• docs/en/Components/Config.md
  • Updated documentation by adding details about the knowledge_search_paths parameter and a quick start guide for knowledge search.
• docs/zh/Components/config.md
  • Updated Chinese configuration documentation by adding details about knowledge_search_paths and a quick start guide, and adjusted formatting.
  • Corrected minor formatting inconsistencies in various sections (e.g., spacing around backticks).
• examples/knowledge_search/agent.yaml.example
  • Added a new example YAML configuration file for Sirchmunk Knowledge Search, demonstrating its setup and available parameters.
• ms_agent/agent/llm_agent.py
  • Imported SirchmunkSearch for knowledge retrieval.
  • Added a knowledge_search attribute to the LLMAgent class (note: type hint SirschmunkSearch contains a typo and should be SirchmunkSearch).
  • Implemented prepare_knowledge_search to initialize the SirchmunkSearch component based on configuration.
  • Modified do_rag method to incorporate knowledge search results into user messages, populating searching_detail and search_result fields.
• ms_agent/cli/run.py
  • Imported OmegaConf for dynamic configuration management.
  • Added a load_env_file method to load environment variables from a .env file.
  • Introduced --knowledge_search_paths argument to enable and configure SirchmunkSearch via the command line.
  • Updated _execute_with_config to handle dynamic creation or update of the knowledge_search configuration based on the new CLI argument.
  • Modified default config loading to use a built-in agent.yaml if no config is specified and no local agent.yaml is found.
• ms_agent/knowledge_search/README.md
  • Added a new README file detailing the Sirchmunk Knowledge Search integration, including its features, installation, configuration, usage examples, environment variables, testing, and troubleshooting.
• ms_agent/knowledge_search/init.py
  • Added the __init__.py file to define the knowledge_search module and expose the SirchmunkSearch class.
• ms_agent/knowledge_search/sirchmunk_search.py
  • Added the SirchmunkSearch class, which wraps sirchmunk.search.AgenticSearch to integrate with ms_agent.
  • Implemented configuration validation, LLM parameter inheritance from the main llm module, search execution, and result parsing into a standard format.
  • Provided methods for adding documents (with a warning for direct addition), retrieving results, querying for synthesized answers, and accessing search logs and details.
• ms_agent/llm/dashscope_llm.py
  • Corrected the base_url parameter in DashScope LLM initialization from config.llm.modelscope_base_url to config.llm.dashscope_base_url.
• ms_agent/llm/utils.py
  • Extended the Message class by adding searching_detail (for search logs and metadata) and search_result (for raw search outcomes) fields to support knowledge search.
• ms_agent/rag/utils.py
  • Added a comment clarifying that SirchmunkSearch is integrated directly within LLMAgent and not through the rag_mapping utility.
• tests/knowledge_search/init.py
  • Added the __init__.py file for the knowledge_search tests module.
• tests/knowledge_search/test_sirschmunk.py
  • Added unit tests for the SirchmunkSearch integration with LLMAgent.
  • Included setup for creating temporary test files and configuration for the agent.
  • Verified that LLMAgent initializes correctly with knowledge search and that user messages are populated with searching_detail and search_result after a query.

• The pull request was opened by suluyana.
• An image was included in the pull request description, likely showcasing the new knowledge search feature in action.
• New files were added to introduce the SirchmunkSearch integration, including its core logic, documentation, and example configurations.
• Existing core agent and CLI files were modified to incorporate and enable the new knowledge search functionality.
• Unit tests were added to ensure the proper functioning and integration of the knowledge search feature within the LLMAgent framework.

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.