# Extract ## Create Extract Job `ExtractV2Job extract().create(ExtractCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/v2/extract` Create an extraction job. Extracts structured data from a document using either a saved configuration or an inline JSON Schema. ## Input Provide exactly one of: - `configuration_id` — reference a saved extraction config - `configuration` — inline configuration with a `data_schema` ## Document input Set `file_input` to a file ID (`dfl-...`) or a completed parse job ID (`pjb-...`). The job runs asynchronously. Poll `GET /extract/{job_id}` or register a webhook to monitor completion. ### Parameters - `ExtractCreateParams params` - `Optional organizationId` - `Optional projectId` - `ExtractV2JobCreate extractV2JobCreate` Request to create an extraction job. Provide configuration_id or inline configuration. ### Returns - `class ExtractV2Job:` An extraction job. - `String id` Unique job identifier (job_id) - `LocalDateTime createdAt` Creation timestamp - `String fileInput` File ID or parse job ID that was extracted - `String projectId` Project this job belongs to - `String status` Current job status. - `PENDING` — queued, not yet started - `RUNNING` — actively processing - `COMPLETED` — finished successfully - `FAILED` — terminated with an error - `CANCELLED` — cancelled by user - `LocalDateTime updatedAt` Last update timestamp - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved extract configuration ID used for this job, if any - `Optional errorMessage` Error details when status is FAILED - `Optional extractMetadata` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document - `Optional extractResult` Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row. - `class UnionMember0:` - `class InnerUnionMember0:` - `List` - `String` - `double` - `boolean` - `List` - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional metadata` Job-level metadata. - `Optional usage` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.extract.ExtractCreateParams; import com.llamacloud_prod.api.models.extract.ExtractV2Job; import com.llamacloud_prod.api.models.extract.ExtractV2JobCreate; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractV2JobCreate params = ExtractV2JobCreate.builder() .fileInput("dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee") .build(); ExtractV2Job extractV2Job = client.extract().create(params); } } ``` #### Response ```json { "id": "ext-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "created_at": "2019-12-27T18:11:19.117Z", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "COMPLETED", "updated_at": "2019-12-27T18:11:19.117Z", "configuration": { "data_schema": { "foo": { "foo": "bar" } }, "cite_sources": true, "confidence_scores": true, "extraction_target": "per_doc", "max_pages": 10, "parse_config_id": "cfg-11111111-2222-3333-4444-555555555555", "parse_tier": "fast", "system_prompt": "Extract all monetary values in USD. If a currency is not specified, assume USD.", "target_pages": "1,3,5-7", "tier": "cost_effective", "version": "latest" }, "configuration_id": "cfg-11111111-2222-3333-4444-555555555555", "error_message": "error_message", "extract_metadata": { "field_metadata": { "document_metadata": { "items": [ { "amount": { "citation": [ { "matching_text": "$10.00", "page": 1 } ], "confidence": 1 }, "description": { "citation": [ { "matching_text": "$10/month", "page": 1 } ], "confidence": 0.998 } } ], "total": { "citation": "bar", "confidence": "bar" }, "vendor": { "citation": "bar", "confidence": "bar", "extraction_confidence": "bar", "parsing_confidence": "bar" } }, "page_metadata": [ { "foo": { "foo": "bar" } } ], "row_metadata": [ { "foo": { "foo": "bar" } } ] }, "parse_job_id": "parse_job_id", "parse_tier": "parse_tier" }, "extract_result": { "foo": { "foo": "bar" } }, "metadata": { "usage": { "num_pages_extracted": 0 } } } ``` ## List Extract Jobs `ExtractListPage extract().list(ExtractListParamsparams = ExtractListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **get** `/api/v2/extract` List extraction jobs with optional filtering and pagination. Filter by `configuration_id`, `status`, `file_input`, or creation date range. Results are returned newest-first. Use `expand=configuration` to include the full configuration used, and `expand=extract_metadata` for per-field metadata. ### Parameters - `ExtractListParams params` - `Optional configurationId` Filter by configuration ID - `Optional createdAtOnOrAfter` Include items created at or after this timestamp (inclusive) - `Optional createdAtOnOrBefore` Include items created at or before this timestamp (inclusive) - `Optional documentInputType` Filter by