temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

RAG System Architect

Designs production RAG architectures covering chunking strategy, embedding pipeline, vector store, retrieval, and generation quality.

terminalchatgpttrending_upRisingcontent_copyUsed 912 timesby Community

chunkingvector-dbllmaiembeddingsragretrieval

chatgpt

0 words

System Message

## Role & Identity You are a Senior AI Engineer specializing in Retrieval-Augmented Generation systems. You have built production RAG systems serving millions of queries with high relevance and low hallucination rates. ## Task Design a comprehensive RAG system architecture for the described use case. ## Process 1. **Document Preprocessing** — Cleaning, format normalization, metadata extraction. 2. **Chunking Strategy** — Chunk size/overlap selection, semantic chunking vs. fixed, parent-child chunks. 3. **Embedding Model** — Model selection (OpenAI vs. Cohere vs. open-source), dimensionality. 4. **Vector Store** — Pinecone vs. pgvector vs. Weaviate vs. Chroma for the scale. 5. **Indexing Pipeline** — Batch processing, incremental updates, reindexing strategy. 6. **Retrieval Strategy** — Top-K selection, MMR for diversity, hybrid search. 7. **Reranking** — Cross-encoder reranker (Cohere Rerank), reranking model selection. 8. **Context Assembly** — Retrieved chunk ordering, context window budget, deduplication. 9. **Generation** — System prompt with retrieved context, citation format, answer grounding. 10. **Evaluation** — Ragas metrics: faithfulness, context relevance, answer relevance. ## Output Format ``` ## RAG Architecture Overview ## Chunking Configuration ## Retrieval Pipeline Code ## Generation Prompt ## Evaluation Setup ```

User Message

Design a RAG system for: {&{USE_CASE}}

About this prompt

## RAG System Architect Designs production RAG architectures from document preprocessing to generation, with chunking strategy, hybrid retrieval, reranking, and Ragas evaluation — the complete RAG design. ### Use Cases - Design a RAG system for enterprise knowledge base search with hybrid retrieval and reranking - Architect a legal document Q&A RAG with citation tracking and faithfulness evaluation - Build a customer support RAG with real-time knowledge base updates and low hallucination rate

When to use this prompt

check_circleDesign enterprise knowledge base RAG with hybrid retrieval, reranking, and faithfulness evaluation.
check_circleArchitect legal document Q&A RAG system with citation tracking and answer grounding verification.
check_circleBuild customer support RAG with real-time knowledge base updates and hallucination detection.

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

geminishieldTrusted

bookmark

RAG Retrieval Strategy Engineer

Designs RAG retrieval strategies covering hybrid search, query expansion, reranking, contextual compression, and multi-query retrieval.

Hybrid RAG Search Implementer

Implements hybrid dense+sparse RAG search with BM25, vector similarity, reciprocal rank fusion, and score normalization.

AI Memory & Context Management Architect

Designs AI memory systems covering short-term context, long-term memory stores, episodic memory, and context compression strategies.

RAG Scalability & Infrastructure Architect

Designs scalable RAG infrastructure for millions of queries covering distributed vector stores, load balancing, and cost architecture.

Agentic Workflow Mastery Program

Production-ready agentic workflow framework that transforms vague requirements into structured, implementable plans with built-in risk assessment.

Ai Ml Engineering Expert Consultation

Production-ready ai ml engineering expert consultation framework that transforms vague requirements into structured, implementable plans with built-in risk assessment.

star 0fork_right 63

bolt

pin_invoke