Releases: kardolus/chatgpt-cli
ChatGPT CLI v1.0.5
ChatGPT CLI v1.0.5 Release Notes
Summary
We're excited to introduce ChatGPT CLI v1.0.5. This update focuses on providing more flexibility in choosing a model by introducing a new feature - the --list-models
flag.
What's New
- Model Listing (
--list-models
flag): With the addition of the new--list-models
flag, you can now easily get a list of all available models. This is a significant step towards providing a more flexible and user-friendly interface.
Improvements
- Codebase: This version includes various codebase improvements to enhance the stability and reliability of the CLI client.
- Documentation: We've updated the README and inline documentation to include details about the new
--list-models
flag.
Bug Fixes
- We've addressed various minor bugs and issues reported by users in this release.
How to Update
Using Homebrew (macOS)
brew upgrade chatgpt-cli
Direct Download
For a quick and easy installation without compiling, you can directly download the pre-built binary for your operating system and architecture.
ChatGPT CLI v1.0.4
We are excited to announce the release of ChatGPT CLI v1.0.4! This release brings a new feature to enhance the user experience with the GPT model.
New Features
- Interactive Mode: With this release, we've introduced the Interactive Mode, allowing for a more conversational experience with the GPT model. Users can now interact in real-time with the model and obtain responses more intuitively. To enter Interactive Mode, use the
-i
or--interactive
flag:
chatgpt --interactive
In Interactive Mode, simply type your queries and the program will print the responses as you go along. To exit Interactive Mode, type 'exit'.
Improvements
- Updated README to include instructions for the new Interactive Mode and how to exit it.
- Minor bug fixes and stability improvements.
How to Upgrade
To upgrade your current installation to v1.0.4, follow the installation instructions in the README for your respective operating system and architecture.
As always, if you encounter any issues or have suggestions for improvements, please submit an issue on GitHub. We appreciate your feedback and contributions to help make this project better!
ChatGPT CLI v1.0.3
New Features
- Custom chat models: In this release, we've added the ability to use custom chat models by specifying the model name with the
-m
or--model
flag. This allows users to leverage specific chat models when interacting with ChatGPT. Note that this feature only supports chat models, not completion models.
Improvements
- Updated README: The README file has been updated to include the new custom model flag feature, providing a clear explanation of how to use it in your queries.
Bug Fixes
- No major bug fixes in this release.
We hope that you find these updates helpful, and we encourage you to provide feedback and report any issues you encounter. Your contributions help make this project better for everyone.
Version Command Enhancement: ChatGPT CLI v1.0.2
ChatGPT CLI v1.0.2 Release Notes
Added
- New
--version
flag added to the CLI tool. This flag displays the version information, including the Git version and commit hash. This enhancement makes it easy to identify the current version of the ChatGPT CLI tool you are using.
Release v1.0.1 - Context Pipe Feature
We're excited to announce the release of ChatGPT CLI v1.0.1! This update introduces a powerful new feature to provide custom context to the ChatGPT API through piping. This allows users to enhance their interactions with the ChatGPT model by supplying additional information from external sources.
Changelog
Added
- Context Pipe Feature: You can now pipe custom context from a local file or other sources into the ChatGPT CLI. This enables the ChatGPT model to reference the provided context during the conversation. To use this feature, simply pipe the content into the CLI command, like this:
cat /path/to/context-file.txt | ./bin/chatgpt "your question"
.
Updated
- README and help messages have been updated to reflect the new context pipe feature and its usage.
- Minor changes to the method signatures and internal implementations to support the new feature.
Thank you for using the ChatGPT CLI, and we hope you enjoy the new context pipe feature in v1.0.1! Your feedback is invaluable in helping us improve and provide even better features in the future.
v1.0.0 - Release Notes
Features:
- Interactive streaming mode for real-time interaction with the GPT-3.5 Turbo model.
- Query mode for single input-output interactions with the GPT-3.5 Turbo model.
- Sliding window history management: Automatically trims conversation history while maintaining context to stay within token limits, enabling seamless and efficient conversations with the GPT model across CLI calls.
- Viper integration for robust configuration management.
- CLI history management: Automatically saves and loads conversation history for a more coherent user experience across sessions.
- Unit and integration tests to ensure the stability and reliability of the codebase.
Improvements:
- Refined error handling for better user experience and easier debugging.
- Code refactoring for better readability and maintainability.
Fixes:
- Fixed issues with token counting and history truncation to comply with token limits.
- Resolved bugs in file management and JSON parsing.
This release marks the first stable version of the ChatGPT CLI, providing a powerful and user-friendly interface for interacting with OpenAI's GPT-3.5 Turbo model. Users can now easily switch between interactive streaming mode and query mode, while enjoying seamless and efficient conversations with the GPT model, thanks to the sliding window history management feature. With robust configuration management through Viper integration and a well-tested codebase, the ChatGPT CLI is now ready for use in various applications.
Version 0.3.0: ChatGPT-CLI History Management
🎉 New Features
- History Management: We have introduced a new set of features to handle message history for the ChatGPT-CLI. This enhancement allows users to keep track of their conversations with the ChatGPT model, enabling a more seamless user experience.
🚀 Improvements
-
FileIO: A new FileIO module has been added to support the Read, Write, and Delete operations for the history file. The module ensures efficient handling of history data, making it easier to manage and maintain conversation history.
-
Unit and Integration Tests: Comprehensive unit and integration tests have been added to ensure the reliability and stability of the new history features. These tests cover the FileIO operations and the overall functionality of the history management system.
-
Updated README: The README has been updated with instructions on how to run the newly added tests, providing clearer guidance for contributors and users.
📚 Documentation
- The documentation has been updated to include information about the new history management features, FileIO operations, and testing procedures. This will help users and contributors to better understand the changes and how to use the new functionality.
Thank you for your continued support! We hope you enjoy the new history management features in ChatGPT-CLI. As always, please let us know if you have any feedback, issues, or suggestions. Happy chatting!
Release v0.2.0 - Streaming Support and Viper Integration
Release v0.2.0 - Streaming Support and Viper Integration
We are excited to announce the release of version v0.2.0 of the ChatGPT CLI! This release adds support for streaming and integrates the Viper configuration library to provide a better command-line experience.
New Features
- Streaming Support: The new release allows you to use the ChatGPT CLI in streaming mode, enabling real-time interaction with the GPT model. Use the default streaming mode for a more interactive experience or switch to query mode with the
-q
flag. - Viper Integration: We have replaced the previous configuration handling with Viper, a popular Go configuration library. Viper enables easier management of environment variables and command-line flags, providing a more robust and user-friendly experience.
How to Use
To use the new release, follow these steps:
- Download the latest binary for your platform from the releases page.
- Ensure the
OPENAI_API_KEY
environment variable is set with your API key. - Run the binary with your desired input:
- For streaming mode (default):
./chatgpt "your input here"
- For query mode:
./chatgpt -q "your input here"
- For streaming mode (default):
Changelog
- Added streaming support for real-time interaction with the GPT model.
- Integrated Viper for better configuration handling.
- Updated the command-line interface to support the
-q
flag for query mode.
Upgrading
To upgrade to this release, download the latest binary for your platform from the releases page and replace your existing binary.