feat: add AG2 multi-agent RAG integration with Milvus

[faridun-ag2]

Summary

Add an integration notebook for AG2 (formerly AutoGen), a multi-agent conversation framework.

• integration/ag2/ag2_multiagent_rag_with_milvus.ipynb — Complete notebook

How it works

1. Documents are embedded using OpenAI embeddings and stored in Milvus (using Milvus Lite)
2. AG2 Research Agent uses a registered search_documents tool to query Milvus
3. AG2 Analyst Agent synthesizes retrieved information into grounded answers
4. Agents collaborate via AG2 GroupChat with automatic tool execution

Key features

• Zero setup: Uses Milvus Lite (in-process, no Docker needed)
• OpenAI embeddings: text-embedding-3-small for text vectorization
• Multi-agent RAG: Researcher retrieves, Analyst synthesizes
• Tool registration: Milvus search exposed as AG2 tool via decorator pattern
• Colab ready: Can run directly in Google Colab

Test plan

• Tested locally with real OpenAI API calls — agents collaborate, retrieve from Milvus, and produce grounded answers
• Black formatted
• DCO signed

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[sre-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: faridun-ag2

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[sre-ci-robot]

Welcome @faridun-ag2! It looks like this is your first PR to milvus-io/bootcamp 🎉

[faridun-ag2]

Hi @jaelgu !

Could you please review this PR when you get a chance? It adds an integration notebook for AG2 (formerly AutoGen) — a multi-agent conversation framework.

The notebook demonstrates AG2 agents collaborating to answer questions using Milvus as the vector store for RAG. It follows the same patterns as the existing LangGraph and LlamaIndex integration notebooks.

Thanks!