RAG Implementation

Seth HobsonCommunityCreated by Seth Hobson

Skill
Tool integration
Data and AI
MIT
No issues found

From the author

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.

— the description by Seth Hobson

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured approach to implementing Retrieval-Augmented Generation (RAG) systems. It covers the end-to-end pipeline, including vector database selection, embedding model configuration, advanced retrieval strategies, and reranking techniques. It includes practical implementation patterns using LangGraph and LangChain to help developers build accurate, knowledge-grounded AI applications that minimize hallucinations.

What it does

Explains the architecture of RAG systems including retrieval and generation phases.
Provides a comparative overview of vector databases and embedding models.
Details advanced retrieval strategies like hybrid search, multi-query, and HyDE.
Demonstrates how to implement RAG pipelines using LangGraph.
Offers patterns for contextual compression and parent document retrieval.
Outlines document chunking strategies for optimized semantic search.

When to use it

When building Q&A systems over proprietary or domain-specific documents.
When you need to reduce LLM hallucinations by grounding responses in factual data.
When creating chatbots that require access to current or private information.
When implementing semantic search functionality for natural language queries.
When building research tools that require source citations.

Advantages

Enables LLMs to access and reason over private or external knowledge bases.
Improves response accuracy and reliability through grounded context.
Provides modular patterns for scaling retrieval performance.
Supports diverse search requirements through hybrid and multi-query approaches.
Facilitates the creation of transparent AI systems with source-backed answers.

Usage examples

“How do I implement a hybrid search RAG pipeline?”: The agent provides a code example using EnsembleRetriever to combine BM25 keyword matching with dense vector embeddings using weighted Reciprocal Rank Fusion.
“What is the best way to improve retrieval accuracy for long documents?”: The agent suggests using the Parent Document Retriever pattern, which uses small chunks for precise retrieval while maintaining larger parent chunks for context.
“How can I use HyDE to improve my RAG system?”: The agent provides a LangGraph implementation that generates a hypothetical document from the user's query to perform more effective semantic similarity searches.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/wshobson/rag-implementation/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip rag-implementation.zip -d .agents/skills

Documentation by Seth Hobson

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: Local persistence with Lite, or self-hosted server deployments
Chroma: Lightweight, easy to use, local development
Qdrant: Fast, filtered search, Rust-based
pgvector: PostgreSQL extension, SQL integration

2. Embeddings

Purpose: Convert text to numerical vectors for similarity search

Models (2026):

Model	Dimensions	Best For
voyage-3-large	1024	Claude apps (Anthropic recommended)
voyage-code-3	1024	Code search
text-embedding-3-large	3072	OpenAI apps, high accuracy
text-embedding-3-small	1536	OpenAI apps, cost-effective
bge-large-en-v1.5	1024	Open source, local deployment
multilingual-e5-large	1024	Multi-language support

3. Retrieval Strategies

Approaches:

Dense Retrieval: Semantic similarity via embeddings
Sparse Retrieval: Keyword matching (BM25, TF-IDF)
Hybrid Search: Combine dense + sparse with weighted fusion
Multi-Query: Generate multiple query variations
HyDE: Generate hypothetical documents for better retrieval

4. Reranking

Purpose: Improve retrieval quality by reordering results

Methods:

Cross-Encoders: BERT-based reranking (ms-marco-MiniLM)
Cohere Rerank: API-based reranking
Maximal Marginal Relevance (MMR): Diversity + relevance
LLM-based: Use LLM to score relevance

Quick Start with LangGraph

from langgraph.graph import StateGraph, START, END
from langchain_anthropic import ChatAnthropic
from langchain_voyageai import VoyageAIEmbeddings
from langchain_pinecone import PineconeVectorStore
from langchain_core.documents import Document
from langchain_core.prompts import ChatPromptTemplate
from langchain_text_splitters import RecursiveCharacterTextSplitter
from typing import TypedDict, Annotated

class RAGState(TypedDict):
    question: str
    context: list[Document]
    answer: str

# Initialize components
llm = ChatAnthropic(model="claude-sonnet-5")
embeddings = VoyageAIEmbeddings(model="voyage-3-large")
vectorstore = PineconeVectorStore(index_name="docs", embedding=embeddings)
retriever = vectorstore.as_retriever(search_kwargs={"k": 4})

# RAG prompt
rag_prompt = ChatPromptTemplate.from_template(
    """Answer based on the context below. If you cannot answer, say so.

