# Datalab Documentation ## Docs - [[DEPRECATED] Marker](https://documentation.datalab.to/api-reference/[deprecated]-marker.md): **DEPRECATED**: Use the new endpoints instead: - `/convert` for document conversion - `/extract` for structured data extraction - `/segment` for document segmentation - `/custom-pipeline` for custom pipeline execution - [[DEPRECATED] OCR](https://documentation.datalab.to/api-reference/[deprecated]-ocr.md): [DEPRECATED] This endpoint is deprecated and will be removed in the future. This endpoint is used to submit a PDF or image for OCR. The OCR text lines will be returned, along with their bbox and polygon coordinates. - [[DEPRECATED] Table Recognition](https://documentation.datalab.to/api-reference/[deprecated]-table-recognition.md): [DEPRECATED] This endpoint is deprecated and will be removed in the future. This endpoint is used to submit a request for table recognition. The detected tables will be returned, as well as their parsed structure. - [Api Health](https://documentation.datalab.to/api-reference/api-health.md): This endpoint is used to check the health of the API, given an API key. - [Add Files To Collection](https://documentation.datalab.to/api-reference/collections/add-files-to-collection.md): Link existing uploaded files to a collection. - [Create Collection](https://documentation.datalab.to/api-reference/collections/create-collection.md): Create a new collection. - [Delete Collection](https://documentation.datalab.to/api-reference/collections/delete-collection.md): Soft-delete (archive) collection. - [Get Batch Run](https://documentation.datalab.to/api-reference/collections/get-batch-run.md): Get batch run status and progress. - [Get Batch Run Results](https://documentation.datalab.to/api-reference/collections/get-batch-run-results.md): Get per-file results for a batch run. - [Get Collection](https://documentation.datalab.to/api-reference/collections/get-collection.md): Get collection with file list. - [List Batch Runs](https://documentation.datalab.to/api-reference/collections/list-batch-runs.md): List batch runs for the team, optionally filtered by collection, eval rubric, and/or pipeline. - [List Collections](https://documentation.datalab.to/api-reference/collections/list-collections.md): List collections for the team. - [Remove File From Collection](https://documentation.datalab.to/api-reference/collections/remove-file-from-collection.md): Unlink a file from a collection (does NOT delete the uploaded file). - [Start Batch Run](https://documentation.datalab.to/api-reference/collections/start-batch-run.md): Start a batch evaluation run on all files in the collection. - [Update Collection](https://documentation.datalab.to/api-reference/collections/update-collection.md): Update collection name/description. - [Convert Document](https://documentation.datalab.to/api-reference/convert-document.md): Convert a PDF, image, or document to markdown, HTML, JSON, or chunks. Use save_checkpoint=true to save parsed state for later /extract or /segment calls. - [Convert Result Check](https://documentation.datalab.to/api-reference/convert-result-check.md): Poll this endpoint to check the status of a Convert request and retrieve the converted document. - [Create Document](https://documentation.datalab.to/api-reference/create-document.md): Create a DOCX document from markdown with track changes support. Supports , , and tags. - [Create Document Result Check](https://documentation.datalab.to/api-reference/create-document-result-check.md): Poll this endpoint to check status of a Create Document request and retrieve the generated document - [Create Workflow](https://documentation.datalab.to/api-reference/create-workflow.md): Create a new workflow definition. - [Archive Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/archive-custom-pipeline.md): Archive a custom processor (soft-delete). Available to any team member with pipeline access. - [Check Pipeline Access](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/check-pipeline-access.md): Check if the current user's team has access to custom processors. Intentionally not gated by ensure_pipeline_access so the frontend can determine access status. - [Delete Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/delete-custom-pipeline.md): Permanently delete a custom processor and all its versions. Admin-only. - [Describe Customizer](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/describe-customizer.md): Conversational endpoint for building a custom processor description. Accepts the chat history, returns the next assistant message. When the system has enough context, includes a proposed_description. - [Export Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/export-custom-pipeline.md): Export a custom processor with all versions. Admin-only. - [Get Custom Pipeline Status](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/get-custom-pipeline-status.md): Check the status of a custom processor generation request using the request_check_url from the initial submission. - [Get Pipeline Eval Definition](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/get-pipeline-eval-definition.md): Get the eval_definition from a custom processor's active