> ## 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. # Preview datasource chunks > Parses an uploaded file and returns the chunks it would produce for the given chunking options without creating a datasource. **Related guide**: Knowledge bases guide. See the [Knowledge bases guide](/docs/ai-studio/ai-engineering/knowledge-bases) for a walkthrough with examples. ## OpenAPI ````yaml post /v2/knowledge/{knowledge_id}/datasources/preview-chunks 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 a user-session onboarding RPC; 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 (ADR 0004). One request shape, one filter dialect, and one response shape per source, validated by a per-source registry. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/knowledge/{knowledge_id}/datasources/preview-chunks: post: tags: - Knowledge Bases summary: Preview datasource chunks description: >- Parses an uploaded file and returns the chunks it would produce for the given chunking options without creating a datasource. operationId: PreviewDatasourceChunks parameters: - name: knowledge_id in: path required: true schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/DatasourcesServicePreviewChunksRequest' required: true responses: '200': description: Datasource chunk preview successfully generated content: application/json: schema: $ref: '#/components/schemas/DatasourcesServicePreviewChunksResponse' components: schemas: DatasourcesServicePreviewChunksRequest: required: - file_id type: object properties: file_id: type: string chunking_options: $ref: '#/components/schemas/DatasourceChunkingOptions' DatasourcesServicePreviewChunksResponse: required: - chunks - metadata type: object properties: chunks: type: array items: $ref: '#/components/schemas/PreviewChunk' metadata: $ref: '#/components/schemas/PreviewChunksMetadata' DatasourceChunkingOptions: type: object properties: chunking_configuration: $ref: '#/components/schemas/ChunkingConfiguration' chunking_cleanup_options: $ref: '#/components/schemas/ChunkingCleanupOptions' PreviewChunk: required: - text type: object properties: text: type: string page_number: type: integer format: uint32 PreviewChunksMetadata: required: - words_count - sentences_count - paragraphs_count - tokens_count - characters_count - chunks_count type: object properties: words_count: type: integer format: uint32 sentences_count: type: integer format: uint32 paragraphs_count: type: integer format: uint32 tokens_count: type: integer format: uint32 characters_count: type: integer format: uint32 chunks_count: type: integer format: uint32 ChunkingConfiguration: description: >- The chunking configuration settings for the datasource. Defaults to the system's standard chunking configuration if not specified. oneOf: - type: object properties: type: type: string enum: - default required: - type description: >- Optimized chunking strategy focusing on speed and avoiding duplication of content chunks. Deprecated: use one of the named chunking strategies instead. deprecated: true - type: object properties: type: type: string enum: - advanced chunk_max_characters: type: number default: 500 description: >- Defines the absolute maximum character length per chunk. Text elements exceeding this size will be automatically split into multiple chunks. chunk_overlap: type: number default: 0 description: >- Specifies the number of characters to overlap between consecutive chunks. This overlap helps maintain semantic continuity when splitting large text elements. required: - type description: >- Provides advanced settings for customizing chunking behavior, enabling fine-grained control to better meet specific data processing needs. Deprecated: use one of the named chunking strategies instead. deprecated: true - type: object properties: type: type: string enum: - token chunk_size: type: integer default: 512 description: Maximum number of tokens per chunk. chunk_overlap: type: integer default: 0 description: >- Number of tokens to overlap between consecutive chunks. Helps preserve continuity across chunk boundaries. required: - type description: >- Splits text into fixed-size token windows with optional overlap. Predictable chunk sizes, no regard for sentence or paragraph boundaries. - type: object properties: type: type: string enum: - sentence chunk_size: type: integer default: 512 description: Maximum number of tokens per chunk. chunk_overlap: type: integer default: 0 description: >- Number of tokens to overlap between consecutive chunks. Helps preserve continuity across chunk boundaries. min_sentences_per_chunk: type: integer default: 1 description: Minimum number of sentences each chunk must contain. required: - type description: >- Groups whole sentences up to the chunk size, so chunks never cut a sentence in half. - type: object properties: type: type: string enum: - recursive chunk_size: type: integer default: 512 description: Maximum number of tokens per chunk. separators: type: array items: type: string description: >- Separator hierarchy to split on, tried in order. Defaults to paragraph, line, space, then character. min_characters_per_chunk: type: integer default: 24 description: Minimum number of characters each chunk must contain. required: - type description: >- Splits on a separator hierarchy, falling back through paragraph, line, sentence, and word boundaries until chunks fit. Respects document structure. - type: object properties: type: type: string enum: - fast target_size: type: integer default: 4096 description: Target chunk size in bytes. delimiters: type: string default: |- .? description: Single-byte characters to split on. pattern: type: string description: >- Multi-byte split pattern. Takes precedence over delimiters when set. prefix: type: boolean default: false description: >- Attach the delimiter to the start of the next chunk instead of the end of the previous one. consecutive: type: boolean default: false description: >- Split at the start of a run of consecutive delimiters rather than at each one. forward_fallback: type: boolean default: false description: >- Search forward for a delimiter when searching backward finds none. required: - type description: >- Splits on delimiters or a regular expression without tokenizing. Fastest option; chunk sizes vary with where delimiters fall. - type: object properties: type: type: string enum: - semantic chunk_size: type: integer default: 512 description: Maximum number of tokens per chunk. embedding_model: type: string description: Embedding model used to detect semantic boundaries. dimensions: type: integer description: >- Number of dimensions for the embedding output, when the model supports it. threshold: type: string default: auto description: Similarity threshold from 0 through 1, or "auto". mode: type: string default: window enum: - window - sentence description: Comparison mode. similarity_window: type: integer default: 1 description: Window size for similarity comparison. required: - type description: >- Embeds the text and breaks where meaning shifts, so related passages stay together. Makes paid embedding calls. - type: object properties: type: type: string enum: - late chunk_size: type: integer default: 512 description: Maximum number of tokens per chunk. separators: type: array items: type: string description: >- Separator hierarchy to split on, tried in order. Defaults to paragraph, line, space, then character. min_characters_per_chunk: type: integer default: 24 description: Minimum number of characters each chunk must contain. embedding_model: type: string description: Embedding model used to embed the document before it is split. dimensions: type: integer description: >- Number of dimensions for the embedding output, when the model supports it. required: - type description: >- Embeds the document before splitting it recursively, so each chunk is embedded with the surrounding document in context. Makes paid embedding calls. - type: object properties: type: type: string enum: - agentic chunk_size: type: integer default: 1024 description: Maximum number of tokens per chunk. model: type: string default: openai/gpt-4o description: Model that chooses the chunk boundaries. candidate_size: type: integer default: 128 description: Size of candidate splits offered to the model. min_characters_per_chunk: type: integer default: 24 description: Minimum number of characters each chunk must contain. system_prompt: type: string description: Custom system prompt for the boundary model. required: - type description: >- Asks a model to choose the boundaries. Slowest and most expensive, best on documents with irregular structure. Makes paid model calls. ChunkingCleanupOptions: type: object properties: delete_emails: type: boolean delete_credit_cards: type: boolean delete_phone_numbers: type: boolean clean_bullet_points: type: boolean clean_numbered_list: type: boolean clean_unicode: type: boolean clean_dashes: type: boolean clean_whitespaces: type: boolean securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````