Audit and optimize RAG pipelines with LlamaIndex, ChromaDB, and Celery best practices.
npx skills add https://github.com/llama-farm/llamafarm --skill rag-skills
Please help me install this Agent Skill. Skill: rag-skills Source: https://github.com/llama-farm/llamafarm/tree/main/.claude/skills/rag-skills Command: npx skills add https://github.com/llama-farm/llamafarm --skill rag-skills
This Skill provides a curated set of RAG-focused best practices covering LlamaIndex usage, ChromaDB vector stores, and Celery workers. It targets reliability, performance, and maintainability of on-prem RAG pipelines.
Apply the rag-skills guidelines to your project by auditing your RAG components and implementing the recommended patterns.
High-intent search queries and answers about installing and using this skill.
Best practices for RAG pipelines using LlamaIndex and ChromaDB include enforcing deterministic IDs, ensuring thread-safe client access, and implementing proper batch processing. These patterns improve ingestion, retrieval, and embedding reliability in production.
To audit a production RAG workflow, apply curated code-review checklists targeting ingestion, retrieval, embeddings, and task orchestration. This enforces configuration guidance and safety considerations across Python stacks to optimize overall pipeline performance.
Ensuring thread-safe ChromaDB client access in Celery workers requires following specific configuration guidance and safety considerations. Implementing proper task naming and routing patterns guarantees consistent, reliable task orchestration across concurrent operations.
Yes, you can use Celery for task orchestration in a LlamaIndex RAG pipeline. Best practices include implementing proper Celery routing, deterministic task naming, and batch processing to maintain reliability and performance across Python stacks.
Inconsistent retrieval results in a RAG ingestion pipeline often stem from lacking deterministic IDs or improper batch processing. Enforcing code-review patterns and configuration guidance for embeddings and ingestion ensures deterministic, reliable pipeline outputs.
The best way to configure Celery routing for RAG task orchestration involves applying specific code-review patterns and safety considerations. Proper task naming and thread-safe client use ensure reliable task execution and consistent pipeline performance.
floflo777Generate RAG project scaffolds for LangChain, LlamaIndex, and vector stores.
nickth3manBuild graph-based LLM workflows with PocketFlow's Node and Flow abstractions.
CodeAtCodeOrchestrate asynchronous Python tasks across distributed workers with Celery.
PatrickjoshanedezDetect verbatim and paraphrased plagiarism using HNSW indexing and fingerprinting.
