rag-implementation

GEO / AI search

wshobson/agentsskills.sh ↗

Installs

12,214

deduplicated, at the last sync

Since we started

+0.9%

40 readings, about 2 hours apart. Not a live curve.

Our category

GEO / AI search

ours

Last read

Sep 3, 2026

from the directory

Our brief

ours

This skill provides comprehensive patterns and components for building Retrieval-Augmented Generation (RAG) systems. It helps users implement knowledge-grounded AI by integrating Large Language Models with external, proprietary knowledge bases using vector databases and semantic search techniques. Users can build Q&A systems or chatbots that provide accurate, factual responses grounded in specific documents.

What it produces
  • Grounded answers/responses
  • Code examples for advanced RAG patterns
What it needs
  • Documents (knowledge base)
  • Vector store setup (e.g., Pinecone, Chroma)
  • LLM credentials or API keys
Paid services

optional

The evidence shows examples using paid services like Pinecone and Anthropic, which require API keys [3], but also lists local or open-source options (like Chroma) that might not be paid.

Registration

not detected

The evidence does not mention any required account or registration process.

Limits and human review

This skill provides architectural guidance and code patterns, but it cannot execute the full deployment of a RAG system. It also cannot guarantee performance or accuracy in a specific real-world environment, only provide methods to improve retrieval quality.

Evidencestatic findingsplugins/llm-application-dev/skills/rag-implementation/references/details.md:1-82plugins/llm-application-dev/skills/rag-implementation/SKILL.md:1-139
static findingsstatic_finding
[{"code":"env_var","match":"PINECONE_API_KEY","path":"references/details.md"},{"code":"api_key_mention","match":"api_key","path":"references/details.md"}]
plugins/llm-application-dev/skills/rag-implementation/references/details.md1–82 · excerpt truncated
# rag-implementation — detailed patterns and worked examples

## Advanced RAG Patterns

### Pattern 1: Hybrid Search with RRF

```python
from langchain_community.retrievers import BM25Retriever
from langchain.retrievers import EnsembleRetriever

# Sparse retriever (BM25 for keyword matching)
bm25_retriever = BM25Retriever.from_documents(documents)
bm25_retriever.k = 10

# Dense retriever (embeddings for semantic search)
dense_retriever = vectorstore.as_retriever(search_kwargs={"k": 10})

# Combine with Reciprocal Rank Fusion weights
ensemble_retriever = EnsembleRetriever(
    retrievers=[bm25_retriever, dense_retriever],
    weights=[0.3, 0.7]  # 30% keyword, 70% semantic
)
```

### Pattern 2: Multi-Query Retrieval

```python
from langchain.retrievers.multi_query import MultiQueryRetriever

# Generate multiple query perspectives for better recall
multi_query_retriever = MultiQueryRetriever.from_llm(
    retriever=vectorstore.as_retriever(search_kwargs={"k": 5}),
    llm=llm
)

# Single query → multiple variations → combined results
results = await multi_query_retriever.ainvoke("What is the main topic?")
```

### Pattern 3: Contextual Compression

```python
from langchain.retrievers
plugins/llm-application-dev/skills/rag-implementation/SKILL.md1–139
---
name: rag-implementation
description: Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
---

# RAG Implementation

Master Retrieval-Augmented Generation (RAG) to build LLM applications that provide accurate, grounded responses using external knowledge sources.

## When to Use This Skill

- Building Q&A systems over proprietary documents
- Creating chatbots with current, factual information
- Implementing semantic search with natural language queries
- Reducing hallucinations with grounded responses
- Enabling LLMs to access domain-specific knowledge
- Building documentation assistants
- Creating research tools with source citation

## Core Components

### 1. Vector Databases

**Purpose**: Store and retrieve document embeddings efficiently

**Options:**

- **Pinecone**: Managed, scalable, serverless
- **Weaviate**: Open-source, hybrid search, GraphQL
- **Milvus**: High performance, on-premise
- **Chroma**: Lightweight, easy to use, local development
- **Qdrant**: Fast, filtered search, Rust

Read 3 of 3 text files in the skill.

Checked September 2026 · GemmaWritten from the skill's published files. Check the source before relying on access or cost details.

Installfrom the directory

npx skills add https://github.com/wshobson/agents

Installing happens there, not here. We are an index with an opinion, not a mirror.

What is inside itfrom the directory

references/details.md
SKILL.md

2 files — names only. The directory does not report sizes.

What the auditors foundfrom the directory

A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.

Gen Agent Trust HubThis skill provides educational templates for implementing Retrieval-Augmented Generation (RAG) using standard libraries. It follows security best practices such as utilizing environment variables for credentials. As with all RAG architectures, it is susceptible to indirect prompt injection from retrieved data sources.Mar 7, 2026 · SAFEpass
SocketNo alertsMar 18, 2026pass
SnykRisk: LOW · No issuesMar 7, 2026 · LOWpass
Runlayer1/1 file flaggedMar 7, 2026 · LOWpass
ZeroLeaksScore: 93/100 · 2 sections analyzedApr 16, 2026 · NONEpass

Installs, reading by readingours

12.1k
12.2k
Aug 31, 202640 readings over 4 days, drawn as the last reading of each day.Sep 3, 2026

Axis starts at 12.1k, not zero — the range is 12.1k to 12.2k.

Asked out loudspoken, not typed

The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.

asking about costsDo I need to pay for this?

The examples show using services like Pinecone and Anthropic, which require API keys or credentials [3]. However, the documentation also lists local options such as Chroma that might not incur costs.

building a systemWhat kind of knowledge bases can I connect it to?

It supports connecting to various vector databases including Pinecone, Weaviate, and Chroma. This allows you to build Q&A systems over proprietary documents or integrate domain-specific knowledge.

Filed alongside itours