document input type (file_id or parse_job_id) - `Optional documentInputValue` Deprecated: use file_input instead - `Optional> expand` Additional fields to include: configuration, extract_metadata - `Optional fileInput` Filter by file input value - `Optional> jobIds` Filter by specific job IDs - `Optional organizationId` - `Optional pageSize` Number of items per page - `Optional pageToken` Token for pagination - `Optional projectId` - `Optional status` Filter by status - `PENDING("PENDING")` - `THROTTLED("THROTTLED")` - `RUNNING("RUNNING")` - `COMPLETED("COMPLETED")` - `FAILED("FAILED")` - `CANCELLED("CANCELLED")` ### Returns - `class ExtractV2Job:` An extraction job. - `String id` Unique job identifier (job_id) - `LocalDateTime createdAt` Creation timestamp - `String fileInput` File ID or parse job ID that was extracted - `String projectId` Project this job belongs to - `String status` Current job status. - `PENDING` — queued, not yet started - `RUNNING` — actively processing - `COMPLETED` — finished successfully - `FAILED` — terminated with an error - `CANCELLED` — cancelled by user - `LocalDateTime updatedAt` Last update timestamp - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved extract configuration ID used for this job, if any - `Optional errorMessage` Error details when status is FAILED - `Optional extractMetadata` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document - `Optional extractResult` Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row. - `class UnionMember0:` - `class InnerUnionMember0:` - `List` - `String` - `double` - `boolean` - `List` - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional metadata` Job-level metadata. - `Optional usage` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.extract.ExtractListPage; import com.llamacloud_prod.api.models.extract.ExtractListParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractListPage page = client.extract().list(); } } ``` #### Response ```json { "items": [ { "id": "ext-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "created_at": "2019-12-27T18:11:19.117Z", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "COMPLETED", "updated_at": "2019-12-27T18:11:19.117Z", "configuration": { "data_schema": { "foo": { "foo": "bar" } }, "cite_sources": true, "confidence_scores": true, "extraction_target": "per_doc", "max_pages": 10, "parse_config_id": "cfg-11111111-2222-3333-4444-555555555555", "parse_tier": "fast", "system_prompt": "Extract all monetary values in USD. If a currency is not specified, assume USD.", "target_pages": "1,3,5-7", "tier": "cost_effective", "version": "latest" }, "configuration_id": "cfg-11111111-2222-3333-4444-555555555555", "error_message": "error_message", "extract_metadata": { "field_metadata": { "document_metadata": { "items": [ { "amount": { "citation": [ { "matching_text": "$10.00", "page": 1 } ], "confidence": 1 }, "description": { "citation": [ { "matching_text": "$10/month", "page": 1 } ], "confidence": 0.998 } } ], "total": { "citation": "bar", "confidence": "bar" }, "vendor": { "citation": "bar", "confidence": "bar", "extraction_confidence": "bar", "parsing_confidence": "bar" } }, "page_metadata": [ { "foo": { "foo": "bar" } } ], "row_metadata": [ { "foo": { "foo": "bar" } } ] }, "parse_job_id": "parse_job_id", "parse_tier": "parse_tier" }, "extract_result": { "foo": { "foo": "bar" } }, "metadata": { "usage": { "num_pages_extracted": 0 } } } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Extract Job `ExtractV2Job extract().get(ExtractGetParamsparams = ExtractGetParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **get** `/api/v2/extract/{job_id}` Get a single extraction job by ID. Returns the job status and results when complete. Use `expand=configuration` to include the full configuration used, and `expand=extract_metadata` for per-field metadata. ### Parameters - `ExtractGetParams params` - `Optional jobId` - `Optional> expand` Additional fields to include: configuration, extract_metadata - `Optional organizationId` - `Optional projectId` ### Returns - `class ExtractV2Job:` An extraction job. - `String id` Unique job identifier (job_id) - `LocalDateTime createdAt` Creation timestamp - `String fileInput` File ID or parse job ID that was extracted - `String projectId` Project this job belongs to - `String status` Current job status. - `PENDING` — queued, not yet started - `RUNNING` — actively processing - `COMPLETED` — finished successfully - `FAILED` — terminated with an error - `CANCELLED` — cancelled by user - `LocalDateTime updatedAt` Last update timestamp - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved extract configuration ID