This commit implements a clean architecture where environment variables
are only read, never set, ensuring compatibility with other ComfyUI
packages.
The changes: - Remove all code that sets global environment variables -
Clean up config.yaml to remove API key placeholders - Add documentation
for safe environment handling - Add comprehensive tests to verify
non-polluting behavior - Ensure backward compatibility for other
packages
The commit includes detailed docs explaining the clean architecture and
safety guarantees for package compatibility.
- Add detailed docstrings to AgentNode, BasicRecursionFilterNode, and
DocumentChunkRecursionFilterNode for clarity and documentation. -
Improve input validation and error handling in agent nodes. - Update
.gitignore to cover more environment, config, and IDE files. - Refactor
LiteLLMCustomEndpointProvider for custom API endpoints. - Add
conditional imports and dummy functions for LightRAG when unavailable. -
Update config.yaml to use environment variables for API keys and clarify
usage. - Refine requirements.txt to avoid heavy LightRAG dependencies. -
Add tests/__init__.py with test suite metadata; remove redundant test
files. - Fix CustomDict import and model config handling in
litellmnodes.py. - Improve chunk processing and recursion filter logic
in agent nodes. - Update utils/__init__.py to include env_config.
- Add new Agent system with base node infrastructure and recursion filtering
- Implement LightRAG integration with document processing and query capabilities
- Add memory management system with Linux memory directory support
- Update node mappings to include new Agent and LightRAG components
- Fix model response format handling in LiteLLM nodes
- Add new dependencies for embedding and vector storage support
- Remove author attribution from init file
- Add new classes for advanced LLM interactions (HTMLRenderer, AddDataModelToLLLm, ModifyModelKwargs, LitellmCompletionV2)
- Implement PDF processing with PDFToImageNode for image extraction
- Enhance error handling and caching in LiteLLMCompletion for improved performance
- Update model options and add support for custom data models and kwargs modifications
- Refactor initialization process and simplify JavaScript components
- Improve multi-modal processing with better image handling in LLM completions
- Update project metadata to reflect evolving focus and capabilities
This commit significantly expands the system's ability to handle complex AI tasks,
including HTML rendering, PDF processing, and more flexible LLM interactions.
It represents a major step towards a more comprehensive, multi-modal AI toolkit
Add litellmnodes.py with various nodes for interacting with LiteLLM models, including:
LiteLLMModelProvider for providing LiteLLM models
LiteLLMCompletion for generating completions using LiteLLM
LiteLLMCompletionListOfPrompts for generating completions for a list of prompts
CreateReflectionFilter and FirstCodeBlockReflectionFilter for creating reflection filters
LiteLLMCompletionWithReflectionFilter for generating completions with a reflection filter
LiteLLMCompletionProvider for providing a completion function
LiteLLMMessage for creating LiteLLM messages
ListToMessages for converting a list to LiteLLM messages
Add .gitignore to ignore config.yaml
Add requirements.txt with required dependencies
Add install.py script for installing the addon via ComfyUI-Manager
Add litellm_uuid.txt to store the addon's UUID
Add init.py to initialize the addon and update node mappings
Add tests/test_litellmnodes.py with unit tests for LiteLLMCompletion
Add config.py for reading configuration settings from config.yaml
Add tests/init.py for tests package
This commit integrates LiteLLM nodes into ComfyUI, allowing users to interact with LiteLLM models directly within the ComfyUI interface. The nodes provide functionality for generating completions, creating reflection filters, handling messages, and more. Configuration settings are read from config.yaml, and the addon can be installed using the provided install.py script when using ComfyUI-Manager.
TashaSkyUp