version. - [Get Pipelines Using Processor](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/get-pipelines-using-processor.md): List pipelines (from the Pipeline table) that reference this custom processor in their steps JSON. - [Get Processor Version Detail](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/get-processor-version-detail.md): Get detailed data for a specific processor version, including pipeline_params and eval_definition. - [Iterate Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/iterate-custom-pipeline.md): Iterate on an existing custom processor. - [List Custom Pipelines](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/list-custom-pipelines.md): List all custom processors for a team. Returns processors ordered by creation date (newest first). - [List Pipeline Versions](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/list-pipeline-versions.md): List all versions of a custom processor, ordered by version descending. - [Restore Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/restore-custom-pipeline.md): Restore an archived custom processor. Admin-only. - [Seed Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/seed-custom-pipeline.md): Directly create a completed custom processor from JSON. Admin-only. - [Set Active Pipeline Version](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/set-active-pipeline-version.md): Set the active version of a custom processor. Changes the active_version pointer to any existing version. - [Submit Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/submit-custom-pipeline.md): Submit a custom processor generation request. - [Transfer Custom Pipeline](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/transfer-custom-pipeline.md): Transfer a custom processor to another team. This endpoint allows admins to transfer ownership of a custom processor from one team to another. This is useful for: 1. Beta testing: Create and test processors internally, then transfer to customers 2. Sharing: Move successful processor configurations b… - [Update Pipeline Eval Definition](https://documentation.datalab.to/api-reference/custom-pipelines-deprecated/update-pipeline-eval-definition.md): Update the eval_definition on a custom processor's active version. - [Custom Processor Result Check](https://documentation.datalab.to/api-reference/custom-processor-result-check.md): Poll this endpoint to check the status of a Custom Processor request and retrieve the results. - [Archive Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/archive-custom-pipeline.md): Archive a custom processor (soft-delete). Available to any team member with pipeline access. - [Check Pipeline Access](https://documentation.datalab.to/api-reference/custom-processors/check-pipeline-access.md): Check if the current user's team has access to custom processors. Intentionally not gated by ensure_pipeline_access so the frontend can determine access status. - [Delete Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/delete-custom-pipeline.md): Permanently delete a custom processor and all its versions. Admin-only. - [Describe Customizer](https://documentation.datalab.to/api-reference/custom-processors/describe-customizer.md): Conversational endpoint for building a custom processor description. Accepts the chat history, returns the next assistant message. When the system has enough context, includes a proposed_description. - [Export Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/export-custom-pipeline.md): Export a custom processor with all versions. Admin-only. - [Get Custom Pipeline Status](https://documentation.datalab.to/api-reference/custom-processors/get-custom-pipeline-status.md): Check the status of a custom processor generation request using the request_check_url from the initial submission. - [Get Pipeline Eval Definition](https://documentation.datalab.to/api-reference/custom-processors/get-pipeline-eval-definition.md): Get the eval_definition from a custom processor's active version. - [Get Pipelines Using Processor](https://documentation.datalab.to/api-reference/custom-processors/get-pipelines-using-processor.md): List pipelines (from the Pipeline table) that reference this custom processor in their steps JSON. - [Get Processor Version Detail](https://documentation.datalab.to/api-reference/custom-processors/get-processor-version-detail.md): Get detailed data for a specific processor version, including pipeline_params and eval_definition. - [Iterate Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/iterate-custom-pipeline.md): Iterate on an existing custom processor. - [List Custom Pipelines](https://documentation.datalab.to/api-reference/custom-processors/list-custom-pipelines.md): List all custom processors for a team. Returns processors ordered by creation date (newest first). - [List Pipeline Versions](https://documentation.datalab.to/api-reference/custom-processors/list-pipeline-versions.md): List all versions of a custom processor, ordered by version descending. - [Restore Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/restore-custom-pipeline.md): Restore an archived custom processor. Admin-only. - [Seed Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/seed-custom-pipeline.md): Directly