--- title: "List Tasks" method: GET path: "/tasks" tags: ["Tasks"] --- # List Tasks `GET /tasks` Lists tasks for the authenticated user with cursor-based pagination and optional filtering by date range. Supports ascending or descending sort order and optional inclusion of chunks/base64 URLs. ## Query parameters - `base64_urls` boolean - `end` string, date-time - `include_chunks` boolean - `limit` integer - `cursor` string, date-time - `start` string, date-time - `sort` 'asc' | 'desc' - `task_types` TaskType[] - `statuses` Status[] ## Response `200` Paginated list of tasks - TasksResponse - `has_more` boolean, required - `next_cursor` string, date-time, nullable - `tasks` TaskResponse[], required - `completed` boolean, required — True when the task reaches a terminal state i.e. `status` is `Succeeded` or `Failed` or `Cancelled` - `configuration` union, required — Unified configuration type that can represent either parse or extract configurations - ParseConfiguration - `chunk_processing` ChunkProcessing — Controls the setting for the chunking and post-processing of each chunk. - `ignore_headers_and_footers` boolean, nullable — DEPRECATED: use `segment_processing.ignore` instead - `target_length` integer — The target number of words in each chunk. If 0, each chunk will contain a single segment. - `tokenizer` union — Specifies which tokenizer to use for the chunking process. This type supports two ways of specifying a tokenizer: 1. Using a predefined tokenizer from the `Tokenizer` enum 2. Using any Hugging Face tokenizer by providing its model ID as a string (e.g. "facebook/bart-large", "Qwen/Qwen-tokenizer", etc.) When using a string, any valid Hugging Face tokenizer ID can be specified, which will be loaded using the Hugging Face tokenizers library. - object — Use one of the predefined tokenizer types - … - object — Use any Hugging Face tokenizer by specifying its model ID Examples: "Qwen/Qwen-tokenizer", "facebook/bart-large" - … - `error_handling` 'Fail' | 'Continue' — Controls how errors are handled during processing: - `Fail`: Stops processing and fails the task when any error occurs - `Continue`: Attempts to continue processing despite non-critical errors (eg. LLM refusals etc.) - `ocr_strategy` 'All' | 'Auto' — Controls the Optical Character Recognition (OCR) strategy. - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page) - `Auto`: Selectively applies OCR only to pages with missing or low-quality text. When text layer is present the bounding boxes from the text layer are used. - `pipeline` 'Azure' | 'Chunkr' - `segment_processing` SegmentProcessing — Configuration for how each document segment is processed and formatted. Each segment has sensible defaults, but you can override specific settings: - `format`: Output as `Html` or `Markdown` - `strategy`: `Auto` (rule-based), `LLM` (AI-generated), or `Ignore` (skip) - `crop_image`: Whether to crop images to segment bounds - `extended_context`: Use full page as context for LLM processing - `description`: Generate descriptions for segments **Defaults per segment type:** Check the documentation for more details. Only specify the fields you want to change - everything else uses the defaults. - `Caption` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Footnote` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `FormRegion` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Formula` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `GraphicalItem` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Legend` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `LineNumber` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `ListItem` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Page` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `PageFooter` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `PageHeader` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `PageNumber` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Picture` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Table` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Text` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Title` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `Unknown` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - `crop_image` 'All' | 'Auto' — Controls the cropping strategy for an item (e.g. segment, chunk, etc.) - `All` crops all images in the item - `Auto` crops images only if required for post-processing - `description` boolean, nullable — Generate LLM descriptions for this segment - `extended_context` boolean, nullable — Use the full page image as context for LLM generation - `format` 'Html' | 'Markdown' — The format for the `content` field of a segment. - `llm` string, nullable - `strategy` 'LLM' | 'Auto' | 'Ignore' — The strategy for generating the `content` field of a segment. - `segmentation_strategy` 'LayoutAnalysis' | 'Page' — Controls the segmentation strategy: - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`, `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained segmentation and better chunking. - `Page`: Treats each page as a single segment. Faster processing, but without layout element detection and only simple chunking. - ExtractConfiguration - `parse_configuration` ParseConfiguration - `chunk_processing` ChunkProcessing — Controls the setting for the chunking and post-processing of each chunk. - `ignore_headers_and_footers` boolean, nullable — DEPRECATED: use `segment_processing.ignore` instead - `target_length` integer — The target number of words in each chunk. If 0, each chunk will contain a single