Develop and optimize AI/ML systems with LLM applications and RAG architectures.
npx skills add https://github.com/slantview/claude --skill ai-engineer-slantview
Please help me install this Agent Skill. Skill: ai-engineer Source: https://github.com/slantview/claude/tree/main/skills/ai-engineer Command: npx skills add https://github.com/slantview/claude --skill ai-engineer-slantview
This Skill streamlines the development and deployment of advanced AI/ML systems, focusing on LLM applications, RAG, and efficient AI pipeline management.
Use the ai-engineer skill to set up a new AI project by analyzing requirements and system architecture.
High-intent search queries and answers about installing and using this skill.
To build a production-ready RAG system, you implement retrieval-augmented generation using vector databases like Pinecone and Qdrant alongside LLM APIs from OpenAI and Anthropic. This integration manages embedding strategies and prompt engineering to deliver accurate, context-aware responses.
Optimizing prompt engineering involves creating, testing, and refining prompts for OpenAI and Anthropic models to improve AI performance. It requires tracking usage and performance metrics to ensure cost-efficiency and high-quality text generation in production environments.
Yes, you can integrate multiple LLM providers like OpenAI and Anthropic within the same AI pipeline. This allows you to leverage different models for complex reasoning and text generation tasks while maintaining centralized AI monitoring and cost management.
You monitor LLM application costs and performance metrics by implementing tracking mechanisms within your AI pipelines. This involves logging usage data, analyzing performance outputs, and optimizing embedding strategies and prompt structures for production readiness.
Yes, sentence-transformers are used to generate embeddings for vector databases like Pinecone and Qdrant. They process text data into vector representations, which are essential for retrieval-augmented generation architectures.
miles990Integrate LLM APIs, embeddings, vector databases, and RAG patterns into software.
Exia-thdBuild and deploy production-grade AI/ML systems with MLOps pipelines.
frankxaiImplement concurrent Python programs using asyncio, aiohttp, and async database drivers.
nimeshgurungDeploy ML models and implement MLOps with PyTorch and TensorFlow.