    Context:
    {context}

    Question: {question}

    Answer:"""
)

async def retrieve(state: RAGState) -> RAGState:
    """Retrieve relevant documents."""
    docs = await retriever.ainvoke(state["question"])
    return {"context": docs}

async def generate(state: RAGState) -> RAGState:
    """Generate answer from context."""
    context_text = "\n\n".join(doc.page_content for doc in state["context"])
    messages = rag_prompt.format_messages(
        context=context_text,
        question=state["question"]
    )
    response = await llm.ainvoke(messages)
    return {"answer": response.content}

# Build RAG graph
builder = StateGraph(RAGState)
builder.add_node("retrieve", retrieve)
builder.add_node("generate", generate)
builder.add_edge(START, "retrieve")
builder.add_edge("retrieve", "generate")
builder.add_edge("generate", END)

rag_chain = builder.compile()

# Use
result = await rag_chain.ainvoke({"question": "What are the main features?"})
print(result["answer"])

Detailed patterns and worked examples

Detailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.

Files

ATTRIBUTION.mdAdded by AutoGineer992 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md4.5 KiB
references/details.md11.5 KiB

references/details.md

rag-implementation — detailed patterns and worked examples

Advanced RAG Patterns

Pattern 1: Hybrid Search with RRF

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

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

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

# Compressor extracts only relevant portions
compressor = LLMChainExtractor.from_llm(llm)

compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor,
    base_retriever=vectorstore.as_retriever(search_kwargs={"k": 10})
)

# Returns only relevant parts of documents
compressed_docs = await compression_retriever.ainvoke("specific query")

Pattern 4: Parent Document Retriever

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

# Small chunks for precise retrieval, large chunks for context
child_splitter = RecursiveCharacterTextSplitter(chunk_size=400, chunk_overlap=50)
parent_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=200)

# Store for parent documents
docstore = InMemoryStore()

parent_retriever = ParentDocumentRetriever(
    vectorstore=vectorstore,
    docstore=docstore,
    child_splitter=child_splitter,
    parent_splitter=parent_splitter
)

# Add documents (splits children, stores parents)
await parent_retriever.aadd_documents(documents)

# Retrieval returns parent documents with full context
results = await parent_retriever.ainvoke("query")

Pattern 5: HyDE (Hypothetical Document Embeddings)

from langchain_core.prompts import ChatPromptTemplate

class HyDEState(TypedDict):
    question: str
    hypothetical_doc: str
    context: list[Document]
    answer: str

hyde_prompt = ChatPromptTemplate.from_template(
    """Write a detailed passage that would answer this question:

    Question: {question}

    Passage:"""
)

async def generate_hypothetical(state: HyDEState) -> HyDEState:
    """Generate hypothetical document for better retrieval."""
    messages = hyde_prompt.format_messages(question=state["question"])
    response = await llm.ainvoke(messages)
    return {"hypothetical_doc": response.content}

async def retrieve_with_hyde(state: HyDEState) -> HyDEState:
    """Retrieve using hypothetical document."""
    # Use hypothetical doc for retrieval instead of original query
    docs = await retriever.ainvoke(state["hypothetical_doc"])
    return {"context": docs}

# Build HyDE RAG graph
builder = StateGraph(HyDEState)
builder.add_node("hypothetical", generate_hypothetical)
builder.add_node("retrieve", retrieve_with_hyde)
builder.add_node("generate", generate)
builder.add_edge(START, "hypothetical")
builder.add_edge("hypothetical", "retrieve")
builder.add_edge("retrieve", "generate")
builder.add_edge("generate", END)

hyde_rag = builder.compile()