create a completed custom processor from JSON. Admin-only. - [Set Active Pipeline Version](https://documentation.datalab.to/api-reference/custom-processors/set-active-pipeline-version.md): Set the active version of a custom processor. Changes the active_version pointer to any existing version. - [Submit Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/submit-custom-pipeline.md): Submit a custom processor generation request. - [Transfer Custom Pipeline](https://documentation.datalab.to/api-reference/custom-processors/transfer-custom-pipeline.md): Transfer a custom processor to another team. This endpoint allows admins to transfer ownership of a custom processor from one team to another. This is useful for: 1. Beta testing: Create and test processors internally, then transfer to customers 2. Sharing: Move successful processor configurations b… - [Update Pipeline Eval Definition](https://documentation.datalab.to/api-reference/custom-processors/update-pipeline-eval-definition.md): Update the eval_definition on a custom processor's active version. - [Delete Workflow](https://documentation.datalab.to/api-reference/delete-workflow.md): Delete a workflow definition. - [Create Eval Rubric](https://documentation.datalab.to/api-reference/eval_rubrics/create-eval-rubric.md): Create new eval rubric for the team. - [Create From Feedback](https://documentation.datalab.to/api-reference/eval_rubrics/create-from-feedback.md): Convert user feedback items into structured eval rubric using LLM rewrite. - [Delete Eval Rubric](https://documentation.datalab.to/api-reference/eval_rubrics/delete-eval-rubric.md): Soft-delete (archive) eval rubric. - [Generate From Feedback](https://documentation.datalab.to/api-reference/eval_rubrics/generate-from-feedback.md): Generate eval rubric from feedback items using LLM rewrite (no DB save). - [Get Eval Rubric](https://documentation.datalab.to/api-reference/eval_rubrics/get-eval-rubric.md): Get eval rubric by ID. - [Import From Pipeline](https://documentation.datalab.to/api-reference/eval_rubrics/import-from-pipeline.md): Import eval_definition from a custom pipeline's active version. - [List Eval Rubrics](https://documentation.datalab.to/api-reference/eval_rubrics/list-eval-rubrics.md): List eval rubrics for the team. - [Update Eval Rubric](https://documentation.datalab.to/api-reference/eval_rubrics/update-eval-rubric.md): Update eval rubric. - [Execute Workflow](https://documentation.datalab.to/api-reference/execute-workflow.md): Execute a workflow definition. - [Extract Result Check](https://documentation.datalab.to/api-reference/extract-result-check.md): Poll this endpoint to check the status of an Extract request and retrieve the extracted structured data. - [Extract Structured Data](https://documentation.datalab.to/api-reference/extract-structured-data.md): Extract structured data from a document using a JSON schema. Provide a file for end-to-end processing, or a checkpoint_id from a previous /convert call to skip re-parsing. - [Extraction Schema Generation Result Check](https://documentation.datalab.to/api-reference/extraction-schema-generation-result-check.md): Poll this endpoint to check status of an Extraction Schema Generation request and retrieve final results - [Create Extraction Schema](https://documentation.datalab.to/api-reference/extraction_schemas/create-extraction-schema.md): Create a new extraction schema for the team. - [Delete Extraction Schema](https://documentation.datalab.to/api-reference/extraction_schemas/delete-extraction-schema.md): Soft-delete (archive) extraction schema. - [Get Extraction Schema](https://documentation.datalab.to/api-reference/extraction_schemas/get-extraction-schema.md): Get extraction schema by ID. - [List Extraction Schemas](https://documentation.datalab.to/api-reference/extraction_schemas/list-extraction-schemas.md): List extraction schemas for the team. - [Update Extraction Schema](https://documentation.datalab.to/api-reference/extraction_schemas/update-extraction-schema.md): Update extraction schema. Optionally create a new version. - [Confirm Upload](https://documentation.datalab.to/api-reference/files/confirm-upload.md): Confirm that a file was successfully uploaded to R2. - [Delete File](https://documentation.datalab.to/api-reference/files/delete-file.md): Delete an uploaded file. - [Get File Download Url](https://documentation.datalab.to/api-reference/files/get-file-download-url.md): Generate presigned URL for downloading a file. - [Get File Metadata](https://documentation.datalab.to/api-reference/files/get-file-metadata.md): Get metadata for an uploaded file. - [List Files](https://documentation.datalab.to/api-reference/files/list-files.md): List all uploaded files for the team. - [Request Upload Url](https://documentation.datalab.to/api-reference/files/request-upload-url.md): Request a presigned upload URL for direct client-side upload to R2. - [Form Filling](https://documentation.datalab.to/api-reference/form-filling.md): Fill PDF or image forms with provided field data. Supports PDFs with and without native form fields. - [Form Filling Result Check](https://documentation.datalab.to/api-reference/form-filling-result-check.md): Poll