segment. - `tokenizer` union — Specifies which tokenizer to use for the chunking process. This type supports two ways of specifying a tokenizer: 1. Using a predefined tokenizer from the `Tokenizer` enum 2. Using any Hugging Face tokenizer by providing its model ID as a string (e.g. "facebook/bart-large", "Qwen/Qwen-tokenizer", etc.) When using a string, any valid Hugging Face tokenizer ID can be specified, which will be loaded using the Hugging Face tokenizers library. - … - `error_handling` 'Fail' | 'Continue' — Controls how errors are handled during processing: - `Fail`: Stops processing and fails the task when any error occurs - `Continue`: Attempts to continue processing despite non-critical errors (eg. LLM refusals etc.) - `ocr_strategy` 'All' | 'Auto' — Controls the Optical Character Recognition (OCR) strategy. - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page) - `Auto`: Selectively applies OCR only to pages with missing or low-quality text. When text layer is present the bounding boxes from the text layer are used. - `pipeline` 'Azure' | 'Chunkr' - `segment_processing` SegmentProcessing — Configuration for how each document segment is processed and formatted. Each segment has sensible defaults, but you can override specific settings: - `format`: Output as `Html` or `Markdown` - `strategy`: `Auto` (rule-based), `LLM` (AI-generated), or `Ignore` (skip) - `crop_image`: Whether to crop images to segment bounds - `extended_context`: Use full page as context for LLM processing - `description`: Generate descriptions for segments **Defaults per segment type:** Check the documentation for more details. Only specify the fields you want to change - everything else uses the defaults. - `Caption` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Footnote` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `FormRegion` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Formula` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `GraphicalItem` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Legend` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `LineNumber` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `ListItem` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Page` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `PageFooter` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `PageHeader` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `PageNumber` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Picture` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Table` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Text` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Title` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `Unknown` GenerationConfig — Controls the processing and generation for the segment. - `crop_image` controls whether to crop the file's images to the segment's bounding box. The cropped image will be stored in the segment's `image` field. Use `All` to always crop, or `Auto` to only crop when needed for post-processing. - `format` specifies the output format: `Html` or `Markdown` - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore` - `Auto`: Process content automatically - `LLM`: Use large language models for processing - `Ignore`: Exclude segments from final output - `description` enables LLM-generated descriptions for segments. **Note:** This uses chunkr's own VLM models and is not configurable via LLM processing configuration. - `extended_context` uses the full page image as context for LLM generation. - … - `segmentation_strategy` 'LayoutAnalysis' | 'Page' — Controls the segmentation strategy: - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`, `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained segmentation and better chunking. - `Page`: Treats each page as a single segment. Faster processing, but without layout element detection and only simple chunking. - `schema` object, required — The schema to be used for the extraction. - `system_prompt` string, nullable — The system prompt to be used for the extraction. - `created_at` string, date-time, required — The date and time when the task was created and queued. - `expires_at` string, date-time, nullable — The date and time when the task will expire. - `file_info` FileInfo, required — Information about the input file. - `mime_type` string, nullable — The MIME type of the file. - `name` string, nullable — The name of the file. - `page_count` integer, nullable — The number of pages in the file. - `ss_cell_count` integer, nullable — The number of cells in the file. Only used for spreadsheets. - `url` string, required — The presigned URL/Base64 encoded URL of the input file. - `finished_at` string, date-time, nullable — The date and time when the task was finished. - `input_file_url` string, nullable — The presigned URL of the input file. Deprecated use `file_info.url` instead. - `message` string, required — A message describing the task's status or any errors that occurred. - `output` union — Unified output type that can represent either parse or extract results - ParseOutputResponse — The processed results of a document parsing task - `chunks` Chunk[], required — Collection of document chunks, where each chunk contains one or more segments - `chunk_id` string — The unique identifier for the chunk. - `chunk_length` integer, required — The total number of tokens in the `embed` field of the chunk. Calculated by the `tokenizer`. - `content` string, nullable — The content of the chunk. This is the text that is generated by combining the `content` field from each segment. Can be used provided as context