base on A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting. # code2prompt [](https://crates.io/crates/code2prompt) [](https://github.com/mufeedvh/code2prompt/blob/master/LICENSE) <h1 align="center"> <a href="https://github.com/mufeedvh/code2prompt"><img src=".assets/code2prompt-screenshot.png" alt="code2prompt"></a> </h1> `code2prompt` is a command-line tool (CLI) that converts your codebase into a single LLM prompt with a source tree, prompt templating, and token counting. ## Table of Contents - [Features](#features) - [Installation](#installation) - [Usage](#usage) - [Templates](#templates) - [User Defined Variables](#user-defined-variables) - [Tokenizers](#tokenizers) - [Contribution](#contribution) - [License](#license) - [Support The Author](#support-the-author) ## Features You can run this tool on the entire directory and it would generate a well-formatted Markdown prompt detailing the source tree structure, and all the code. You can then upload this document to either GPT or Claude models with higher context windows and ask it to: - Quickly generate LLM prompts from codebases of any size. - Customize prompt generation with Handlebars templates. (See the [default template](src/default_template.hbs)) - Respects `.gitignore`. - Filter and exclude files using glob patterns. - Display the token count of the generated prompt. (See [Tokenizers](#tokenizers) for more details) - Optionally include Git diff output (staged files) in the generated prompt. - Automatically copy the generated prompt to the clipboard. - Save the generated prompt to an output file. - Exclude files and folders by name or path. - Add line numbers to source code blocks. You can customize the prompt template to achieve any of the desired use cases. It essentially traverses a codebase and creates a prompt with all source files combined. In short, it automates copy-pasting multiple source files into your prompt and formatting them along with letting you know how many tokens your code consumes. ## Installation ### Binary releases Download the latest binary for your OS from [Releases](https://github.com/mufeedvh/code2prompt/releases). ### Source build Requires: - [Git](https://git-scm.org/downloads), [Rust](https://rust-lang.org/tools/install) and Cargo. ```sh git clone https://github.com/mufeedvh/code2prompt.git cd code2prompt/ cargo build --release ``` ## cargo installs from the [`crates.io`](https://crates.io) registry. ```sh cargo install code2prompt ``` For unpublished builds: ```sh cargo install --git https://github.com/mufeedvh/code2prompt ``` ### AUR `code2prompt` is available in the [`AUR`](https://aur.archlinux.org/packages?O=0&K=code2prompt). Install it via any AUR helpers. ```sh paru/yay -S code2prompt ``` ### Nix If you are on nix, You can use `nix-env` or `profile` to install. ```sh # without flakes: nix-env -iA nixpkgs.code2prompt # with flakes: nix profile install nixpkgs#code2prompt ``` ## Usage Generate a prompt from a codebase directory: ```sh code2prompt path/to/codebase ``` Use a custom Handlebars template file: ```sh code2prompt path/to/codebase -t path/to/template.hbs ``` Filter files using glob patterns: ```sh code2prompt path/to/codebase --include="*.rs,*.toml" ``` Exclude files using glob patterns: ```sh code2prompt path/to/codebase --exclude="*.txt,*.md" ``` Exclude files/folders from the source tree based on exclude patterns: ```sh code2prompt path/to/codebase --exclude="*.npy,*.wav" --exclude-from-tree ``` Display the token count of the generated prompt: ```sh code2prompt path/to/codebase --tokens ``` Specify a tokenizer for token count: ```sh code2prompt path/to/codebase --tokens --encoding=p50k ``` Supported tokenizers: `cl100k`, `p50k`, `p50k_edit`, `r50k_bas`. > [!NOTE] > See [Tokenizers](#tokenizers) for more details. Save the generated prompt to an output file: ```sh code2prompt path/to/codebase --output=output.txt ``` Print output as JSON: ```sh code2prompt path/to/codebase --json ``` The JSON output will have the following structure: ```json { "prompt": "<Generated Prompt>", "directory_name": "codebase", "token_count": 1234, "model_info": "ChatGPT models, text-embedding-ada-002", "files": [] } ``` Generate a Git commit message (for staged files): ```sh code2prompt path/to/codebase --diff -t templates/write-git-commit.hbs ``` Generate a Pull Request with branch comparing (for staged files): ```sh code2prompt path/to/codebase --git-diff-branch 'main, development' --git-log-branch 'main, development' -t templates/write-github-pull-request.hbs ``` Add line numbers to source code blocks: ```sh code2prompt path/to/codebase --line-number ``` Disable wrapping code inside markdown code blocks: ```sh code2prompt path/to/codebase --no-codeblock ``` - Rewrite the code to another language. - Find bugs/security vulnerabilities. - Document the code. - Implement new features. > I initially wrote this for personal use to utilize Claude 3.0's 200K context window and it has proven to be pretty useful so I decided to open-source