opensearch-project / opensearch-project/flow-framework
[META] Onboard templates for agent-related use cases
Open
Nobody has claimed this yet.
discuss
Meta
- Dominant language
- Java
- Stars
- 62
- Forks
- 66
- Avg merge
- 3d 20h
- Merged PRs (30d)
- 20
Description
There are several new agent-related use cases which could benefit from having out-of-the-box flow framework templates built for, and greatly help users try out these new features.
This includes but is not limited to:
- Chatbot with memory: conversational agent + LLM provisioning
- Deep research: plan-execute-reflect agent + LLM provisioning
- Deep research with MCP: plan-execute-reflect agent + LLM provisioning + MCP integration for common/useful MCP servers
- Agentic search (NLQ): flow agent + LLM + ingest pipeline provisioning
- Agentic search (RAG): TBD, currently not supported as of Sept 2025
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the existing flow framework templates and identify which listed use cases are supported by the current framework, starting with chatbot with memory and deep research. Done means defining the scope and adding supported out-of-the-box templates, while documenting or separating the agentic RAG case because the issue says it is not currently supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java
- Domain
- ai, tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100