Add multi-LLM provider support (OpenAI, Anthropic, Google, Ollama)#22
Merged
advaitpatel merged 5 commits intomainfrom Feb 23, 2026
Merged
Add multi-LLM provider support (OpenAI, Anthropic, Google, Ollama)#22advaitpatel merged 5 commits intomainfrom
advaitpatel merged 5 commits intomainfrom
Conversation
added 5 commits
February 23, 2026 01:09
## Summary Add support for multiple LLM providers to DockSec, allowing users to choose between OpenAI, Anthropic Claude, Google Gemini, and Ollama (local models) for AI-powered security analysis. ## Changes ### Core Features - **Multi-provider architecture**: Support for 4 LLM providers (OpenAI, Anthropic, Google, Ollama) - **New CLI flags**: `--provider` and `--model` for runtime provider/model selection - **Enhanced configuration**: Environment variable support for all providers (LLM_PROVIDER, LLM_MODEL, ANTHROPIC_API_KEY, GOOGLE_API_KEY, OLLAMA_BASE_URL) - **Optional dependencies**: Provider packages are optional - install only what you need ### Files Modified - `requirements.txt` - Added langchain-anthropic, langchain-google-genai, langchain-ollama - `setup.py` - Updated dependencies and version to 2026.2.23 - `config_manager.py` - Multi-provider configuration with validation - `utils.py` - Rewritten get_llm() with optional provider imports - `docksec.py` - Added --provider and --model CLI arguments - `README.md` - Documentation for all providers with setup examples - `docs/CHANGELOG.md` - Release notes for v2026.2.23 ## Backward Compatibility ✓ **No breaking changes** - OpenAI remains the default provider ✓ Existing `.env` files work without modification ✓ All existing commands work identically ✓ Current users don't need to change anything ## Usage Examples ### Use default (OpenAI) export OPENAI_API_KEY="your-key" docksec Dockerfile
advaitpatel
commented
Feb 23, 2026
Owner
Author
advaitpatel
left a comment
advaitpatel
left a comment
There was a problem hiding this comment.
all tests are passed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add support for multiple LLM providers to DockSec, allowing users to choose between OpenAI, Anthropic Claude, Google Gemini, and Ollama (local models) for AI-powered security analysis.
Changes
Core Features
--providerand--modelfor runtime provider/model selectionFiles Modified
requirements.txt- Added langchain-anthropic, langchain-google-genai, langchain-ollamasetup.py- Updated dependencies and version to 2026.2.23config_manager.py- Multi-provider configuration with validationutils.py- Rewritten get_llm() with optional provider importsdocksec.py- Added --provider and --model CLI argumentsREADME.md- Documentation for all providers with setup examplesdocs/CHANGELOG.md- Release notes for v2026.2.23Backward Compatibility
.envfiles work without modificationUsage Examples
Use default (OpenAI)