it! ## Templates `code2prompt` comes with a set of built-in templates for common use cases. You can find them in the [`templates`](templates) directory. ### [`document-the-code.hbs`](templates/document-the-code.hbs) Use this template to generate prompts for documenting the code. It will add documentation comments to all public functions, methods, classes and modules in the codebase. ### [`find-security-vulnerabilities.hbs`](templates/find-security-vulnerabilities.hbs) Use this template to generate prompts for finding potential security vulnerabilities in the codebase. It will look for common security issues and provide recommendations on how to fix or mitigate them. ### [`clean-up-code.hbs`](templates/clean-up-code.hbs) Use this template to generate prompts for cleaning up and improving the code quality. It will look for opportunities to improve readability, adherence to best practices, efficiency, error handling, and more. ### [`fix-bugs.hbs`](templates/fix-bugs.hbs) Use this template to generate prompts for fixing bugs in the codebase. It will help diagnose issues, provide fix suggestions, and update the code with proposed fixes. ### [`write-github-pull-request.hbs`](templates/write-github-pull-request.hbs) Use this template to create GitHub pull request description in markdown by comparing the git diff and git log of two branches. ### [`write-github-readme.hbs`](templates/write-github-readme.hbs) Use this template to generate a high-quality README file for the project, suitable for hosting on GitHub. It will analyze the codebase to understand its purpose and functionality, and generate the README content in Markdown format. ### [`write-git-commit.hbs`](templates/write-git-commit.hbs) Use this template to generate git commits from the staged files in your git directory. It will analyze the codebase to understand its purpose and functionality, and generate the git commit message content in Markdown format. ### [`improve-performance.hbs`](templates/improve-performance.hbs) Use this template to generate prompts for improving the performance of the codebase. It will look for optimization opportunities, provide specific suggestions, and update the code with the changes. You can use these templates by passing the `-t` flag followed by the path to the template file. For example: ```sh code2prompt path/to/codebase -t templates/document-the-code.hbs ``` ## User Defined Variables `code2prompt` supports the use of user defined variables in the Handlebars templates. Any variables in the template that are not part of the default context (`absolute_code_path`, `source_tree`, `files`) will be treated as user defined variables. During prompt generation, `code2prompt` will prompt the user to enter values for these user defined variables. This allows for further customization of the generated prompts based on user input. For example, if your template includes `{{challenge_name}}` and `{{challenge_description}}`, you will be prompted to enter values for these variables when running `code2prompt`. This feature enables creating reusable templates that can be adapted to different scenarios based on user provided information. ## Tokenizers Tokenization is implemented using [`tiktoken-rs`](https://github.com/zurawiki/tiktoken-rs). `tiktoken` supports these encodings used by OpenAI models: | Encoding name | OpenAI models | | ----------------------- | ------------------------------------------------------------------------- | | `cl100k_base` | ChatGPT models, `text-embedding-ada-002` | | `p50k_base` | Code models, `text-davinci-002`, `text-davinci-003` | | `p50k_edit` | Use for edit models like `text-davinci-edit-001`, `code-davinci-edit-001` | | `r50k_base` (or `gpt2`) | GPT-3 models like `davinci` | | `o200k_base` | GPT-4o models | For more context on the different tokenizers, see the [OpenAI Cookbook](https://github.com/openai/openai-cookbook/blob/66b988407d8d13cad5060a881dc8c892141f2d5c/examples/How_to_count_tokens_with_tiktoken.ipynb) ## How is it useful? `code2prompt` makes it easy to generate prompts for LLMs from your codebase. It traverses the directory, builds a tree structure, and collects information about each file. You can customize the prompt generation using Handlebars templates. The generated prompt is automatically copied to your clipboard and can also be saved to an output file. `code2prompt` helps streamline the process of creating LLM prompts for code analysis, generation, and other tasks. ## Contribution Ways to contribute: - Suggest a feature - Report a bug - Fix something and open a pull request - Help me document the code - Spread the word ## License Licensed under the MIT License, see <a href="https://github.com/mufeedvh/code2prompt/blob/master/LICENSE">LICENSE</a> for more information. ## Liked the project? If you liked the project and found it useful, please give it a :star: and consider supporting the authors! ", Assign "at most 3 tags" to the expected json: {"id":"11139","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"