> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Parse text > Split large text documents into smaller, manageable chunks using different chunking strategies optimized for RAG (Retrieval-Augmented Generation) workflows. This endpoint supports multiple chunking algorithms including token-based, sentence-based, recursive, semantic, and specialized strategies. **Related guide**: Chunking guide. See the [Chunking guide](/ai-studio/ai-engineering/chunking) for a walkthrough with examples. ## OpenAPI ````yaml post /v2/chunking openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://my.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - name: File Systems description: >- Create and manage persistent file systems that agents and MCP clients read from and write to. - name: Knowledge Bases description: Create and manage knowledge bases used by agents and retrieval workflows. - name: Memory Stores description: Create and manage memory stores, memories, and memory documents. - name: Evals description: Run an evaluator against a conversation and its result - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. - description: List models available through the AI Router. name: Models - name: Policies - name: Alerts description: >- Alerts evaluate a Reporting API metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: API keys description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. - name: Audit Logs description: Audit logs record workspace entity changes and access-relevant events. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Hub description: Hub items are reusable templates available to a workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the orq.ai model catalog: every model orq offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Projects description: Projects organize resources within a workspace - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Threads description: Threads group related trace invocations and their aggregate usage - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Webhooks description: >- Create and manage webhooks that deliver workspace events to external HTTPS endpoints. - name: Workspaces description: >- A workspace is the tenant. Create is called from a user session during onboarding; Get, List, and Update are the public management surface. - name: Workspace Security description: >- Workspace-level domain verification and IP allowlist controls. These operations are restricted to workspace administrators. - name: Workspace Settings description: >- Workspace-level settings managed with a workspace credential. A workspace is the tenant, so these settings are a singleton — there is nothing to create or delete, only read and update. - name: Responses - description: Run agents on a cron cadence. Minimum firing interval is 1 hour. name: Agent Schedules - name: Embeddings - name: Telemetry description: >- Unified query envelope for traces, metrics, and logs. One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. - description: Beta. Run typed classification questions against a classify model. name: Classify - description: Search Gateway with managed credits or BYOK. name: Web Search externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/chunking: post: tags: - Chunking summary: Parse text description: >- Split large text documents into smaller, manageable chunks using different chunking strategies optimized for RAG (Retrieval-Augmented Generation) workflows. This endpoint supports multiple chunking algorithms including token-based, sentence-based, recursive, semantic, and specialized strategies. operationId: parse requestBody: content: application/json: schema: oneOf: - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - token title: Token Chunker chunk_size: type: integer exclusiveMinimum: 0 default: 512 description: Maximum tokens per chunk chunk_overlap: type: integer minimum: 0 default: 0 description: Number of tokens to overlap between chunks required: - text - strategy title: Token Chunker Strategy description: >- Splits text based on token count. Best for ensuring chunks fit within LLM context windows and maintaining consistent chunk sizes for embedding models. - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - sentence title: Sentence Chunker chunk_size: type: integer exclusiveMinimum: 0 default: 512 description: Maximum tokens per chunk chunk_overlap: type: integer minimum: 0 default: 0 description: Number of overlapping tokens between chunks min_sentences_per_chunk: type: integer exclusiveMinimum: 0 default: 1 description: Minimum number of sentences per chunk required: - text - strategy title: Sentence Chunker Strategy description: >- Splits text at sentence boundaries while respecting token limits. Ideal for maintaining semantic coherence and readability. - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - recursive title: Recursive Chunker chunk_size: type: integer exclusiveMinimum: 0 default: 512 description: Maximum tokens per chunk separators: type: array items: type: string default: - |+ - |+ - ' ' - '' description: Hierarchy of separators to use for splitting min_characters_per_chunk: type: integer exclusiveMinimum: 0 default: 24 description: Minimum characters allowed per chunk required: - text - strategy title: Recursive Chunker Strategy description: >- Recursively splits text using a hierarchy of separators (paragraphs, sentences, words). Versatile general-purpose chunker that preserves document structure. - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - semantic title: Semantic Chunker chunk_size: type: integer exclusiveMinimum: 0 default: 512 description: Maximum tokens per chunk threshold: anyOf: - type: number minimum: 0 maximum: 1 - type: string enum: - auto default: auto description: >- Similarity threshold for grouping (0-1) or "auto" for automatic detection embedding_model: type: string description: >- Embedding model to use for semantic similarity. [Available embedding models](/ai-gateway/supported-models#embedding-models) dimensions: type: integer exclusiveMinimum: 0 description: >- Number of dimensions for the embedding output. Required for text-embedding-3 models. Supported range: 256-3072 for text-embedding-3-large, 256-1536 for text-embedding-3-small. max_tokens: type: integer exclusiveMinimum: 0 description: >- Maximum number of tokens per embedding request. Default is 8191 for text-embedding-3 models. mode: type: string enum: - window - sentence default: window description: 'Chunking mode: window-based or sentence-based similarity' similarity_window: