AI Blocks › Build and ship software
RAG pipeline designer
Describe your documents. Get chunking, embedding and vector database choices, with ways to test results.
RAG pipeline designer is a free AI skill for the job "Build and ship software". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by Alireza Rezvani · Level: advanced · Thinking: high
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
A design for retrieving answers from your documents, backed by numbers from your own files rather than guesses. You get chunking, embedding and vector database choices, plus a test that shows how well retrieval works. It follows three rules: analyse your real documents before choosing chunk sizes, design from your requirements such as size, query load and speed, and finish with an evaluation run. A design without test numbers is only a guess. Model and price choices come as tiers to check before buying, since they go stale fast. It runs three small Python tools for chunking, pipeline design and retrieval scoring.
You give it
- Your documents or a sample
- Number of documents and daily queries
- Speed and cost limits
- Python installed
You get
- Chunking strategy picked from your files
- Pipeline design
- Embedding and database tier choices
- Retrieval test results
Use it when
- You want an assistant that answers from your company documents.
- Your current search returns the wrong passages.
- You must choose a vector database and need a basis for the choice.
- You want to measure retrieval quality before launch.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.