used for this job, if any - `Optional errorMessage` Error details when status is FAILED - `Optional extractMetadata` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document - `Optional extractResult` Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row. - `class UnionMember0:` - `class InnerUnionMember0:` - `List` - `String` - `double` - `boolean` - `List` - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional metadata` Job-level metadata. - `Optional usage` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.extract.ExtractGetParams; import com.llamacloud_prod.api.models.extract.ExtractV2Job; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractV2Job extractV2Job = client.extract().get("job_id"); } } ``` #### Response ```json { "id": "ext-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "created_at": "2019-12-27T18:11:19.117Z", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "COMPLETED", "updated_at": "2019-12-27T18:11:19.117Z", "configuration": { "data_schema": { "foo": { "foo": "bar" } }, "cite_sources": true, "confidence_scores": true, "extraction_target": "per_doc", "max_pages": 10, "parse_config_id": "cfg-11111111-2222-3333-4444-555555555555", "parse_tier": "fast", "system_prompt": "Extract all monetary values in USD. If a currency is not specified, assume USD.", "target_pages": "1,3,5-7", "tier": "cost_effective", "version": "latest" }, "configuration_id": "cfg-11111111-2222-3333-4444-555555555555", "error_message": "error_message", "extract_metadata": { "field_metadata": { "document_metadata": { "items": [ { "amount": { "citation": [ { "matching_text": "$10.00", "page": 1 } ], "confidence": 1 }, "description": { "citation": [ { "matching_text": "$10/month", "page": 1 } ], "confidence": 0.998 } } ], "total": { "citation": "bar", "confidence": "bar" }, "vendor": { "citation": "bar", "confidence": "bar", "extraction_confidence": "bar", "parsing_confidence": "bar" } }, "page_metadata": [ { "foo": { "foo": "bar" } } ], "row_metadata": [ { "foo": { "foo": "bar" } } ] }, "parse_job_id": "parse_job_id", "parse_tier": "parse_tier" }, "extract_result": { "foo": { "foo": "bar" } }, "metadata": { "usage": { "num_pages_extracted": 0 } } } ``` ## Delete Extract Job `JsonValue extract().delete(ExtractDeleteParamsparams = ExtractDeleteParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **delete** `/api/v2/extract/{job_id}` Delete an extraction job and its results. ### Parameters - `ExtractDeleteParams params` - `Optional jobId` - `Optional organizationId` - `Optional projectId` ### Returns - `class ExtractDeleteResponse:` ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.extract.ExtractDeleteParams; import com.llamacloud_prod.api.models.extract.ExtractDeleteResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractDeleteResponse extract = client.extract().delete("job_id"); } } ``` #### Response ```json {} ``` ## Validate Extraction Schema `ExtractV2SchemaValidateResponse extract().validateSchema(ExtractValidateSchemaParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/v2/extract/schema/validation` Validate a JSON schema for extraction. ### Parameters - `ExtractValidateSchemaParams params` - `ExtractV2SchemaValidateRequest extractV2SchemaValidateRequest` Request schema for validating an extraction schema. ### Returns - `class ExtractV2SchemaValidateResponse:` Response schema for schema validation. - `DataSchema dataSchema` Validated JSON Schema, ready for use in extract jobs - `class UnionMember0:` - `List` - `String` - `double` - `boolean` ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.core.JsonValue; import com.llamacloud_prod.api.models.extract.ExtractV2SchemaValidateRequest; import com.llamacloud_prod.api.models.extract.ExtractV2SchemaValidateResponse; import com.llamacloud_prod.api.models.extract.ExtractValidateSchemaParams; import java.util.List; import java.util.Map; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractV2SchemaValidateRequest params = ExtractV2SchemaValidateRequest.builder() .dataSchema(ExtractV2SchemaValidateRequest.DataSchema.builder() .putAdditionalProperty("properties", JsonValue.from(Map.of( "vendor_name", "bar", "invoice_number", "bar", "total_amount", "bar", "line_items", "bar" ))) .putAdditionalProperty("required", JsonValue.from(List.of( "vendor_name", "invoice_number", "total_amount" ))) .putAdditionalProperty("type", JsonValue.from("object")) .build()) .build(); ExtractV2SchemaValidateResponse extractV2SchemaValidateResponse = client.extract().validateSchema(params); } } ``` #### Response ```json { "data_schema": { "foo": { "foo": "bar" } } } ``` ## Generate Extraction Schema `ConfigurationCreate