RHAIENG-5038: fix missing milvus deps in llama-server targets#98
Merged
Conversation
The shared run_llama_server.yaml configures inline::milvus as the vector_io provider, but 8 agent Makefiles only installed llama-stack and ollama — missing pymilvus, milvus-lite, and a setuptools upper bound (<82.0.0) needed to avoid the removed pkg_resources API. Also moves milvus_data directory creation from the ollama target into llama-server where it actually belongs. Closes: RHAIENG-5038 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Contributor
|
ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (8)
📝 WalkthroughWalkthroughEight agent setup Makefiles are updated in parallel with two changes: ollama targets now display completion messaging, and llama-server targets add pymilvus, milvus-lite, and constrained setuptools dependencies to enable vector database functionality. ChangesMilvus Vector Database and Setup Flow
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Warning Review ran into problems🔥 ProblemsGit: Failed to clone repository. Please run the Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Ticket
RHAIENG-5038
Summary
pymilvus==2.6.9,milvus-lite>=2.5.1, andsetuptools>=80.9.0,<82.0.0to thellama-serverMakefile target in 8 agents (langgraph/{react_agent, human_in_the_loop, agentic_rag, react_with_database_memory}, llamaindex/websearch_agent, crewai/websearch_agent, google/adk, langflow/simple_tool_calling_agent)mkdir -p ../../../milvus_datato thellama-servertarget so it works standalone without runningmake ollamafirstmilvus_datadirectory creation from theollamatarget (6 agents) since it's a llama-stack concern, not an ollama concernautogen/mcp_agentalready had correct deps in its pyproject.toml[llama]extra — no changes neededvanilla_python/openai_responses_agentanda2a/langgraph_crewai_agenthave nollama-servertarget (by design) — not affectedTest plan
For all 9 agents with a
llama-servertarget, verified clean venv install + milvus imports:langgraph/react_agent— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKlanggraph/human_in_the_loop— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKlanggraph/agentic_rag— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKlanggraph/react_with_database_memory— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKllamaindex/websearch_agent— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKcrewai/websearch_agent— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKgoogle/adk— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKlangflow/simple_tool_calling_agent— pymilvus 2.6.9, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKautogen/mcp_agent(no changes, baseline) — pymilvus 3.0.0, milvus_lite OK, setuptools 81.0.0, llama_stack OK, milvus_data OKAssisted by Claude Opus 4.6 (1M context)