this endpoint to check status of a Form Filling request and retrieve the filled form - [Generate Extraction Schemas](https://documentation.datalab.to/api-reference/generate-extraction-schemas.md): For a given file, generate potential extraction schemas. - [Get Execution Status](https://documentation.datalab.to/api-reference/get-execution-status.md): Get the status and results of a workflow execution. - [Get Workflow](https://documentation.datalab.to/api-reference/get-workflow.md): Get workflow definition with all steps. - [Health](https://documentation.datalab.to/api-reference/health.md): This endpoint is used to check the health of the API. Returns a JSON object with the key "status" set to "ok". - [List Step Types](https://documentation.datalab.to/api-reference/list-step-types.md): List all available step types that can be used in workflows. - [List Workflows](https://documentation.datalab.to/api-reference/list-workflows.md): List all workflow definitions with their steps. - [Marker Result Check](https://documentation.datalab.to/api-reference/marker-result-check.md): Poll this endpoint to check status of Marker request and retrieve final results - [OCR Result Check](https://documentation.datalab.to/api-reference/ocr-result-check.md): Poll this endpoint to check status of an OCR request and retrieve final results - [Add Template Examples](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/add-template-examples.md): Upload example files for a template. Admin-only. - [Clone Template](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/clone-template.md): Clone a template to the user's team as a new custom processor. - [Download Template Example](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/download-template-example.md): Fetch example file from R2 and return content directly. - [Download Template Example Thumbnail](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/download-template-example-thumbnail.md): Stream thumbnail image for an example file. - [Get Template](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/get-template.md): Get detailed info for a pipeline template. - [List Templates](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/list-templates.md): List all published pipeline templates. - [Promote To Template](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/promote-to-template.md): Create a template by copying an existing completed processor. Admin-only. - [Remove Template](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/remove-template.md): Un-template a pipeline (sets is_template=False). Admin-only. - [Remove Template Example](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/remove-template-example.md): Remove an example file from a template. Admin-only. - [Update Template](https://documentation.datalab.to/api-reference/pipeline-templates-deprecated/update-template.md): Update template metadata. Admin-only. - [Archive Pipeline](https://documentation.datalab.to/api-reference/pipelines/archive-pipeline.md): Archive a pipeline, hiding it from the default list. - [Create Pipeline](https://documentation.datalab.to/api-reference/pipelines/create-pipeline.md): Create a new pipeline for the team. - [Create Pipeline Version](https://documentation.datalab.to/api-reference/pipelines/create-pipeline-version.md): Create a new version snapshot of the pipeline's current steps. - [Discard Draft](https://documentation.datalab.to/api-reference/pipelines/discard-draft.md): Discard draft changes and reset Pipeline.steps to a published version's steps. - [Get Pipeline](https://documentation.datalab.to/api-reference/pipelines/get-pipeline.md): Get pipeline by pipeline_id. - [Get Pipeline Execution](https://documentation.datalab.to/api-reference/pipelines/get-pipeline-execution.md): Poll execution status. Returns per-step status with lookup keys for partial results. - [Get Pipeline Rate](https://documentation.datalab.to/api-reference/pipelines/get-pipeline-rate.md): Get the per-page rate for a pipeline based on its configuration and the caller's plan. - [Get Step Result](https://documentation.datalab.to/api-reference/pipelines/get-step-result.md): Fetch intermediate result for a specific pipeline execution step. - [List Pipeline Executions](https://documentation.datalab.to/api-reference/pipelines/list-pipeline-executions.md): List recent executions for a pipeline. - [List Pipeline Versions](https://documentation.datalab.to/api-reference/pipelines/list-pipeline-versions.md): List all versions of a pipeline, newest first. - [List Pipelines](https://documentation.datalab.to/api-reference/pipelines/list-pipelines.md): List pipelines for the team. - [Run Pipeline](https://documentation.datalab.to/api-reference/pipelines/run-pipeline.md): Execute a pipeline on a file, creating an execution DAG with per-step tracking and billing. - [Save Pipeline](https://documentation.datalab.to/api-reference/pipelines/save-pipeline.md): Name and promote a pipeline to saved status. - [Unarchive Pipeline](https://documentation.datalab.to/api-reference/pipelines/unarchive-pipeline.md): Unarchive a pipeline, restoring it to the default list. - [Update Pipeline](https://documentation.datalab.to/api-reference/pipelines/update-pipeline.md): Update