Andrius: I'm learning how to access AI programmatically through an API using Python.
Artificial Intelligence
API
Daniel recommended a free and low-cost LLM: https://openrouter.ai/
https://openrouter.ai/openai/gpt-oss-20b:free OpenAI: gpt-oss-20b
Programming languages
Python
requests HTTP library for Python
langextract Daniel recommended https://github.com/google/langextract "Python library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions." I could try to craft instructions and examples related to the ideas I want to parse from documents.
Installation (for Linux)
python3 -m venv langextract_env source langextract_env/bin/activate pip3 install langextract
On-device models don't require an API key. For developers using local LLMs, LangExtract offers built-in support for Ollama. So first I run
ollama serve
Activation. On my computer I go to
kompas/langextract/langextract_env/bin
and I run:
source activate python3
AI Tools
https://insight7.io/5-best-ai-tools-for-qualitative-research-in-2025/
https://huggingface.co/tasks/zero-shot-classification
https://intelgic.com/text-processing-ai
Julia
Look at:
- ActiveInference.jl
- https://examples.rxinfer.com/