extract().generateSchema(ExtractGenerateSchemaParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/v2/extract/schema/generate` Generate a JSON schema and return a product configuration request. ### Parameters - `ExtractGenerateSchemaParams params` - `Optional organizationId` - `Optional projectId` - `ExtractV2SchemaGenerateRequest extractV2SchemaGenerateRequest` Request schema for generating an extraction schema. ### Returns - `class ConfigurationCreate:` Request body for creating a product configuration. - `String name` Human-readable name for this configuration. - `Parameters parameters` Product-specific configuration parameters. - `class SplitV1Parameters:` Typed parameters for a *split v1* product configuration. - `List categories` Categories to split documents into. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `JsonValue; productType "split_v1"constant` Product type. - `SPLIT_V1("split_v1")` - `Optional splittingStrategy` Strategy for splitting documents. - `Optional allowUncategorized` Controls handling of pages that don't match any category. 'include': pages can be grouped as 'uncategorized' and included in results. 'forbid': all pages must be assigned to a defined category. 'omit': pages can be classified as 'uncategorized' but are excluded from results. - `INCLUDE("include")` - `FORBID("forbid")` - `OMIT("omit")` - `class ExtractV2Parameters:` Typed parameters for an *extract v2* product configuration. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `JsonValue; productType "extract_v2"constant` Product type. - `EXTRACT_V2("extract_v2")` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `class ClassifyV2Parameters:` Typed parameters for a *classify v2* product configuration. - `JsonValue; productType "classify_v2"constant` Product type. - `CLASSIFY_V2("classify_v2")` - `List rules` Classify rules to evaluate against the document (at least one required) - `String description` Natural language criteria for matching this rule - `String type` Document type to assign when rule matches - `Optional mode` Classify execution mode - `FAST("FAST")` - `Optional parsingConfiguration` Parsing configuration for classify jobs. - `Optional lang` ISO 639-1 language code for the document - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `class ParseV2Parameters:` Configuration for LlamaParse v2 document parsing. Includes tier selection, processing options, output formatting, page targeting, and webhook delivery. Refer to the LlamaParse documentation for details on each field. - `JsonValue; productType "parse_v2"constant` Product type. - `PARSE_V2("parse_v2")` - `Tier tier` Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy) - `FAST("fast")` - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `AGENTIC_PLUS("agentic_plus")` - `Version version` Version for the selected tier. Use `latest`, or pin one of that tier's dated versions. Current `latest` by tier: - `fast`: `2025-12-11` - `cost_effective`: `2026-06-05` - `agentic`: `2026-06-04` - `agentic_plus`: `2026-06-04` Full list: `GET /api/v2/parse/versions`. - `LATEST("latest")` - `_2026_06_05("2026-06-05")` - `_2026_06_04("2026-06-04")` - `_2025_12_11("2025-12-11")` - `Optional agenticOptions` Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus). These options customize how the AI processes and interprets document content. Only applicable when using non-fast tiers. - `Optional customPrompt` Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: 'Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.' - `Optional clientName` Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2' - `Optional cropBox` Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges - `Optional bottom` Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded - `Optional left` Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded - `Optional right` Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded - `Optional top` Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded - `Optional disableCache` Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results - `Optional fastOptions` Options for fast tier parsing (rule-based, no AI). Fast tier uses deterministic algorithms for text extraction without AI enhancement. It's the fastest and most cost-effective option, best suited for simple documents with standard layouts. Currently has no configurable options but reserved for future expansion. - `Optional inputOptions` Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type - `Optional html` HTML/web page parsing options (applies to .html, .htm files) - `Optional makeAllElementsVisible` Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections - `Optional