pipeline steps. This is the auto-save path. - [Add Template Examples](https://documentation.datalab.to/api-reference/processor-templates/add-template-examples.md): Upload example files for a template. Admin-only. - [Clone Template](https://documentation.datalab.to/api-reference/processor-templates/clone-template.md): Clone a template to the user's team as a new custom processor. - [Download Template Example](https://documentation.datalab.to/api-reference/processor-templates/download-template-example.md): Fetch example file from R2 and return content directly. - [Download Template Example Thumbnail](https://documentation.datalab.to/api-reference/processor-templates/download-template-example-thumbnail.md): Stream thumbnail image for an example file. - [Get Template](https://documentation.datalab.to/api-reference/processor-templates/get-template.md): Get detailed info for a pipeline template. - [List Templates](https://documentation.datalab.to/api-reference/processor-templates/list-templates.md): List all published pipeline templates. - [Promote To Template](https://documentation.datalab.to/api-reference/processor-templates/promote-to-template.md): Create a template by copying an existing completed processor. Admin-only. - [Remove Template](https://documentation.datalab.to/api-reference/processor-templates/remove-template.md): Un-template a pipeline (sets is_template=False). Admin-only. - [Remove Template Example](https://documentation.datalab.to/api-reference/processor-templates/remove-template-example.md): Remove an example file from a template. Admin-only. - [Update Template](https://documentation.datalab.to/api-reference/processor-templates/update-template.md): Update template metadata. Admin-only. - [Run Custom Pipeline](https://documentation.datalab.to/api-reference/run-custom-pipeline.md): Execute a custom pipeline configuration. The pipeline_id must reference a completed custom pipeline ID or a template ID. - [Run Custom Processor](https://documentation.datalab.to/api-reference/run-custom-processor.md): Execute a custom processor configuration. The pipeline_id must reference a completed custom processor ID or a template ID. - [Segment Document](https://documentation.datalab.to/api-reference/segment-document.md): Segment a document into sections using a schema. Returns page ranges for each identified segment. Provide a file for end-to-end processing, or a checkpoint_id from a previous /convert call. - [Segment Result Check](https://documentation.datalab.to/api-reference/segment-result-check.md): Poll this endpoint to check the status of a Segment request and retrieve the segmentation results. - [Table Rec Result Check](https://documentation.datalab.to/api-reference/table-rec-result-check.md): Poll this endpoint to check status of Table Rec request and retrieve final results - [Thumbnails](https://documentation.datalab.to/api-reference/thumbnails.md) - [Track Changes](https://documentation.datalab.to/api-reference/track-changes.md): Extract and display tracked changes from DOCX documents. Returns markdown, HTML, and/or chunks with change annotations. - [Track Changes Result Check](https://documentation.datalab.to/api-reference/track-changes-result-check.md): Poll this endpoint to check the status of a Track Changes request and retrieve the results. - [API Limits & Rate Limiting](https://documentation.datalab.to/docs/common/limits.md) - [Supported File Types](https://documentation.datalab.to/docs/common/supportedfiletypes.md) - [API](https://documentation.datalab.to/docs/on-prem/api.md): Our on-prem container's API mimics Datalab's API. - [Overview](https://documentation.datalab.to/docs/on-prem/overview.md): Run inference on your own infrastructure - [Running the Container](https://documentation.datalab.to/docs/on-prem/running-the-container.md): Getting our container up-and-running takes minutes. - [Usage Analytics](https://documentation.datalab.to/docs/on-prem/usage-analytics.md): Monitor inference request analytics and performance metrics in your on-prem deployment. - [Batch Processing](https://documentation.datalab.to/docs/recipes/conversion/batch-documents.md): Convert multiple documents efficiently with parallel processing. - [Document Conversion](https://documentation.datalab.to/docs/recipes/conversion/conversion-api-overview.md): Convert documents to Markdown, HTML, JSON, or chunks using the Convert API. - [Create Document](https://documentation.datalab.to/docs/recipes/create-document/create-document-api-overview.md): Generate DOCX files from markdown with track changes support. - [Document Segmentation](https://documentation.datalab.to/docs/recipes/document-segmentation/auto-segmentation.md): Automatically split multi-document PDFs into separate segments. - [Track Changes in Word Docs](https://documentation.datalab.to/docs/recipes/extract-redlines-and-comments/track-changes-from-word-documents.md): Pull tracked changes and comments from Word documents for review workflows - [File Upload](https://documentation.datalab.to/docs/recipes/file-management/file-upload-api.md): Upload and manage files for use in pipelines and document processing. - [Forge