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 in order
)

chunks = splitter.split_documents(documents)

Token-Based Splitting

from langchain_text_splitters import TokenTextSplitter

splitter = TokenTextSplitter(
    chunk_size=512,
    chunk_overlap=50,
    encoding_name="cl100k_base"  # OpenAI tiktoken encoding
)

Semantic Chunking

from langchain_experimental.text_splitter import SemanticChunker

splitter = SemanticChunker(
    embeddings=embeddings,
    breakpoint_threshold_type="percentile",
    breakpoint_threshold_amount=95
)

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,
    strip_headers=False
)

Vector Store Configurations

Pinecone (Serverless)

from pinecone import Pinecone, ServerlessSpec
from langchain_pinecone import PineconeVectorStore

# Initialize Pinecone client
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

# Create index if needed
if "my-index" not in pc.list_indexes().names():
    pc.create_index(
        name="my-index",
        dimension=1024,  # voyage-3-large dimensions
        metric="cosine",
        spec=ServerlessSpec(cloud="aws", region="us-east-1")
    )

# Create vector store
index = pc.Index("my-index")
vectorstore = PineconeVectorStore(index=index, embedding=embeddings)

Weaviate

import weaviate
from langchain_weaviate import WeaviateVectorStore

client = weaviate.connect_to_local()  # or connect_to_weaviate_cloud()

vectorstore = WeaviateVectorStore(
    client=client,
    index_name="Documents",
    text_key="content",
    embedding=embeddings
)

Chroma (Local Development)

from langchain_chroma import Chroma

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

Milvus (Local Persistence)

Install langchain-milvus>=0.4,<0.5 and milvus-lite>=3.2.2,<4 (Python 3.10+). Reuse the application's embeddings object.

from langchain_milvus import Milvus

vectorstore = Milvus(
    embedding_function=embeddings,
    collection_name="documents",
    connection_args={"uri": "./rag_milvus.db"},
    index_params={"index_type": "AUTOINDEX", "metric_type": "COSINE", "params": {}},
    consistency_level="Strong",
    drop_old=False,
)

Reuse the same file, collection, and embedding model to reopen persisted data. Close vectorstore.client on application shutdown. See the Milvus integration guide.

pgvector (PostgreSQL)

from langchain_postgres.vectorstores import PGVector

connection_string = "postgresql+psycopg://user:pass@localhost:5432/vectordb"

vectorstore = PGVector(
    embeddings=embeddings,
    collection_name="documents",
    connection=connection_string,
)

Retrieval Optimization

1. Metadata Filtering

from langchain_core.documents import Document

# Add metadata during indexing
docs_with_metadata = []
for doc in documents:
    doc.metadata.update({
        "source": doc.metadata.get("source", "unknown"),
        "category": determine_category(doc.page_content),
        "date": datetime.now().isoformat()
    })
    docs_with_metadata.append(doc)

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

2. Maximal Marginal Relevance (MMR)

# Balance relevance with diversity
results = await vectorstore.amax_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')

async def retrieve_and_rerank(query: str, k: int = 5) -> list[Document]:
    # Get initial results
    candidates = await vectorstore.asimilarity_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
    ranked = sorted(zip(candidates, scores), key=lambda x: x[1], reverse=True)
    return [doc for doc, score in ranked[:k]]

4. Cohere Rerank

from langchain.retrievers import CohereRerank
from langchain_cohere import CohereRerank

reranker = CohereRerank(model="rerank-english-v3.0", top_n=5)

# Wrap retriever with reranking
reranked_retriever = ContextualCompressionRetriever(
    base_compressor=reranker,
    base_retriever=vectorstore.as_retriever(search_kwargs={"k": 20})
)

Prompt Engineering for RAG

Contextual Prompt with Citations

rag_prompt = ChatPromptTemplate.from_template(
    """Answer the question based on the context below. Include citations using [1], [2], etc.