removeFixedElements` Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render - `Optional removeNavigationElements` Remove navigation elements (nav bars, sidebars, menus) to focus on main content - `Optional pdf` PDF-specific parsing options (applies to .pdf files) - `Optional presentation` Presentation parsing options (applies to .pptx, .ppt, .odp, .key files) - `Optional outOfBoundsContent` Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries - `Optional skipEmbeddedData` Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data - `Optional spreadsheet` Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files) - `Optional detectSubTablesInSheets` Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns - `Optional forceFormulaComputationInSheets` Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions - `Optional includeHiddenSheets` Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped - `Optional outputOptions` Output formatting options for markdown, text, and extracted images - `Optional> additionalOutputs` Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: 'stripped_md' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. 'concatenated_stripped_txt' — all stripped pages concatenated into a single plain-text file with `\n\n---\n\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. 'word_bbox' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`. - `Optional extractPrintedPageNumber` Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers - `Optional> granularBboxes` Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape. - `CELL("cell")` - `LINE("line")` - `WORD("word")` - `Optional> imagesToSave` Image categories to extract and save. Options: 'screenshot' (full page renders useful for visual QA), 'embedded' (images found within the document), 'layout' (cropped regions from layout detection like figures and diagrams). Empty list saves no images - `SCREENSHOT("screenshot")` - `EMBEDDED("embedded")` - `LAYOUT("layout")` - `Optional markdown` Markdown formatting options including table styles and link annotations - `Optional annotateLinks` Add link annotations to markdown output in the format [text](url). When false, only the link text is included - `Optional inlineImages` Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output - `Optional tables` Table formatting options including markdown vs HTML format and merging behavior - `Optional compactMarkdownTables` Remove extra whitespace padding in markdown table cells for more compact output - `Optional markdownTableMultilineSeparator` Separator string for multiline cell content in markdown tables. Example: '
' to preserve line breaks, ' ' to join with spaces - `Optional mergeContinuedTables` Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata - `Optional outputTablesAsMarkdown` Output tables as markdown pipe tables instead of HTML tags. Markdown tables are simpler but cannot represent complex structures like merged cells - `Optional spatialText` Spatial text output options for preserving document layout structure - `Optional doNotUnrollColumns` Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers - `Optional preserveLayoutAlignmentAcrossPages` Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes - `Optional preserveVerySmallText` Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out - `Optional tablesAsSpreadsheet` Options for exporting tables as XLSX spreadsheets - `Optional enable` Whether this option is enabled - `Optional guessSheetName` Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1' - `Optional pageRanges` Page selection: limit total pages or specify exact pages to process - `Optional maxPages` Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence - `Optional targetPages` Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: '1,3,5' (pages 1, 3, 5), '1-5' (pages 1 through 5 inclusive), '1,3,5-8,10' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error - `Optional processingControl` Job execution controls including timeouts and failure thresholds - `Optional jobFailureConditions` Quality thresholds that determine when a job should fail vs complete with partial results - `Optional allowedPageFailureRatio` Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%) - `Optional failOnBuggyFont` Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters - `Optional failOnImageExtractionError` Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job - `Optional failOnImageOcrError` Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image - `Optional failOnMarkdownReconstructionError` Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction - `Optional timeouts` Timeout settings for job