rag-pipelines skillA
rag-pipelines is agent-read markdown (skill) from jnpiyush/agentx: Design and build production RAG (Retrieval-Augmented Generation) pipelines. Use when implementing document ingestion, chunking strategies, embedding selection, vector search, hybrid retrieval, reranking, or generation with grounding..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# RAG Pipelines > **Purpose**: Build production-grade Retrieval-Augmented Generation systems that ground LLM responses in authoritative knowledge. --- ## When to Use This Skill - Building document Q&A systems grounded in enterprise knowledge - Implementing semantic search over unstructured documents - Designing chunking strategies for different document types - Selecting and configuring vector databases for retrieval - Implementing hybrid search (keyword + semantic) and reranking - Optimizing retrieval quality (precision, recall, faithfulness) ## Prerequisites - Document corpus to index - Embedding model access (OpenAI, Azure OpenAI, or open-source) - Vector store or search service - LLM for generation ## Decision Tree ``` Building a RAG system? +- What type of documents? | +- Short, structured (FAQ, KB articles)? | -> Small chunks (256-512 tokens), simple splitting | +- Long, unstructured (reports, papers)? | -> Semantic chunking, hierarchical retrieval | +- Code repositories? | -> AST-aware chunking, function-level | +- Multi-modal (PDFs with tables/images)? | -> Document intelligence + specialized parsers +- What query patterns? …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/rag-pipelines@v1.0.0mdr add jnpiyush/agentx/rag-pipelines@sha256:c1d080a58f61077ePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_njm43dryh4uf7dsh)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 11,694 B | A | view · diff |
| v1.0.0 | 2026-04-22 | 7f3a017 | 11,692 B | A | view · diff |
| v1.0.0 | 2026-03-04 | 848caee | 11,679 B | A | view · diff |
| v1.0.0 | 2026-03-01 | 969f335 | 11,674 B | A | view · diff |
| v1.0.0 | 2026-03-01 | bb11a09 | 10,650 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11694 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_njm43dryh4uf7dsh GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/rag-pipelines GET https://markdownregistry.com/api/v1/blob/c1d080a58f61077ec7a2054e83a09b068197f65e46ab20bdeab9a627b2724eeb
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.