type: integer exclusiveMinimum: 0 default: 1 description: Window size for similarity comparison required: - text - strategy - embedding_model title: Semantic Chunker Strategy description: >- Groups semantically similar sentences using embeddings. Excellent for maintaining topic coherence and context within chunks. - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - agentic title: Agentic Chunker model: type: string description: >- Model to use for chunking. [Available models](/ai-gateway/supported-models#chat-models) example: openai/gpt-5.6-sol chunk_size: type: integer exclusiveMinimum: 0 default: 1024 description: Maximum tokens per chunk candidate_size: type: integer exclusiveMinimum: 0 default: 128 description: Size of candidate splits for LLM evaluation min_characters_per_chunk: type: integer exclusiveMinimum: 0 default: 24 description: Minimum characters allowed per chunk system_prompt: type: string description: >- Custom system prompt for the agentic chunker LLM. Overrides the default prompt that instructs the model how to identify chunk boundaries. Maximum 20,000 tokens. required: - text - strategy - model title: Agentic Chunker Strategy description: >- Agentic LLM-powered chunker that uses AI to determine optimal split points. Best for complex documents requiring intelligent segmentation. - type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: type: string enum: - fast title: Fast Chunker target_size: type: integer exclusiveMinimum: 0 default: 4096 description: Target chunk size in bytes delimiters: type: string default: |- .? description: >- Single-byte delimiter characters. Each character is treated as a separate delimiter (e.g., ".?!" splits on period, question mark, or exclamation). Use escaped sequences for special chars. pattern: type: string description: >- Multi-byte pattern for splitting (e.g., "▁" for SentencePiece tokenizers). Takes precedence over delimiters if set. prefix: type: boolean default: false description: >- Attach delimiter to start of next chunk instead of end of current chunk consecutive: type: boolean default: false description: >- When true, splits at the START of consecutive delimiter runs, keeping the run with the following chunk (e.g., splits before "\n\n\n" not in the middle) forward_fallback: type: boolean default: false description: >- Search forward if no delimiter found in backward search window required: - text - strategy title: Fast Chunker Strategy description: >- High-performance SIMD-optimized byte-level chunking. Best for large files (>1MB) where speed and memory efficiency are critical. 2x faster and 3x less memory than token-based chunking. - title: Late Chunker Strategy required: - text - strategy - embedding_model type: object properties: text: type: string description: The text content to be chunked metadata: type: boolean default: true description: Whether to include metadata for each chunk return_type: type: string enum: - chunks - texts default: chunks description: >- Return format: chunks (with metadata) or texts (plain strings) strategy: title: Late Chunker enum: - late type: string chunk_size: type: integer exclusiveMinimum: 0 default: 512 description: Maximum tokens per chunk separators: type: array items: type: string default: - |+ - |+ - ' ' - '' description: Hierarchy of separators to use for splitting min_characters_per_chunk: type: integer exclusiveMinimum: 0 default: 24 description: Minimum characters allowed per chunk embedding_model: type: string description: >- Embedding model used to generate context-aware chunk embeddings. [Available embedding models](/ai-gateway/supported-models#embedding-models) dimensions: type: integer exclusiveMinimum: 0 description: >- Number of dimensions for the embedding output. Required for text-embedding-3 models. Supported range: 256-3072 for text-embedding-3-large, 256-1536 for text-embedding-3-small. max_tokens: type: integer exclusiveMinimum: 0 description: >- Maximum number of tokens per embedding request. Default is 8191 for text-embedding-3 models. description: >- Splits text after preserving the full-document context in its embeddings. Best for retrieval workflows where each chunk should retain information from the surrounding document. title: Chunking Request description: >- Request payload for text chunking with strategy-specific configuration example: text: >- The quick brown fox jumps over the lazy dog. This is a sample text that will be chunked into smaller pieces. Each chunk will maintain context while respecting the maximum chunk size. strategy: semantic chunk_size: 256 threshold: 0.8 embedding_model: openai/text-embedding-3-small dimensions: 512 mode: window similarity_window: 1 metadata: true required: true responses: '200': description: Text successfully chunked content: application/json: schema: $ref: '#/components/schemas/ParseResponse' example: chunks: - id: 01HQ3K4M5N6P7Q8R9SATBVCWDX text: The quick brown fox jumps over the lazy dog. index: 0 metadata: start_index: 0 end_index: 44 token_count: 10 - id: 01HQ3K4M5N6P7Q8R9SATBVCWDY text: >- This is a sample text that will be chunked into smaller pieces. index: 1 metadata: start_index: 45 end_index: 108 token_count: 12 x-code-samples: - lang: typescript label: Node.js source: |- import { Orq } from "@orq-ai/node"; const orq = new Orq({ apiKey: process.env["ORQ_API_KEY"] }); const result = await orq.chunking.parse({ text: "Your long text content here...", strategy: "semantic", chunk_size: 256, threshold: 0.8, embedding_model: "openai/text-embedding-3-small", dimensions: 512 }); console.log(result.chunks); - lang: python label: Python source: |- from orq_ai_sdk import Orq orq = Orq(api_key=os.getenv("ORQ_API_KEY")) result = orq.chunking.parse( text="Your long text content here...", strategy="semantic", chunk_size=256, threshold=0.8, embedding_model="openai/text-embedding-3-small", dimensions=512 ) for chunk in result.chunks: print(f"Chunk {chunk.index}: {chunk.text[:50]}...") components: schemas: ParseResponse: required: - chunks type: object properties: chunks: type: array items: $ref: '#/components/schemas/Chunk' Chunk: required: - id - text - index type: object properties: id: type: string text: type: string index: type: integer format: int32 metadata: $ref: '#/components/schemas/ChunkMetadata' ChunkMetadata: required: - start_index - end_index - token_count type: object properties: start_index: type: integer format: int32 end_index: type: integer format: int32 token_count: type: integer format: int32 securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.