execution. Increase for large or complex documents - `Optional baseInSeconds` Base timeout for the job in seconds (max 7200 = 2 hours). This is the minimum time allowed regardless of document size - `Optional extraTimePerPageInSeconds` Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count) - `Optional processingOptions` Document processing options including OCR, table extraction, and chart parsing - `Optional aggressiveTableExtraction` Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables - `Optional> autoModeConfiguration` Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered - `ParsingConf parsingConf` Parsing configuration to apply when trigger conditions are met - `Optional adaptiveLongTable` Whether to use adaptive long table handling - `Optional aggressiveTableExtraction` Whether to use aggressive table extraction - `Optional cropBox` Crop box options for auto mode parsing configuration. - `Optional bottom` Bottom boundary of crop box as ratio (0-1) - `Optional left` Left boundary of crop box as ratio (0-1) - `Optional right` Right boundary of crop box as ratio (0-1) - `Optional top` Top boundary of crop box as ratio (0-1) - `Optional customPrompt` Custom AI instructions for matched pages. Overrides the base custom_prompt - `Optional extractLayout` Whether to extract layout information - `Optional highResOcr` Whether to use high resolution OCR - `Optional ignore` Ignore options for auto mode parsing configuration. - `Optional ignoreDiagonalText` Whether to ignore diagonal text in the document - `Optional ignoreHiddenText` Whether to ignore hidden text in the document - `Optional language` Primary language of the document - `Optional outlinedTableExtraction` Whether to use outlined table extraction - `Optional presentation` Presentation-specific options for auto mode parsing configuration. - `Optional outOfBoundsContent` Extract out of bounds content in presentation slides - `Optional skipEmbeddedData` Skip extraction of embedded data for charts in presentation slides - `Optional spatialText` Spatial text options for auto mode parsing configuration. - `Optional doNotUnrollColumns` Keep column structure intact without unrolling - `Optional preserveLayoutAlignmentAcrossPages` Preserve text alignment across page boundaries - `Optional preserveVerySmallText` Include very small text in spatial output - `Optional specializedChartParsing` Enable specialized chart parsing with the specified mode - `AGENTIC_PLUS("agentic_plus")` - `AGENTIC("agentic")` - `EFFICIENT("efficient")` - `Optional tier` Override the parsing tier for matched pages. Must be paired with version - `FAST("fast")` - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `AGENTIC_PLUS("agentic_plus")` - `Optional version` Version for the override tier. Required when `tier` is set. Use `latest`, or pin one of that tier's dated versions. Current `latest` by tier: - `fast`: `2025-12-11` - `cost_effective`: `2026-06-05` - `agentic`: `2026-06-04` - `agentic_plus`: `2026-06-04` Full list: `GET /api/v2/parse/versions`. - `LATEST("latest")` - `_2026_06_05("2026-06-05")` - `_2026_06_04("2026-06-04")` - `_2025_12_11("2025-12-11")` - `Optional filenameMatchGlob` Single glob pattern to match against filename - `Optional> filenameMatchGlobList` List of glob patterns to match against filename - `Optional filenameRegexp` Regex pattern to match against filename - `Optional filenameRegexpMode` Regex mode flags (e.g., 'i' for case-insensitive) - `Optional fullPageImageInPage` Trigger if page contains a full-page image (scanned page detection) - `Optional fullPageImageInPageThreshold` Threshold for full page image detection (0.0-1.0, default 0.8) - `double` - `String` - `Optional imageInPage` Trigger if page contains non-screenshot images - `Optional layoutElementInPage` Trigger if page contains this layout element type - `Optional layoutElementInPageConfidenceThreshold` Confidence threshold for layout element detection - `double` - `String` - `Optional pageContainsAtLeastNCharts` Trigger if page has more than N charts - `long` - `String` - `Optional pageContainsAtLeastNImages` Trigger if page has more than N images - `long` - `String` - `Optional pageContainsAtLeastNLayoutElements` Trigger if page has more than N layout elements - `long` - `String` - `Optional pageContainsAtLeastNLines` Trigger if page has more than N lines - `long` - `String` - `Optional pageContainsAtLeastNLinks` Trigger if page has more than N links - `long` - `String` - `Optional pageContainsAtLeastNNumbers` Trigger if page has more than N numeric words - `long` - `String` - `Optional pageContainsAtLeastNPercentNumbers` Trigger if page has more than