A Node.js CLI that uses Ollama and LM Studio models (Llava, Gemma, Llama etc.) to intelligently rename files by their contents
Rename videos
ai-renamer-videos-1080p.mp4
Rename images
ai-renamer-images-1080p.mp4
Rename files
ai-renamer-files-1080p.mp4
You need to have Ollama or LM Studio and at least one LLM (Llava, Gemma, Llama etc.) installed on your system. You need to have ffmpeg to rename videos.
Run with NPX
npx ai-renamer /pathRun with NPM
# Install it globally
npm install -g ai-renamer
# Run it
ai-renamer /pathOllama is the default provider so you don't have to do anything. You can just run npx ai-renamer /images. At the first launch it will try to auto-select the Llava model but if it couldn't do that you can specify the model.
npx ai-renamer /path --provider=ollama --model=llava:13bYou need to set the provider as lm-studio and it will auto-select the loaded model in LM Studio.
npx ai-renamer /path --provider=lm-studioYou need to set the provider as openai and the api-key with your API key and it will auto-select the gpt-4o model. But you can assign any model with --model flag.
npx ai-renamer /path --provider=openai --api-key=OPENAI_API_KEYIf you're using a different port in Ollama or LM Studio you could simply specify the base URLs.
npx ai-renamer /path --provider=ollama --base-url=http:https://127.0.0.1:11434
npx ai-renamer /path --provider=lm-studio --base-url=http:https://127.0.0.1:1234The values of the flags will be saved to your disk when you use them. You can find the config file at ~/ai-renamer.json. If you're using a Mac it's /Users/your-user-name/ai-renamer.json. Also when you set a flag you don't have to use them again. The script gets the values from this config file.
npx ai-renamer --help
Options:
-h, --help Show help [boolean]
--version Show version number [boolean]
-p, --provider Set the provider (e.g. ollama, openai,
lm-studio) [string]
-a, --api-key Set the API key if you're using openai as
provider [string]
-u, --base-url Set the API base URL (e.g.
http:https://127.0.0.1:11434 for ollama) [string]
-m, --model Set the model to use (e.g. gemma2, llama3,
gpt-4o) [string]
-f, --frames Set the maximum number of frames to extract from
videos (e.g. 3, 5, 10) [number]
-c, --case Set the case style (e.g. camelCase, pascalCase,
snakeCase, kebabCase) [string]
-x, --chars Set the maximum number of characters in the new
filename (e.g. 25) [number]
-l, --language Set the output language (e.g. English, Turkish)
[string]
-s, --include-subdirectories Include files in subdirectories when processing
(e.g: true, false) [string]
-r, --custom-prompt Add a custom prompt to the LLM (e.g. "Only
describe the background") [string]ai-renamer uses change-case library for case styling
# value: result
camelCase: twoWords
capitalCase: Two Words
constantCase: TWO_WORDS
dotCase: two.words
kebabCase: two-words
noCase: two words
pascalCase: TwoWords
pascalSnakeCase: Two_Words
pathCase: two/words
sentenceCase: Two words
snakeCase: two_words
trainCase: Two-WordsFeel free to contribute. Open a new issue, or make a pull request.