Skip to main content

LLM plugin for iaedu.pt API — no adapter required

Project description

llm-iaedu

Plugin for LLM that enables using the iaedu.pt API as a model — no adapter, no Docker.

Quick Start

Linux / macOS

# Install
pip install llm-iaedu

# Configure credentials (Endpoint, API Key, Channel ID)
llm-iaedu configure

# Ask anything
llm -m iaedu "What is the capital of Portugal?"

Ubuntu / Debian (PEP 668)

Ubuntu 23.04+ blocks system-wide pip install. Use one of:

Option 1: pipx (if you already pipx install llm):

pipx inject llm llm-iaedu

# Configure credentials (works after pipx inject, no extra install):
llm iaedu-configure
# OR from the git repo:
make configure
# OR manually:
mkdir -p ~/.config/iaedu
cat > ~/.config/iaedu/env << EOF
IAEDU_ENDPOINT=https://api.iaedu.pt/agent-chat/api/v1/agent/YOUR-AGENT-ID/stream
IAEDU_CHANNEL_ID=your-channel-id
IAEDU_API_KEY=your-api-key
EOF

llm -m iaedu "What is the capital of Portugal?"

Option 2: Virtual environment:

python3 -m venv venv
source venv/bin/activate
pip install llm-iaedu
llm-iaedu configure
llm -m iaedu "What is the capital of Portugal?"

Option 3: From git clone:

git clone https://github.com/rodolfomatos/llm-iaedu.git
cd llm-iaedu
make ubuntu-setup   # shows instructions
make configure      # interactive credential setup
make check          # verify everything works

Setup

Quick (interactive)

# From git clone (has Makefile):
make configure

# From pip install (no repo):
llm-iaedu configure

Paste the three values from iaedu.pt (Endpoint URL, API Key, Channel ID) when prompted. The script creates ~/.config/iaedu/env with everything needed — works from any directory.

Manual

Create ~/.config/iaedu/env:

IAEDU_ENDPOINT=https://api.iaedu.pt/agent-chat/api/v1/agent/your-agent-id/stream
IAEDU_CHANNEL_ID=your-channel-id
IAEDU_API_KEY=your-api-key

Or place a .env in any project directory for local config.

Config Precedence

  1. Current shell (export IAEDU_*)
  2. ./.env (local)
  3. ~/.config/iaedu/env (global)
  4. ~/.iaedu.env (legacy)

Usage

# One-off
llm -m iaedu "What is the capital of Portugal?"

# Default model (just skip -m)
llm models default iaedu
llm "What is the capital of Portugal?"

# Interactive chat
llm chat -m iaedu

# Pipe input
cat file.txt | llm -m iaedu

Development

git clone https://github.com/rodolfomatos/llm-iaedu.git
cd llm-iaedu

# Standard
make setup
# ... or Ubuntu/Debian:
make ubuntu-setup
# ... or pipx:
make pipx-setup

make configure
make check

How it works

The plugin calls the iaedu.pt API directly — no adapter server required. It loads config from environment variables or .env files, sends prompts as multipart form data, and streams token responses.

Requirements

  • Python 3.8+
  • llm CLI
  • iaedu.pt account with API key, channel ID, and agent ID

Project

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_iaedu-0.4.tar.gz (5.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_iaedu-0.4-py3-none-any.whl (6.0 kB view details)

Uploaded Python 3

File details

Details for the file llm_iaedu-0.4.tar.gz.

File metadata

  • Download URL: llm_iaedu-0.4.tar.gz
  • Upload date:
  • Size: 5.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for llm_iaedu-0.4.tar.gz
Algorithm Hash digest
SHA256 81e005661642a6e80c9bb23163c6fa0ba2ebe9bc4577f40cdf7a4ed0569c5d39
MD5 b4a8d0a9103f12481277cb92a7110245
BLAKE2b-256 fe998f89929c5ef5146c870da058b37eb838f2eea27992deae242db18ca9bb04

See more details on using hashes here.

File details

Details for the file llm_iaedu-0.4-py3-none-any.whl.

File metadata

  • Download URL: llm_iaedu-0.4-py3-none-any.whl
  • Upload date:
  • Size: 6.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for llm_iaedu-0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 ef4b2e697c2c11ea376364986bf93699ee656d94ac98b31276bf17e6952cced5
MD5 75ea243f2fb76fe86d85c6566cd0fd2f
BLAKE2b-256 17a7c09c0cb3661751069179069de6532b10a72a658e7b234a855d6f8dbc0934

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page