chunking-strategies

Included with Lifetime

$97 forever

Expert guidance on document chunking strategies for RAG systems. Use this skill when designing how to split documents for vector embeddings. Activate when: chunking, chunk size, text splitting, document segmentation, overlap, semantic chunking, recursive splitting.

AI Agents

What this skill does


# Chunking Strategies for RAG

**Optimize document splitting for retrieval accuracy and context preservation.**

## When to Use

- Designing a new RAG pipeline
- Retrieval quality is poor due to chunk boundaries
- Documents have mixed content types (code, tables, prose)
- Need to balance context window limits with retrieval precision

## Chunking Methods

### 1. Fixed-Size Chunking

```python
from langchain.text_splitter import CharacterTextSplitter

splitter = CharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separator="\n"
)
chunks = splitter.split_text(document)
```

**Best for**: Homogeneous content, quick prototyping
**Avoid when**: Documents have natural boundaries (sections, paragraphs)

### 2. Recursive Character Splitting

```python
from langchain.text_splitter import RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separators=["\n\n", "\n", ".", " ", ""]
)
chunks = splitter.split_documents(docs)
```

**Best for**: General-purpose text, maintains paragraph integrity
**Hierarchy**: Tries larger separators first, falls back to smaller

### 3. Semantic Chunking

```python
from langchain_experimental.text_splitter import SemanticChunker
from langchain_openai import OpenAIEmbeddings

splitter = SemanticChunker(
    embeddings=OpenAIEmbeddings(),
    breakpoint_threshold_type="percentile",
    breakpoint_threshold_amount=95
)
chunks = splitter.split_text(document)
```

**Best for**: When meaning matters more than size
**Trade-off**: Slower, requires embedding calls

### 4. Document-Specific Chunking

#### Markdown
```python
from langchain.text_splitter import MarkdownHeaderTextSplitter

headers = [
    ("#", "h1"),
    ("##", "h2"),
    ("###", "h3"),
]
splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers)
chunks = splitter.split_text(markdown_doc)
```

#### Code
```python
from langchain.text_splitter import Language, RecursiveCharacterTextSplitter

splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.PYTHON,
    chunk_size=2000,
    chunk_overlap=200
)
chunks = splitter.split_documents(code_docs)
```

#### HTML
```python
from langchain.text_splitter import HTMLHeaderTextSplitter

splitter = HTMLHeaderTextSplitter(
    headers_to_split_on=[("h1", "h1"), ("h2", "h2"), ("h3", "h3")]
)
chunks = splitter.split_text(html_doc)
```

## Chunk Size Guidelines

| Content Type | Recommended Size | Overlap |
|--------------|------------------|---------|
| Dense technical docs | 500-1000 tokens | 10-20% |
| Conversational/FAQ | 200-500 tokens | 5-10% |
| Legal/contracts | 1000-1500 tokens | 15-20% |
| Code | 1500-2000 tokens | 10-15% |
| Mixed content | 800-1200 tokens | 15% |

## Advanced: Parent-Child Chunking

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

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

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

**Why**: Small chunks = precise retrieval, large chunks = better context

## Metadata Enrichment

Always attach metadata to chunks:

```python
for i, chunk in enumerate(chunks):
    chunk.metadata.update({
        "source": doc.metadata["source"],
        "chunk_index": i,
        "total_chunks": len(chunks),
        "doc_type": detect_doc_type(chunk.page_content),
        "has_code": bool(re.search(r'```', chunk.page_content)),
        "timestamp": datetime.now().isoformat()
    })
```

## Evaluation Checklist

- [ ] Chunks don't break mid-sentence
- [ ] Code blocks stay intact
- [ ] Tables aren't split across chunks
- [ ] Headers stay with their content
- [ ] Overlap preserves context continuity
- [ ] Metadata enables filtering

## Best Practices

1. **Start with recursive splitting** - works for 80% of cases
2. **Test retrieval quality** - not just chunk count
3. **Use overlap** - 10-20% prevents context loss at boundaries
4. **Match chunk size to model** - consider embedding model's optimal input
5. **Preserve structure** - use document-aware splitters when possible

Files: 1

Size: 4.6 KB

Complexity: 9/100

Category: AI Agents

Source: https://github.com/latestaiagents/agent-skills/tree/main/plugins/rag-architect/skills/chunking-strategies

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts