GitHub user xintongsong created a discussion: Planning Flink Agents 0.3
# Brainstorm
Let's start with a brainstorm of potential features, issues, tasks that we may
work on in this release cycle. No worries about feasibility, priority, workload
and time plan at this stage. Just list whatever come to you mind, and we'll
discuss them later.
Below is my list (not ordered by priority). Please feel free to add more in
comments.
## From @xintongsong
- Installation & Deployment
- Enhance the quickstart experience. - Currently, there are too many manual
steps, thus chances for users to make mistakes and run into problems.
- Agent Development
- Support Python 3.12
- Support cross-language actions & events
- Memory
- Support for knowledge. - Not entirely sure about this. What is the
relationship between Knowledge and ContextRetrievalAction?
- MemoryRef auto resolving - Using MemoryRef for Events and Resource
arguments just like using the referenced value
- Integrate with mature AI storage frameworks - E.g., mem0, reme, agents,
etc. Why build from scratch?
- Support auto-arguments for tool using - Not all arguments should be decided
by LLM. Avoid unnecessary randomness.
- Support searching tools and prompts from the MCP server
- Support for agent skills
- Support for multi-agent system
- Multimodal capabilities
- Human-in-the-loop
- Structured information extraction
- Agent Execution and Operation
- Durable execution enhancement - What if the job fails when the durable
execution code block is executed halfway? 2PC? User defined handling?
- Serve as a service - A service that accepts the request, put it into the
source, collect the output from the sink, and send the response.
- Event log
- Enable by default and display in UI
- Support per-event-type configurable log levels
- Support querying and filtering
- Eval
- How to quantitatively measure agent performance?
- How to compare performance of two different versions (prompt, model,
parameter, ...)?
- Tech Debt
- Refactor ActionExecutionOperator
- Refactor AgentPlan & resource cache
- Loading MCP Tools & Prompts in runtime - in case of updates on the MCP
server side
- Support async execution for cross-language resource access
- Unify long-term memory management for Java & Python
- CI
- Run the examples
- Submit jobs to a standalone flink cluster - in addition to the
mini-cluster
- Fault tolerant test - kill the TM and see if it recovers as expected
GitHub link: https://github.com/apache/flink-agents/discussions/516
----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]
