ai/ollama.md b/knowledge base/ai/ollama.md new file mode 100644 index 0000000..8a99d14 --- /dev/null +++ b/knowledge base/ai/ollama.md @@ -0,0 +1,90 @@ +# Ollama + +The easiest way to get up and running with large language models. + + + +1. [TL;DR](#tldr) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + +
+ Setup + +```sh +brew install --cask 'ollama-app' # or just brew install 'ollama' +``` + +
+ +Cloud models are automatically offloaded to Ollama's cloud service.
+This allows to keep using one's local tools while running larger models that wouldn't fit on a personal computer.
+Those models are _usually_ tagged with the `cloud` suffix. + +
+ Usage + +```sh +# Download models. +ollama pull 'qwen2.5-coder:7b' +ollama pull 'glm-4.7:cloud' + +# List pulled models. +ollama list + +# Run models. +ollama run 'gemma3' + +# Quickly set up a coding tool with Ollama models. +ollama launch + +# Launch models. +ollama launch 'claude' --model 'glm-4.7-flash' + +# Only configure model, without launching them. +ollama launch 'claude' --config + +# Sign into Ollama cloud, or create a new account. +ollama signin +``` + +
+ + + +## Further readings + +- [Website] +- [Codebase] +- [Blog] + +### Sources + +- [Documentation] + + + + + + + +[Blog]: https://ollama.com/blog +[Codebase]: https://github.com/ollama/ollama +[Documentation]: https://docs.ollama.com/ +[Website]: https://ollama.com/ + + diff --git a/knowledge base/ai/openhands.md b/knowledge base/ai/openhands.md new file mode 100644 index 0000000..21e963c --- /dev/null +++ b/knowledge base/ai/openhands.md @@ -0,0 +1,73 @@ +# OpenHands + +Community focused on AI-driven development. + +1. [TL;DR](#tldr) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + +
+ Setup + +```sh +docker pull 'docker.openhands.dev/openhands/runtime:1.2-nikolaik' +docker run -it --rm --name 'openhands-app' --pull='always' \ + -e 'AGENT_SERVER_IMAGE_REPOSITORY=docker.openhands.dev/openhands/runtime' \ + -e 'AGENT_SERVER_IMAGE_TAG=1.2-nikolaik' \ + -e 'LOG_ALL_EVENTS=true' \ + -v '/var/run/docker.sock:/var/run/docker.sock' \ + -v "$HOME/.openhands:/.openhands" \ + -p '3000:3000' \ + --add-host 'host.docker.internal:host-gateway' \ + 'docker.openhands.dev/openhands/openhands:1.2' +``` + +
+ + + + + +## Further readings + +- [Website] +- [Codebase] +- [Blog] + +### Sources + +- [Documentation] + + + + + + + +[Blog]: https://openhands.dev/blog +[Codebase]: https://github.com/OpenHands/OpenHands +[Documentation]: https://docs.openhands.dev/ +[Website]: https://openhands.dev/ + + diff --git a/knowledge base/ai/use a local llm for coding assistance in vscode.md b/knowledge base/ai/use a local llm for coding assistance in vscode.md new file mode 100644 index 0000000..66e7491 --- /dev/null +++ b/knowledge base/ai/use a local llm for coding assistance in vscode.md @@ -0,0 +1,56 @@ +# Use a local LLM for coding assistance in VSCode + +1. [Setup](#setup) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## Setup + +1. Install Ollama and download the models you mean to use.
+ Refer [Ollama]. + +
+ + ```sh + brew install 'ollama' + ollama pull 'llama3.1:8b' + ollama pull 'qwen2.5-coder:7b' + ollama pull 'nomic-embed-text:latest' + ``` + +
+ +1. Install the [Continue VSCode extension]. +1. Configure the extension to use local LLMs only. + +
+ + 1. Open the extension's sidebar. + 1. In the top-right, select Local Config from the dropdown menu. + 1. Eventually, tweak the configuration file. + +
+ +## Further readings + +- [Ollama] +- [Continue VSCode extension] + +### Sources + +- [How to use a local LLM as a free coding copilot in VS Code] + + + + + +[Ollama]: ollama.md + + + + +[Continue VSCode extension]: https://marketplace.visualstudio.com/items?itemName=Continue.continue +[How to use a local LLM as a free coding copilot in VS Code]: https://medium.com/@smfraser/how-to-use-a-local-llm-as-a-free-coding-copilot-in-vs-code-6dffc053369d diff --git a/knowledge base/jargon.md b/knowledge base/jargon.md index 617b980..55dfb92 100644 --- a/knowledge base/jargon.md +++ b/knowledge base/jargon.md @@ -90,6 +90,7 @@ | LAN | Local Area Network | | | LED | Light Emitting Diode | | | LIFO | Last In First Out | | +| LLM | Large Language Model | | | M2COTS | Mass Market COTS | Widely available COTS products | | MR | Merge Request | Prevalently used in GitLab | | NACL | Network ACL | |