- macOS (Apple Silicon or Intel)
- Homebrew installed
- Git installed
- Databricks Workspace
- Databricks account with appropriate permissions
uv python list Great! You already have all the Python versions you need. There's no need to install them again.
Here's what you have installed:
| Python Version | Installed | Location |
|---|---|---|
| β 3.11.9 | Yes | /Users/welcome/anaconda3/bin/python |
| β 3.12.11 | Yes | /opt/homebrew/bin/python3.12 |
| β 3.13.13 | Yes | /opt/homebrew/bin/python3.13 |
| On a Mac, `.rar` files are not supported by default, so you need a tool to extract them. Here are the easiest ways: | |
| ### Option 1: Use βThe Unarchiverβ (recommended) | |
| 1. Install it from the Mac App Store: **The Unarchiver** | |
| 2. Open it once after installation. | |
| 3. Go to **Settings β Archive Formats** and make sure **RAR** is checked. | |
| 4. Now just **double-click your .rar file** (or right-click β Open With β The Unarchiver). | |
| 5. It will extract the files into the same folder (or ask you where to save). |
(base) welcome@jaisairams-Laptop ~ % source ~/.zprofile.sh (base) welcome@jaisairams-Laptop ~ % curl -fsSL https://floci.io/install.sh | sh Installing Floci CLI... Downloading floci 0.1.8 for darwin-arm64... Checksum verified. Installing to /usr/local/bin requires sudo... Password:
Floci CLI 0.1.8 installed to /usr/local/bin/floci
| cd /Users/welcome/Desktop/sai_welcome_hanuman/welcome_sairam_repo/monocle/test_tools | |
| ./.venv/bin/python -m pytest tests/integration/test_non_llm_*eval*.py tests/unit/test_non_llm_*eval*.py -q --disable-warnings | |
| ============================= test session starts ============================== | |
| platform darwin -- Python 3.10.0, pytest-9.0.3, pluggy-1.6.0 | |
| rootdir: /Users/welcome/Desktop/sai_welcome_hanuman/welcome_sairam_repo/monocle/test_tools |
(.venv) welcome@jaisairams-Laptop demo % cd ..
(.venv) welcome@jaisairams-Laptop spec_experiments % uvx --from git+https://github.com/github/spec-kit.git specify init copilot_example
βββββββββββββββ ββββββββ βββββββββββββββββββββ βββ
βββββββββββββββββββββββββββββββββββββββββββββββ ββββ
ββββββββββββββββββββββ βββ βββββββββ βββββββ
βββββββββββββββ ββββββ βββ βββββββββ βββββ
βββββββββββ ββββββββββββββββββββββ βββ
βββββββββββ ββββββββ βββββββββββββ βββ
| curl -fsSL https://ollama.com/install.sh | sh | |
| ollama run qwen3.5:9b | |
| qwen3.5:9b | |
| export ANTHROPIC_AUTH_TOKEN=ollama # required but ignored |
Based on my research, here's a comprehensive deep summary on LangGraph:
LangGraph is a low-level orchestration framework for building, managing, and deploying stateful, multi-actor agents powered by LLMs. It's designed for building long-running workflows that need persistence, memory, and complex control flow.
Key distinction: LangGraph is NOT a high-level agent framework like LangChain's agents. It's intentionally low-level, focusing entirely on agent orchestration and runtime capabilities.