rag-implementation
GEO / AI searchwshobson/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
oursThis 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.
- Grounded answers/responses
- Code examples for advanced RAG patterns
- Documents (knowledge base)
- Vector store setup (e.g., Pinecone, Chroma)
- LLM credentials or API keys
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.
not detected
The evidence does not mention any required account or registration process.
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
[{"code":"env_var","match":"PINECONE_API_KEY","path":"references/details.md"},{"code":"api_key_mention","match":"api_key","path":"references/details.md"}]# 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--- 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.
Installfrom the directory
npx skills add https://github.com/wshobson/agentsInstalling happens there, not here. We are an index with an opinion, not a mirror.
What is inside itfrom the directory
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.
Installs, reading by readingours
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.
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.
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.