llms-py 2.0.30__tar.gz → 2.0.32__tar.gz

{llms_py-2.0.30/llms_py.egg-info → llms_py-2.0.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llms-py
-Version: 2.0.30
+Version: 2.0.32
 Summary: A lightweight CLI tool and OpenAI-compatible server for querying multiple Large Language Model (LLM) providers
 Home-page: https://github.com/ServiceStack/llms
 Author: ServiceStack
@@ -54,6 +54,7 @@ Configure additional providers and models in [llms.json](llms/llms.json)
 - **Multi-Provider Support**: OpenRouter, Ollama, Anthropic, Google, OpenAI, Grok, Groq, Qwen, Z.ai, Mistral
 - **OpenAI-Compatible API**: Works with any client that supports OpenAI's chat completion API
 - **Built-in Analytics**: Built-in analytics UI to visualize costs, requests, and token usage
+- **GitHub OAuth**: Optionally Secure your web UI and restrict access to specified GitHub Users
 - **Configuration Management**: Easy provider enable/disable and configuration management
 - **CLI Interface**: Simple command-line interface for quick interactions
 - **Server Mode**: Run an OpenAI-compatible HTTP server at `http://localhost:{PORT}/v1/chat/completions`
@@ -108,6 +109,26 @@ As they're a good indicator for the reliability and speed you can expect from di
 test the response times for all configured providers and models, the results of which will be frequently published to
 [/checks/latest.txt](https://github.com/ServiceStack/llms/blob/main/docs/checks/latest.txt)
 
+## Change Log
+
+#### v2.0.30 (2025-11-01)
+- Improved Responsive Layout with collapsible Sidebar
+- Watching config files for changes and auto-reloading
+- Add cancel button to cancel pending request
+- Return focus to textarea after request completes
+- Clicking outside model or system prompt selector will collapse it
+- Clicking on selected item no longer deselects it
+- Support `VERBOSE=1` for enabling `--verbose` mode (useful in Docker)
+
+#### v2.0.28 (2025-10-31)
+- Dark Mode
+- Drag n' Drop files in Message prompt
+- Copy & Paste files in Message prompt
+- Support for GitHub OAuth and optional restrict access to specified Users
+- Support for Docker and Docker Compose
+
+[llms.py Releases](https://github.com/ServiceStack/llms/releases)
+
 ## Installation
 
 ### Using pip
@@ -255,7 +276,10 @@ See [GITHUB_OAUTH_SETUP.md](GITHUB_OAUTH_SETUP.md) for detailed setup instructio
 
 ## Configuration
 
-The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.json` and defines available providers, models, and default settings. Key sections:
+The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.json` and defines available providers, models, and default settings. If it doesn't exist, `llms.json` is auto created with the latest 
+configuration, so you can re-create it by deleting your local config (e.g. `rm -rf ~/.llms`). 
+
+Key sections:
 
 ### Defaults
 - `headers`: Common HTTP headers for all requests
@@ -268,7 +292,6 @@ The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.jso
 - `convert`: Max image size and length limits and auto conversion settings
 
 ### Providers
-
 Each provider configuration includes:
 - `enabled`: Whether the provider is active
 - `type`: Provider class (OpenAiProvider, GoogleProvider, etc.)

{llms_py-2.0.30 → llms_py-2.0.32}/README.md

@@ -14,6 +14,7 @@ Configure additional providers and models in [llms.json](llms/llms.json)
 - **Multi-Provider Support**: OpenRouter, Ollama, Anthropic, Google, OpenAI, Grok, Groq, Qwen, Z.ai, Mistral
 - **OpenAI-Compatible API**: Works with any client that supports OpenAI's chat completion API
 - **Built-in Analytics**: Built-in analytics UI to visualize costs, requests, and token usage
+- **GitHub OAuth**: Optionally Secure your web UI and restrict access to specified GitHub Users
 - **Configuration Management**: Easy provider enable/disable and configuration management
 - **CLI Interface**: Simple command-line interface for quick interactions
 - **Server Mode**: Run an OpenAI-compatible HTTP server at `http://localhost:{PORT}/v1/chat/completions`
@@ -68,6 +69,26 @@ As they're a good indicator for the reliability and speed you can expect from di
 test the response times for all configured providers and models, the results of which will be frequently published to
 [/checks/latest.txt](https://github.com/ServiceStack/llms/blob/main/docs/checks/latest.txt)
 
+## Change Log
+
+#### v2.0.30 (2025-11-01)
+- Improved Responsive Layout with collapsible Sidebar
+- Watching config files for changes and auto-reloading
+- Add cancel button to cancel pending request
+- Return focus to textarea after request completes
+- Clicking outside model or system prompt selector will collapse it
+- Clicking on selected item no longer deselects it
+- Support `VERBOSE=1` for enabling `--verbose` mode (useful in Docker)
+
+#### v2.0.28 (2025-10-31)
+- Dark Mode
+- Drag n' Drop files in Message prompt
+- Copy & Paste files in Message prompt
+- Support for GitHub OAuth and optional restrict access to specified Users
+- Support for Docker and Docker Compose
+
+[llms.py Releases](https://github.com/ServiceStack/llms/releases)
+
 ## Installation
 
 ### Using pip
@@ -215,7 +236,10 @@ See [GITHUB_OAUTH_SETUP.md](GITHUB_OAUTH_SETUP.md) for detailed setup instructio
 
 ## Configuration
 
-The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.json` and defines available providers, models, and default settings. Key sections:
+The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.json` and defines available providers, models, and default settings. If it doesn't exist, `llms.json` is auto created with the latest 
+configuration, so you can re-create it by deleting your local config (e.g. `rm -rf ~/.llms`). 
+
+Key sections:
 
 ### Defaults
 - `headers`: Common HTTP headers for all requests
@@ -228,7 +252,6 @@ The configuration file [llms.json](llms/llms.json) is saved to `~/.llms/llms.jso
 - `convert`: Max image size and length limits and auto conversion settings
 
 ### Providers
-
 Each provider configuration includes:
 - `enabled`: Whether the provider is active
 - `type`: Provider class (OpenAiProvider, GoogleProvider, etc.)