Evals](https://documentation.datalab.to/docs/recipes/forge-evals/overview.md): Compare parsing configurations across multiple documents to find the best settings for your use case - [Form Filling](https://documentation.datalab.to/docs/recipes/form-filling/form-filling-api-overview.md): Automatically fill PDF and image forms with structured data. - [Recipes Overview](https://documentation.datalab.to/docs/recipes/overview.md): End-to-end guides for common document processing workflows. - [Create a Pipeline](https://documentation.datalab.to/docs/recipes/pipelines/create-pipeline.md): Build pipelines using Forge or the SDK to chain document processors. - [Custom Processors](https://documentation.datalab.to/docs/recipes/pipelines/custom-processors.md): Fine-tune document conversion output with AI-generated custom processors. - [Pipelines](https://documentation.datalab.to/docs/recipes/pipelines/pipeline-overview.md): Build versioned document processing pipelines by chaining processors together. - [Pipeline Versioning](https://documentation.datalab.to/docs/recipes/pipelines/pipeline-versioning.md): Manage pipeline drafts, publish immutable versions, and pin production deployments. - [Run a Pipeline](https://documentation.datalab.to/docs/recipes/pipelines/run-pipeline.md): Execute pipelines with version selection, overrides, polling, and per-processor result retrieval. - [Structured Extraction](https://documentation.datalab.to/docs/recipes/structured-extraction/api-overview.md): Extract structured data from documents using JSON schemas. - [Extraction Confidence Scoring](https://documentation.datalab.to/docs/recipes/structured-extraction/confidence-scoring.md): Score extraction results with per-field confidence ratings and reasoning. - [Handling Long Documents](https://documentation.datalab.to/docs/recipes/structured-extraction/handling-long-documents.md): Tips for structured extraction on documents with 50+ pages. - [Saved Schemas](https://documentation.datalab.to/docs/recipes/structured-extraction/saved-schemas.md): Create and manage reusable extraction schemas in the Datalab UI. Reference saved schemas by ID instead of sending the full schema with every request. - [Table Recognition](https://documentation.datalab.to/docs/recipes/table-recognition/table-rec-api-overview.md): Extract tables from documents. - [API Overview](https://documentation.datalab.to/docs/welcome/api.md): REST API reference for document conversion, form filling, and file management. - [Quickstart](https://documentation.datalab.to/docs/welcome/quickstart.md): Get started with Datalab to convert PDFs, images, and documents into Markdown, HTML, or JSON in minutes. - [Python SDK](https://documentation.datalab.to/docs/welcome/sdk.md): The Datalab Python SDK provides a simple interface for document conversion, pipelines, structured extraction, form filling, and file management. - [Command Line Interface](https://documentation.datalab.to/docs/welcome/sdk/cli.md): Use the Datalab CLI to convert documents from the command line. - [Document Conversion](https://documentation.datalab.to/docs/welcome/sdk/conversion.md): Convert PDFs, images, and documents to Markdown, HTML, JSON, or chunks using the Datalab SDK. - [Structured Extraction](https://documentation.datalab.to/docs/welcome/sdk/extraction.md): Extract structured data from documents using JSON schemas with the Datalab SDK. - [File Management](https://documentation.datalab.to/docs/welcome/sdk/file-management.md): Upload, list, and manage files in Datalab storage using the SDK. - [Form Filling](https://documentation.datalab.to/docs/welcome/sdk/form-filling.md): Fill PDF and image forms with structured field data using the Datalab SDK. - [Pipelines](https://documentation.datalab.to/docs/welcome/sdk/pipelines.md): Create, version, and run document processing pipelines using the Datalab SDK. - [Document Segmentation](https://documentation.datalab.to/docs/welcome/sdk/segmentation.md): Segment documents into logical sections using the Datalab SDK. - [Welcome to Datalab](https://documentation.datalab.to/index.md) - [Billing](https://documentation.datalab.to/platform/billing.md) - [Changelog](https://documentation.datalab.to/platform/changelog.md): Major changes to the Datalab hosted service are listed here. - [Error Codes](https://documentation.datalab.to/platform/errors.md): HTTP error codes, response formats, and retry guidance. - [Migration Guide](https://documentation.datalab.to/platform/migration.md): Migrate from deprecated endpoints to the current API. - [Security Best Practices](https://documentation.datalab.to/platform/security.md): Keep your Datalab integration secure with these best practices. - [Troubleshooting](https://documentation.datalab.to/platform/troubleshooting.md): Common issues and solutions when using the Datalab API. - [Version Policies](https://documentation.datalab.to/platform/versioning.md) - [Webhooks](https://documentation.datalab.to/platform/webhooks.md) ## OpenAPI Specs - [openapi](https://documentation.datalab.to/api-reference/openapi.json) ## Optional - [Try Datalab for Free](https://www.datalab.to/auth/sign_up) - [Blog](https://www.datalab.to/blog) - [API Reference](https://documentation.datalab.to/api-reference/health)