to the LLM. - `embed` string, nullable — Suggested text to be embedded for the chunk. This text is generated by combining the `embed` field from each segment. - `segments` Segment[], required — Collection of document segments that form this chunk. When `target_chunk_length` > 0, contains the maximum number of segments that fit within that length (segments remain intact). Otherwise, contains exactly one segment. - `bbox` BoundingBox, required — Bounding box for an item. It is used for segments and OCR results. - … - `confidence` number, float, nullable — Confidence score of the layout analysis model - `content` string — Content of the segment, will be either HTML or Markdown, depending on format chosen. - `description` string, nullable — Description of the segment, generated by the LLM. - `embed` string, nullable — Embeddable content of the segment. - `image` string, nullable — Presigned URL to the image of the segment. - `llm` string, nullable — LLM representation of the segment. - `ocr` OCRResult[], nullable — OCR results for the segment. - … - `page_height` number, float, required — Height of the page/sheet containing the segment. - `page_number` integer, required — Page number/Sheet number of the segment. - `page_width` number, float, required — Width of the page/sheet containing the segment. - `segment_id` string, required — Unique identifier for the segment. - `segment_length` integer, nullable — Length of the segment in tokens. - `segment_type` 'Caption' | 'Footnote' | 'Formula' | 'FormRegion' | 'GraphicalItem' | 'Legend' | 'LineNumber' | 'ListItem' | 'Page' | 'PageFooter' | 'PageHeader' | 'PageNumber' | 'Picture' | 'Table' | 'Text' | 'Title' | 'Unknown' | 'SectionHeader', required — All the possible types for a segment. - `ss_cells` Cell[], nullable — Cells of the segment. Only used for Spreadsheets. - … - `ss_header_bbox` BoundingBox — Bounding box for an item. It is used for segments and OCR results. - … - `ss_header_ocr` OCRResult[], nullable — OCR results of the header of the segment, if found. Only used for Spreadsheets. - … - `ss_header_range` string, nullable — Header range of the segment, if found. The header can have overlap with the `segment.range` if the table contains the header, if the header is located in a different sheet, the header range will have no overlap with the `segment.range`. Only used for Spreadsheets. - `ss_header_text` string, nullable — Text content of the header of the segment, if found. Only used for Spreadsheets. - `ss_range` string, nullable — Range of the segment in Excel notation (e.g., A1:B5). Only used for Spreadsheets. - `ss_sheet_name` string, nullable — Name of the sheet containing the segment. Only used for Spreadsheets. - `text` string — Text content of the segment. Calculated by the OCR results. - `file_name` string, nullable — The name of the file. Deprecated use `file_info.name` instead. - `mime_type` string, nullable — The MIME type of the file. Deprecated use `file_info.mime_type` instead. - `page_count` integer, nullable — The number of pages in the file. Deprecated use `file_info.page_count` instead. - `pages` Page[], nullable — The pages of the file. Includes the image and metadata for each page. - `dpi` number, float, nullable — DPI of the page/sheet. All cropped images are scaled to this DPI. - `image` string, required — The presigned URL of the page/sheet image. - `page_height` number, float, required — The number of pages in the file. - `page_number` integer, required — The number of pages in the file. - `page_width` number, float, required — The number of pages in the file. - `ss_sheet_name` string, nullable — The name of the sheet containing the page. Only used for Spreadsheets. - `pdf_url` string, nullable — The presigned URL of the PDF file. - ExtractOutputResponse — The processed results of a document extraction task. Shapes: - `results`: JSON matching the user-provided schema. - `citations`: mirror of `results`; only leaf positions (primitive or array-of-primitives) contain a `Vec` supporting that field. - `metrics`: mirror of `results`; only leaf positions contain a `Metrics` object for that field. - `citations` unknown, required - `metrics` unknown, required - `results` unknown, required - `parse_task_id` string, nullable — The ID of the source `parse` task that was used for the task - `started_at` string, date-time, nullable — The date and time when the task was started. - `status` 'Starting' | 'Processing' | 'Succeeded' | 'Failed' | 'Cancelled', required — The status of the task. - `task_id` string, required — The unique identifier for the task. - `task_type` 'Parse' | 'Extract', required - `task_url` string, nullable — The presigned URL of the task. - `version_info` VersionInfo, required — Version information for the task. - `client_version` union, required — Represents different types of SDK clients and their versions - 'Legacy' — Legacy SDK without version information (< 0.3.3) - object — Version of the current manually-maintained SDK - `ManualSdk` string, required — Version of the current manually-maintained SDK - object — Version of the auto-generated SDK - `GeneratedSdk` string, required — Version of the auto-generated SDK - 'Unspecified' — Unspecified/raw API request without any client version headers - `server_version` string, required — The version of the server. ## Other responses - `401` — Unauthorized - `500` — Server error --- [API](https://skmtc.net/chunkr/apis/chunkr-api.md) · [All operations](https://skmtc.net/chunkr/apis/chunkr-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/chunkr/chunkr-api/versions/cfcf1ff1cbb0/schema)