rag-implementation
用向量資料庫、embedding 和 rerank 建構 RAG 問答系統
中文翻譯
---
name: rag-implementation
description: 用向量資料庫和語意搜尋，為 LLM 應用建構 Retrieval-Augmented Generation（RAG）系統。在實作有知識依據的 AI、建構文件問答系統，或把 LLM 接上外部知識庫時使用。
---
# RAG Implementation
精通 Retrieval-Augmented Generation（RAG），打造能利用外部知識來源、給出準確且有依據回答的 LLM 應用。
## When to Use This Skill
- 針對私有文件建構問答系統
- 建立能提供最新、事實性資訊的聊天機器人
- 用自然語言查詢實作語意搜尋
- 用有依據的回答減少幻覺
- 讓 LLM 能存取特定領域的知識
- 建構文件助理
- 建立附帶來源引用的研究工具
## Core Components
### 1. Vector Databases
**用途**：有效率地儲存和檢索文件 embedding
**選項：**
- **Pinecone**：託管式、可擴展、serverless
- **Weaviate**：開源、混合搜尋、GraphQL
- **Milvus**：高效能、可地端部署
- **Chroma**：輕量、好上手、適合本機開發
- **Qdrant**：快速、支援過濾搜尋、用 Rust 寫的
- **pgvector**：PostgreSQL 擴充套件，可跟 SQL 整合
### 2. Embeddings
**用途**：把文字轉成數值向量，用來做相似度搜尋
**模型（2026）：**
| Model | Dimensions | Best For |
|-------|------------|----------|
| **voyage-3-large** | 1024 | Claude 應用（Anthropic 推薦） |
| **voyage-code-3** | 1024 | 程式碼搜尋 |
| **text-embedding-3-large** | 3072 | OpenAI 應用、高準確度 |
| **text-embedding-3-small** | 1536 | OpenAI 應用、高性價比 |
| **bge-large-en-v1.5** | 1024 | 開源、本機部署 |
| **multilingual-e5-large** | 1024 | 多語言支援 |
### 3. Retrieval Strategies
**做法：**
- **Dense Retrieval**：用 embedding 做語意相似度
- **Sparse Retrieval**：關鍵字比對（BM25、TF-IDF）
- **Hybrid Search**：用加權融合結合 dense + sparse
- **Multi-Query**：產生多種查詢變體
- **HyDE**：產生假設性文件來提升檢索效果
### 4. Reranking
**用途**：重新排序結果來提升檢索品質
**方法：**
- **Cross-Encoders**：以 BERT 為基礎的 rerank（ms-marco-MiniLM）
- **Cohere Rerank**：以 API 提供的 rerank
- **Maximal Marginal Relevance (MMR)**：兼顧多樣性和相關性
- **LLM-based**：用 LLM 為相關性打分
## Quick Start with LangGraph
```python
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
詳細的 pattern 文件放在 `references/details.md`。上面這層導覽不夠用的時候，再去讀那個檔案。英文原文
---
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-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
```python
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.