Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/simonw/files-to-prompt
Concatenate a directory full of files into a single prompt for use with LLMs
https://github.com/simonw/files-to-prompt
Last synced: about 9 hours ago
JSON representation
Concatenate a directory full of files into a single prompt for use with LLMs
- Host: GitHub
- URL: https://github.com/simonw/files-to-prompt
- Owner: simonw
- License: apache-2.0
- Created: 2024-03-22T15:42:41.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-10-16T23:25:24.000Z (about 2 months ago)
- Last Synced: 2024-10-29T15:48:30.593Z (about 1 month ago)
- Language: Python
- Size: 27.3 KB
- Stars: 550
- Watchers: 11
- Forks: 47
- Open Issues: 16
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome - simonw/files-to-prompt - Concatenate a directory full of files into a single prompt for use with LLMs (Python)
- jimsghstars - simonw/files-to-prompt - Concatenate a directory full of files into a single prompt for use with LLMs (Python)
README
# files-to-prompt
[![PyPI](https://img.shields.io/pypi/v/files-to-prompt.svg)](https://pypi.org/project/files-to-prompt/)
[![Changelog](https://img.shields.io/github/v/release/simonw/files-to-prompt?include_prereleases&label=changelog)](https://github.com/simonw/files-to-prompt/releases)
[![Tests](https://github.com/simonw/files-to-prompt/actions/workflows/test.yml/badge.svg)](https://github.com/simonw/files-to-prompt/actions/workflows/test.yml)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/simonw/files-to-prompt/blob/master/LICENSE)Concatenate a directory full of files into a single prompt for use with LLMs
For background on this project see [Building files-to-prompt entirely using Claude 3 Opus](https://simonwillison.net/2024/Apr/8/files-to-prompt/).
## Installation
Install this tool using `pip`:
```bash
pip install files-to-prompt
```## Usage
To use `files-to-prompt`, provide the path to one or more files or directories you want to process:
```bash
files-to-prompt path/to/file_or_directory [path/to/another/file_or_directory ...]
```This will output the contents of every file, with each file preceded by its relative path and separated by `---`.
### Options
- `-e/--extension `: Only include files with the specified extension. Can be used multiple times.
```bash
files-to-prompt path/to/directory -e txt -e md
```- `--include-hidden`: Include files and folders starting with `.` (hidden files and directories).
```bash
files-to-prompt path/to/directory --include-hidden
```- `--ignore-gitignore`: Ignore `.gitignore` files and include all files.
```bash
files-to-prompt path/to/directory --ignore-gitignore
```- `--ignore `: Specify one or more patterns to ignore. Can be used multiple times.
```bash
files-to-prompt path/to/directory --ignore "*.log" --ignore "temp*"
```- `c/--cxml`: Output in Claude XML format.
```bash
files-to-prompt path/to/directory --cxml
```- `-o/--output `: Write the output to a file instead of printing it to the console.
```bash
files-to-prompt path/to/directory -o output.txt
```### Example
Suppose you have a directory structure like this:
```
my_directory/
├── file1.txt
├── file2.txt
├── .hidden_file.txt
├── temp.log
└── subdirectory/
└── file3.txt
```Running `files-to-prompt my_directory` will output:
```
my_directory/file1.txt
---
Contents of file1.txt
---
my_directory/file2.txt
---
Contents of file2.txt
---
my_directory/subdirectory/file3.txt
---
Contents of file3.txt
---
```If you run `files-to-prompt my_directory --include-hidden`, the output will also include `.hidden_file.txt`:
```
my_directory/.hidden_file.txt
---
Contents of .hidden_file.txt
---
...
```If you run `files-to-prompt my_directory --ignore "*.log"`, the output will exclude `temp.log`:
```
my_directory/file1.txt
---
Contents of file1.txt
---
my_directory/file2.txt
---
Contents of file2.txt
---
my_directory/subdirectory/file3.txt
---
Contents of file3.txt
---
```### Claude XML Output
Anthropic has provided [specific guidelines](https://docs.anthropic.com/claude/docs/long-context-window-tips) for optimally structuring prompts to take advantage of Claude's extended context window.
To structure the output in this way, use the optional `--cxml` flag, which will produce output like this:
```xml
my_directory/file1.txt
Contents of file1.txt
my_directory/file2.txt
Contents of file2.txt
```
## Development
To contribute to this tool, first checkout the code. Then create a new virtual environment:
```bash
cd files-to-prompt
python -m venv venv
source venv/bin/activate
```Now install the dependencies and test dependencies:
```bash
pip install -e '.[test]'
```To run the tests:
```bash
pytest
```