rag-implementation

RAG Implementation

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

Use this skill when

Do not use this skill when

Instructions

Safety

Core Components

1. Vector Databases

Purpose: Store and retrieve document embeddings efficiently

Options:

2. Embeddings

Purpose: Convert text to numerical vectors for similarity search

Models:

3. Retrieval Strategies

Approaches:

4. Reranking

Purpose: Improve retrieval quality by reordering results

Methods:

Quick Start

from langchain.document_loaders import DirectoryLoader
from langchain.text_splitters import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI

# 1. Load documents
loader = DirectoryLoader('./docs', glob="**/*.txt")
documents = loader.load()

# 2. Split into chunks
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    length_function=len
)
chunks = text_splitter.split_documents(documents)

# 3. Create embeddings and vector store
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(chunks, embeddings)

# 4. Create retrieval chain
qa_chain = RetrievalQA.from_chain_type(
    llm=OpenAI(),
    chain_type="stuff",
    retriever=vectorstore.as_retriever(search_kwargs={"k": 4}),
    return_source_documents=True
)

# 5. Query
result = qa_chain({"query": "What are the main features?"})
print(result['result'])
print(result['source_documents'])

Advanced RAG Patterns

Pattern 1: Hybrid Search

from langchain.retrievers import BM25Retriever, EnsembleRetriever

# Sparse retriever (BM25)
bm25_retriever = BM25Retriever.from_documents(chunks)
bm25_retriever.k = 5

# Dense retriever (embeddings)
embedding_retriever = vectorstore.as_retriever(search_kwargs={"k": 5})

# Combine with weights
ensemble_retriever = EnsembleRetriever(
    retrievers=[bm25_retriever, embedding_retriever],
    weights=[0.3, 0.7]
)

Pattern 2: Multi-Query Retrieval

from langchain.retrievers.multi_query import MultiQueryRetriever

# Generate multiple query perspectives
retriever = MultiQueryRetriever.from_llm(
    retriever=vectorstore.as_retriever(),
    llm=OpenAI()
)

# Single query → multiple variations → combined results
results = retriever.get_relevant_documents("What is the main topic?")

Pattern 3: Contextual Compression

from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import LLMChainExtractor

compressor = LLMChainExtractor.from_llm(llm)

compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor,
    base_retriever=vectorstore.as_retriever()
)

# Returns only relevant parts of documents
compressed_docs = compression_retriever.get_relevant_documents("query")

Pattern 4: Parent Document Retriever

from langchain.retrievers import ParentDocumentRetriever
from langchain.storage import InMemoryStore

# Store for parent documents
store = InMemoryStore()

# Small chunks for retrieval, large chunks for context
child_splitter = RecursiveCharacterTextSplitter(chunk_size=400)
parent_splitter = RecursiveCharacterTextSplitter(chunk_size=2000)

retriever = ParentDocumentRetriever(
    vectorstore=vectorstore,
    docstore=store,
    child_splitter=child_splitter,
    parent_splitter=parent_splitter
)

Document Chunking Strategies

Recursive Character Text Splitter

from langchain.text_splitters import RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    length_function=len,
    separators=["\n\n", "\n", " ", ""]  # Try these in order
)

Token-Based Splitting

from langchain.text_splitters import TokenTextSplitter

splitter = TokenTextSplitter(
    chunk_size=512,
    chunk_overlap=50
)

Semantic Chunking

from langchain.text_splitters import SemanticChunker

splitter = SemanticChunker(
    embeddings=OpenAIEmbeddings(),
    breakpoint_threshold_type="percentile"
)

Markdown Header Splitter

from langchain.text_splitters import MarkdownHeaderTextSplitter

headers_to_split_on = [
    ("#", "Header 1"),
    ("##", "Header 2"),
    ("###", "Header 3"),
]

splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on)

Vector Store Configurations

Pinecone

import pinecone
from langchain.vectorstores import Pinecone

pinecone.init(api_key="your-api-key", environment="us-west1-gcp")

index = pinecone.Index("your-index-name")

vectorstore = Pinecone(index, embeddings.embed_query, "text")

Weaviate

import weaviate
from langchain.vectorstores import Weaviate

client = weaviate.Client("http://localhost:8080")

vectorstore = Weaviate(client, "Document", "content", embeddings)

Chroma (Local)

from langchain.vectorstores import Chroma

vectorstore = Chroma(
    collection_name="my_collection",
    embedding_function=embeddings,
    persist_directory="./chroma_db"
)

Retrieval Optimization

1. Metadata Filtering

# Add metadata during indexing
chunks_with_metadata = []
for i, chunk in enumerate(chunks):
    chunk.metadata = {
        "source": chunk.metadata.get("source"),
        "page": i,
        "category": determine_category(chunk.page_content)
    }
    chunks_with_metadata.append(chunk)

# Filter during retrieval
results = vectorstore.similarity_search(
    "query",
    filter={"category": "technical"},
    k=5
)

2. Maximal Marginal Relevance

# Balance relevance with diversity
results = vectorstore.max_marginal_relevance_search(
    "query",
    k=5,
    fetch_k=20,  # Fetch 20, return top 5 diverse
    lambda_mult=0.5  # 0=max diversity, 1=max relevance
)

3. Reranking with Cross-Encoder

from sentence_transformers import CrossEncoder

reranker = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')

# Get initial results
candidates = vectorstore.similarity_search("query", k=20)

# Rerank
pairs = [[query, doc.page_content] for doc in candidates]
scores = reranker.predict(pairs)

# Sort by score and take top k
reranked = sorted(zip(candidates, scores), key=lambda x: x[1], reverse=True)[:5]

Prompt Engineering for RAG

Contextual Prompt

prompt_template = """Use the following context to answer the question. If you cannot answer based on the context, say "I don't have enough information."

Context:
{context}

Question: {question}

Answer:"""

With Citations

prompt_template = """Answer the question based on the context below. Include citations using [1], [2], etc.

Context:
{context}

Question: {question}

Answer (with citations):"""

With Confidence

prompt_template = """Answer the question using the context. Provide a confidence score (0-100%) for your answer.

Context:
{context}

Question: {question}

Answer:
Confidence:"""

Evaluation Metrics

def evaluate_rag_system(qa_chain, test_cases):
    metrics = {
        'accuracy': [],
        'retrieval_quality': [],
        'groundedness': []
    }

    for test in test_cases:
        result = qa_chain({"query": test['question']})

        # Check if answer matches expected
        accuracy = calculate_accuracy(result['result'], test['expected'])
        metrics['accuracy'].append(accuracy)

        # Check if relevant docs were retrieved
        retrieval_quality = evaluate_retrieved_docs(
            result['source_documents'],
            test['relevant_docs']
        )
        metrics['retrieval_quality'].append(retrieval_quality)

        # Check if answer is grounded in context
        groundedness = check_groundedness(
            result['result'],
            result['source_documents']
        )
        metrics['groundedness'].append(groundedness)

    return {k: sum(v)/len(v) for k, v in metrics.items()}

Resources

Best Practices

Common Issues