Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/simonw/llm-claude-3
LLM plugin for interacting with the Claude 3 family of models
https://github.com/simonw/llm-claude-3
Last synced: 5 days ago
JSON representation
LLM plugin for interacting with the Claude 3 family of models
- Host: GitHub
- URL: https://github.com/simonw/llm-claude-3
- Owner: simonw
- License: apache-2.0
- Created: 2024-03-04T15:22:22.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-12-17T20:09:57.000Z (about 2 months ago)
- Last Synced: 2025-01-25T16:01:51.616Z (12 days ago)
- Language: Python
- Homepage:
- Size: 37.1 KB
- Stars: 285
- Watchers: 3
- Forks: 29
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- jimsghstars - simonw/llm-claude-3 - LLM plugin for interacting with the Claude 3 family of models (Python)
- awesome_ai_agents - Llm-Claude-3 - LLM plugin for interacting with the Claude 3 family of models (Building / LLM Models)
README
# llm-claude-3
[](https://pypi.org/project/llm-claude-3/)
[](https://github.com/simonw/llm-claude-3/releases)
[](https://github.com/simonw/llm-claude-3/actions/workflows/test.yml)
[](https://github.com/simonw/llm-claude-3/blob/main/LICENSE)
LLM access to Claude 3 by Anthropic
## Installation
Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
```bash
llm install llm-claude-3
```
## Usage
First, set [an API key](https://console.anthropic.com/settings/keys) for Claude 3:
```bash
llm keys set claude
# Paste key here
```
You can also set the key in the environment variable `ANTHROPIC_API_KEY`
Run `llm models` to list the models, and `llm models --options` to include a list of their options.
Run prompts like this:
```bash
llm -m claude-3.5-sonnet 'Fun facts about pelicans'
llm -m claude-3.5-haiku 'Fun facts about armadillos'
llm -m claude-3-opus 'Fun facts about squirrels'
```
Images are supported too:
```bash
llm -m claude-3.5-sonnet 'describe this image' -a https://static.simonwillison.net/static/2024/pelicans.jpg
llm -m claude-3-haiku 'extract text' -a page.png
```
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-claude-3
python3 -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
llm install -e '.[test]'
```
To run the tests:
```bash
pytest
```
This project uses [pytest-recording](https://github.com/kiwicom/pytest-recording) to record Anthropic API responses for the tests.
If you add a new test that calls the API you can capture the API response like this:
```bash
PYTEST_ANTHROPIC_API_KEY="$(llm keys get claude)" pytest --record-mode once
```
You will need to have stored a valid Anthropic API key using this command first:
```bash
llm keys set claude
# Paste key here
```