Feat/refine memory

[suluyana]

[gemini-code-assist[bot]]

Summary of Changes

Hello @suluyana, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on a comprehensive refinement of the agent's memory management system, aiming to enhance its flexibility, efficiency, and robustness. Key changes include a significant overhaul of how memories are stored, retrieved, and configured, alongside improvements in LLM service integration and core utility functions. The goal is to provide a more scalable and maintainable foundation for the agent's long-term memory capabilities and external service interactions.

Highlights

• Refined Memory Management: The memory system has been significantly refactored, centralizing memory handling within DefaultMemory and introducing a SharedMemoryManager for efficient instance reuse. The dedicated mem0ai.py file has been removed, with its core functionalities integrated and enhanced within default_memory.py.
• Enhanced DefaultMemory Capabilities: The DefaultMemory class now supports asynchronous operations for adding and searching memories, includes improved metadata handling (user_id, agent_id, run_id), and offers more flexible search capabilities through meta_infos. It also features dynamic configuration of embedders, LLMs, and vector stores, along with robust error handling for memory operations.
• Standardized LLM Service Configuration: A new ServiceConfig system has been introduced to standardize the retrieval of default base URLs for various LLM services (Modelscope, Dashscope, Deepseek, Anthropic, OpenAI), improving consistency and ease of configuration across different LLM providers.
• Improved Tooling and Configuration: The read_file tool in the filesystem now supports reading multiple file paths simultaneously. SerpApi search clients are now lazily loaded to optimize resource usage. Additionally, the agent.yaml generation configuration has been adjusted, and the coding.yaml memory configuration has been updated to align with the new, more granular memory structure.

Using Gemini Code Assist

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.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 :thumbsup: and :thumbsdown: 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.

[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.