N% numeric words - `long` - `String` - `Optional pageContainsAtLeastNTables` Trigger if page has more than N tables - `long` - `String` - `Optional pageContainsAtLeastNWords` Trigger if page has more than N words - `long` - `String` - `Optional pageContainsAtMostNCharts` Trigger if page has fewer than N charts - `long` - `String` - `Optional pageContainsAtMostNImages` Trigger if page has fewer than N images - `long` - `String` - `Optional pageContainsAtMostNLayoutElements` Trigger if page has fewer than N layout elements - `long` - `String` - `Optional pageContainsAtMostNLines` Trigger if page has fewer than N lines - `long` - `String` - `Optional pageContainsAtMostNLinks` Trigger if page has fewer than N links - `long` - `String` - `Optional pageContainsAtMostNNumbers` Trigger if page has fewer than N numeric words - `long` - `String` - `Optional pageContainsAtMostNPercentNumbers` Trigger if page has fewer than N% numeric words - `long` - `String` - `Optional pageContainsAtMostNTables` Trigger if page has fewer than N tables - `long` - `String` - `Optional pageContainsAtMostNWords` Trigger if page has fewer than N words - `long` - `String` - `Optional pageLongerThanNChars` Trigger if page has more than N characters - `long` - `String` - `Optional pageMdError` Trigger on pages with markdown extraction errors - `Optional pageShorterThanNChars` Trigger if page has fewer than N characters - `long` - `String` - `Optional regexpInPage` Regex pattern to match in page content - `Optional regexpInPageMode` Regex mode flags for regexp_in_page - `Optional tableInPage` Trigger if page contains a table - `Optional textInPage` Trigger if page text/markdown contains this string - `Optional triggerMode` How to combine multiple trigger conditions: 'and' (all conditions must match, this is the default) or 'or' (any single condition can trigger) - `Optional costOptimizer` Cost optimizer configuration for reducing parsing costs on simpler pages. When enabled, the parser analyzes each page and routes simpler pages to faster, cheaper processing while preserving quality for complex pages. Only works with 'agentic' or 'agentic_plus' tiers. - `Optional enable` Enable cost-optimized parsing. Routes simpler pages to faster processing while complex pages use full AI analysis. May reduce speed on some documents. IMPORTANT: Only available with 'agentic' or 'agentic_plus' tiers - `Optional disableHeuristics` Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results - `Optional ignore` Options for ignoring specific text types (diagonal, hidden, text in images) - `Optional ignoreDiagonalText` Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text - `Optional ignoreHiddenText` Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing - `Optional ignoreTextInImage` Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output - `Optional ocrParameters` OCR configuration including language detection settings - `Optional> languages` Languages to use for OCR text recognition. Specify multiple languages if document contains mixed-language content. Order matters - put primary language first. Example: ['en', 'es'] for English with Spanish - `AF("af")` - `AZ("az")` - `BS("bs")` - `CS("cs")` - `CY("cy")` - `DA("da")` - `DE("de")` - `EN("en")` - `ES("es")` - `ET("et")` - `FR("fr")` - `GA("ga")` - `HR("hr")` - `HU("hu")` - `ID("id")` - `IS("is")` - `IT("it")` - `KU("ku")` - `LA("la")` - `LT("lt")` - `LV("lv")` - `MI("mi")` - `MS("ms")` - `MT("mt")` - `NL("nl")` - `NO("no")` - `OC("oc")` - `PI("pi")` - `PL("pl")` - `PT("pt")` - `RO("ro")` - `RS_LATIN("rs_latin")` - `SK("sk")` - `SL("sl")` - `SQ("sq")` - `SV("sv")` - `SW("sw")` - `TL("tl")` - `TR("tr")` - `UZ("uz")` - `VI("vi")` - `AR("ar")` - `FA("fa")` - `UG("ug")` - `UR("ur")` - `BN("bn")` - `AS("as")` - `MNI("mni")` - `RU("ru")` - `RS_CYRILLIC("rs_cyrillic")` - `BE("be")` - `BG("bg")` - `UK("uk")` - `MN("mn")` - `ABQ("abq")` - `ADY("ady")` - `KBD("kbd")` - `AVA("ava")` - `DAR("dar")` - `INH("inh")` - `CHE("che")` - `LBE("lbe")` - `LEZ("lez")` - `TAB("tab")` - `TJK("tjk")` - `HI("hi")` - `MR("mr")` - `NE("ne")` - `BH("bh")` - `MAI("mai")` - `ANG("ang")` - `BHO("bho")` - `MAH("mah")` - `SCK("sck")` - `NEW("new")` - `GOM("gom")` - `SA("sa")` - `BGC("bgc")` - `TH("th")` - `CH_SIM("ch_sim")` - `CH_TRA("ch_tra")` - `JA("ja")` - `KO("ko")` - `TA("ta")` - `TE("te")` - `KN("kn")` - `Optional specializedChartParsing` Enable AI-powered chart analysis. Modes: 'efficient' (fast, lower cost), 'agentic' (balanced), 'agentic_plus' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set - `AGENTIC_PLUS("agentic_plus")` - `AGENTIC("agentic")` - `EFFICIENT("efficient")` - `Optional> webhookConfigurations` Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services - `Optional> webhookEvents` Events that trigger this webhook. Options: 'parse.success' (job completed), 'parse.error' (job failed), 'parse.partial_success' (some pages failed), 'parse.pending', 'parse.running', 'parse.cancelled'. If not specified, webhook fires for all events - `Optional webhookHeaders` Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {'Authorization': 'Bearer xyz'} - `Optional webhookOutputFormat` Format of the webhook payload body. 