Development Environments and APIs
Technical guides on Development Environments and APIs.
-
Find Missing Ollama Models in Open WebUI
Check which Ollama endpoint Open WebUI uses, inspect the server’s model list and verify container networking and configuration.
-
Run vLLM on RTX: Rocky Linux 9 and Ubuntu 24.04 or 26.04
Check GPU and Python requirements, prepare vLLM on the target Linux distribution and test model serving with the recorded configuration.
-
[Local LLM 08] Install Python and Create Project Environments
Install Python, create a virtual environment per project and verify which interpreter and package installer are active.
-
[Local LLM 09] Install Node.js and npm and Check Executable Paths
Verify Node.js and npm installation, locate the executable used by the terminal, and inspect project dependency handling.
-
[Local LLM 10] Install WSL2 and Understand Files and Networking
Prepare WSL2 and identify which environment owns a file path, process or network endpoint when working between Windows and Linux.
-
[Local LLM 11] Understand Docker Desktop, Containers, Volumes and Ports
Install and check Docker Desktop, then distinguish container processes, persistent volumes and published ports.
-
[Local LLM 12] Set Up Web Chat with Open WebUI and Ollama
Connect Open WebUI to the correct Ollama endpoint and verify model discovery, container networking and persistent data.
-
[Local LLM 13] Call the Ollama API from Python
Send a request to the local Ollama API from Python, handle the response, and distinguish connection errors from model errors.
-
[Local LLM 14] Write Prompts with Clear Source Text and Constraints
Separate instructions, reference text and output constraints so that a model request can be checked and repeated.