Giving language models context of your codebase
Project description
code-payload
Condense and summarize a codebase for passing to an LLM as context.
Features
- Token-based Summarization: Summarizes content based on token counts, making it suitable for language models.
- Flexible Configuration: Supports configuration through YAML files, environment variables, and CLI arguments.
- Rich CLI Interface: Use the CLI to interact with your projects, including rendering Jinja2 templates.
- Customizable Templates: Generate custom summaries or reports using Jinja2 templates.
Installation
We recommend using pipx
to make this globally available. Alternatively you can use pip
.
pipx install code-payload
Usage
code-payload --help
Example Usage
To process a project directory and output a JSON summary:
code-payload /path/to/your/project
To override the file extensions to include:
code-payload /path/to/your/project --include-extensions .py,.js,.md
To use a custom template:
code-payload /path/to/your/project --render-args template_input=readme_summary.j2
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
code_payload-0.1.7.dev0.tar.gz
(24.7 kB
view details)
Built Distribution
File details
Details for the file code_payload-0.1.7.dev0.tar.gz
.
File metadata
- Download URL: code_payload-0.1.7.dev0.tar.gz
- Upload date:
- Size: 24.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 758b1fe8730029eff6735251a6cd53a850fecac47d88632baa52ef95b98bd5fc |
|
MD5 | 860769789a1ff2137f497c45c54cdf18 |
|
BLAKE2b-256 | d77c0160e3d958dd45283ab99db4c06d7ca8b3c90b0725eff2d76f75dbbb7433 |
File details
Details for the file code_payload-0.1.7.dev0-py3-none-any.whl
.
File metadata
- Download URL: code_payload-0.1.7.dev0-py3-none-any.whl
- Upload date:
- Size: 24.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d5a2dba29dd191ba46bc43e760a18f2872461ae8a036fde9e8be68fb392e1b61 |
|
MD5 | ba5cd79829965e70220804f01149f1ef |
|
BLAKE2b-256 | 3f3a984b02dc040397ca624ab95575d2191b8c00444dff0d409192923bdc1ff9 |