    If you cannot answer based on the context, say "I don't have enough information."

    Context:
    {context}

    Question: {question}

    Instructions:
    1. Use only information from the context
    2. Cite sources with [1], [2] format
    3. If uncertain, express uncertainty

    Answer (with citations):"""
)

Structured Output for RAG

from pydantic import BaseModel, Field

class RAGResponse(BaseModel):
    answer: str = Field(description="The answer based on context")
    confidence: float = Field(description="Confidence score 0-1")
    sources: list[str] = Field(description="Source document IDs used")
    reasoning: str = Field(description="Brief reasoning for the answer")

# Use with structured output
structured_llm = llm.with_structured_output(RAGResponse)

Evaluation Metrics

from typing import TypedDict

class RAGEvalMetrics(TypedDict):
    retrieval_precision: float  # Relevant docs / retrieved docs
    retrieval_recall: float     # Retrieved relevant / total relevant
    answer_relevance: float     # Answer addresses question
    faithfulness: float         # Answer grounded in context
    context_relevance: float    # Context relevant to question

async def evaluate_rag_system(
    rag_chain,
    test_cases: list[dict]
) -> RAGEvalMetrics:
    """Evaluate RAG system on test cases."""
    metrics = {k: [] for k in RAGEvalMetrics.__annotations__}

    for test in test_cases:
        result = await rag_chain.ainvoke({"question": test["question"]})

        # Retrieval metrics
        retrieved_ids = {doc.metadata["id"] for doc in result["context"]}
        relevant_ids = set(test["relevant_doc_ids"])

        precision = len(retrieved_ids & relevant_ids) / len(retrieved_ids)
        recall = len(retrieved_ids & relevant_ids) / len(relevant_ids)

        metrics["retrieval_precision"].append(precision)
        metrics["retrieval_recall"].append(recall)

        # Use LLM-as-judge for quality metrics
        quality = await evaluate_answer_quality(
            question=test["question"],
            answer=result["answer"],
            context=result["context"],
            expected=test.get("expected_answer")
        )
        metrics["answer_relevance"].append(quality["relevance"])
        metrics["faithfulness"].append(quality["faithfulness"])
        metrics["context_relevance"].append(quality["context_relevance"])

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

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

Seth Hobson

Publisher

Seth Hobson (Community)

Source

wshobson/agents · plugins/llm-application-dev/skills/rag-implementation · commit 4bde316

Licence

MIT License (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by Seth Hobson or Seth Hobson.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download rag-implementation.zip

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by Seth Hobson

RAG Implementation

When to Use This Skill

Core Components

1. Vector Databases

2. Embeddings

3. Retrieval Strategies

4. Reranking

Quick Start with LangGraph

Detailed patterns and worked examples

Files

references/details.md

rag-implementation — detailed patterns and worked examples

Advanced RAG Patterns

Pattern 1: Hybrid Search with RRF

Pattern 2: Multi-Query Retrieval

Pattern 3: Contextual Compression

Pattern 4: Parent Document Retriever

Pattern 5: HyDE (Hypothetical Document Embeddings)

Document Chunking Strategies

Recursive Character Text Splitter

Token-Based Splitting

Semantic Chunking

Markdown Header Splitter

Vector Store Configurations

Pinecone (Serverless)

Weaviate

Chroma (Local Development)

Milvus (Local Persistence)

pgvector (PostgreSQL)

Retrieval Optimization

1. Metadata Filtering

2. Maximal Marginal Relevance (MMR)

3. Reranking with Cross-Encoder

4. Cohere Rerank

Prompt Engineering for RAG

Contextual Prompt with Citations

Structured Output for RAG

Evaluation Metrics

Requirements and compatibility

Security

Attribution and licence

Related skills

Claude API

Transformers

Open Notebook

Vision Sft

LLM Evaluation

Lora Qlora Recipes

Download ZIP