Rag Implementation by @wshobson · Skillet

Rag Implementation by @wshobson · Skillet

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

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"])