Requirements
- Java 17 or later — required to run the application.
Download from Adoptium or use your system package manager.
- An API key — PromptFx works with OpenAI (recommended) or
Google Gemini.
Step-by-step Setup
-
Download the latest release
Go to the
Releases page
and download the
promptfx-*-jar-with-dependencies.jar file.
-
Place your API key
Create a plain text file named apikey.txt in the same folder as the JAR,
and paste your OpenAI API key into it. Alternatively, set the
OPENAI_API_KEY environment variable.
For Gemini, create apikey-gemini.txt with your Gemini key.
-
Run the application
Open a terminal in the folder containing the JAR and run:
java -jar promptfx-0.1.0-SNAPSHOT-jar-with-dependencies.jar
On Windows you can also double-click the JAR if your Java installation is associated with
.jar files.
-
(Optional) Set the API key from within the app
Click the key 🔑 button in the top toolbar to enter or update your OpenAI API key interactively.
Tip: PromptFx opens to the Document Q&A view by default.
Click Open Folder to select a folder of documents (.pdf, .docx, .txt) and start asking questions immediately.
Document Q&A Quick Start
The Document Q&A view lets you ask natural-language questions about a folder of local documents
using retrieval-augmented generation (RAG).
Click Open Folder and navigate to a folder containing PDF, DOCX, or TXT files.
Type your question in the input box and press Enter (or click Ask).
PromptFx automatically extracts text, computes embeddings, retrieves relevant snippets, and generates an answer with source citations.
Click any snippet in the results to open the source document and jump to the exact page.
Document Q&A – full-screen mode
Other Built-in Views
- API tab — Test completions, chat, images, embeddings, and audio APIs directly.
- Tools tab — Browse the prompt library, run prompt templates, and execute batch scripts.
- Text tab — Translation, summarization, sentiment analysis, entity extraction, and more.
- Fun tab — Experimental: emoji conversion, AI-to-AI chat, and other demos.
- Audio tab — Speech-to-text (Whisper) and text-to-speech.
- Vision tab — Image generation (DALL-E, Gemini Imagen) and image description.
Troubleshooting
- If the app doesn't start, check that Java 17+ is installed:
java -version
- If you see authentication errors, verify your API key is correct and placed in the right file.
- For further help, see the Wiki or
open an issue.