rag-patternslisted
Install: claude install-skill claude-dev-suite/claude-dev-suite
# RAG Patterns
## Standard RAG Pipeline
```
Documents → Chunk → Embed → Store (vector DB)
Query → Embed → Retrieve → Augment prompt → Generate answer
```
## Chunking Strategies
```python
from langchain_text_splitters import RecursiveCharacterTextSplitter
# Recommended defaults
splitter = RecursiveCharacterTextSplitter(
chunk_size=800, # chars (not tokens)
chunk_overlap=200,
separators=["\n\n", "\n", ". ", " ", ""],
)
chunks = splitter.split_documents(docs)
```
| Strategy | Best For | Chunk Size |
|----------|----------|------------|
| Fixed-size with overlap | General text | 500-1000 chars |
| Recursive character | Structured docs | 500-1000 chars |
| Semantic (by meaning) | Long-form content | Variable |
| Document-aware (markdown headers) | Technical docs | Section-based |
### Metadata Enrichment
```python
for chunk in chunks:
chunk.metadata.update({
"source": doc.metadata["source"],
"section": extract_section_title(chunk),
"doc_id": doc.metadata["id"],
"chunk_index": i,
})
```
## Retrieval Strategies
### Hybrid Search (keyword + semantic)
```python
from langchain.retrievers import EnsembleRetriever
from langchain_community.retrievers import BM25Retriever
bm25 = BM25Retriever.from_documents(docs, k=5)
vector_retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
hybrid = EnsembleRetriever(
retrievers=[bm25, vector_retriever],
weights=[0.3, 0.7],
)
```
### Re-ranking
```python
from cohere i