About
What is logseq-plugin-gpt3-openai?
Logseq-plugin-gpt3-openai is a powerful plugin designed to bring GPT-3 AI capabilities directly into the Logseq note-taking environment. It leverages OpenAI's ChatGPT API (gpt-3.5-turbo by default) to assist users with various tasks, from generating text and summaries to creating flashcards and outlines. The plugin supports custom prompt templates, allowing users to tailor AI responses to their specific needs. Beyond text generation, it also integrates Whisper for speech-to-text transcription and DALL-E for image generation, saving images directly to assets. Users can select multiple blocks for input, regenerate responses, and inject prefixes or tags for better organization. It requires an OpenAI API Key, which users need to obtain and configure in the plugin settings.
Best used for
Ideal for writers, students, and content creators who need to enhance their note-taking with AI-powered text generation, summarization, and transcription directly within Logseq. Especially valuable for quickly generating ideas, creating study materials, and converting audio notes to text without leaving their knowledge base.
Common actions
deepfakecollaborationlow-code/no-codeautomated workflowopen-sourceworkflowsgithub copilot"AI Agents"face swapping
Capabilities
Key features
- GPT-3 text generation
- Custom prompt templates
- Whisper speech-to-text
- DALL-E image generation
- Multi-block selection
- Inject prefix/tag
Target Audience
writerstudentcontent creatorblogger
Pricing & Plans
Open Source ยท Usage-based
FAQs
What OpenAI models does logseq-plugin-gpt3-openai support?
The plugin uses OpenAI's gpt-3.5-turbo model by default. Users can change this in the settings to text-davinci-003 for GPT-3 or gpt-4, provided they have access to these models through their OpenAI API key.
Do I need a paid OpenAI account to use this plugin?
You need an OpenAI API Key. While there might be a free welcome credit, continued usage typically requires providing a credit card to OpenAI, as the plugin incurs usage-based costs through the OpenAI API.
What audio formats are supported for Whisper transcription?
The Whisper feature supports m4a, mp3, mp4, mpeg, mpga, wav, and webm formats. Note that the Logseq mobile app's default .aac audio format is not directly supported, requiring conversion or a different recording app.