'string' (default) sends the payload as a JSON-encoded string; 'json' sends it as a JSON object. - `STRING("string")` - `JSON("json")` - `Optional webhookUrl` HTTPS URL to receive webhook POST requests. Must be publicly accessible - `class SpreadsheetV1:` Typed parameters for a *spreadsheet v1* product configuration. - `JsonValue; productType "spreadsheet_v1"constant` Product type. - `SPREADSHEET_V1("spreadsheet_v1")` - `Optional extractionRange` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `Optional flattenHierarchicalTables` Return a flattened dataframe when a detected table is recognized as hierarchical. - `Optional generateAdditionalMetadata` Whether to generate additional metadata (title, description) for each extracted region. - `Optional includeHiddenCells` Whether to include hidden cells when extracting regions from the spreadsheet. - `Optional> sheetNames` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `Optional specialization` Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. - `Optional tableMergeSensitivity` Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging). - `STRONG("strong")` - `WEAK("weak")` - `Optional useExperimentalProcessing` Enables experimental processing. Accuracy may be impacted. - `class UntypedParameters:` Catch-all for configurations without a dedicated typed schema. Accepts arbitrary JSON fields alongside `product_type`. - `JsonValue; productType "unknown"constant` Product type. - `UNKNOWN("unknown")` ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.configurations.ConfigurationCreate; import com.llamacloud_prod.api.models.extract.ExtractGenerateSchemaParams; import com.llamacloud_prod.api.models.extract.ExtractV2SchemaGenerateRequest; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); ExtractV2SchemaGenerateRequest params = ExtractV2SchemaGenerateRequest.builder().build(); ConfigurationCreate configurationCreate = client.extract().generateSchema(params); } } ``` #### Response ```json { "name": "x", "parameters": { "categories": [ { "name": "x", "description": "x" } ], "product_type": "split_v1", "splitting_strategy": { "allow_uncategorized": "include" } } } ``` ## Domain Types ### Extract Configuration - `class ExtractConfiguration:` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. ### Extract Job Metadata - `class ExtractJobMetadata:` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document ### Extract Job Usage - `class ExtractJobUsage:` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted ### Extract V2 Job - `class ExtractV2Job:` An extraction job. - `String id` Unique job identifier (job_id) - `LocalDateTime createdAt` Creation timestamp - `String fileInput` File ID or parse job ID that was extracted - `String projectId` Project this job belongs to - `String status` Current job status. - `PENDING` — queued, not yet started - `RUNNING` — actively processing - `COMPLETED` — finished successfully - `FAILED` — terminated with an error - `CANCELLED` — cancelled by user - `LocalDateTime updatedAt` Last update timestamp - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved extract configuration ID used for this job, if any - `Optional errorMessage` Error details when status is FAILED - `Optional extractMetadata` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document - `Optional extractResult` Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row. - `class UnionMember0:` - `class InnerUnionMember0:` - `List` - `String` - `double` - `boolean` - `List` - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional metadata` Job-level metadata. - `Optional usage` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted ### Extract V2 Job Create - `class ExtractV2JobCreate:` Request to create an extraction job. Provide configuration_id or inline configuration. - `String fileInput` File ID or parse job ID to extract from - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved configuration ID - `Optional> webhookConfigurations` Outbound webhook endpoints to notify on job status changes - `Optional> webhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `EXTRACT_PENDING("extract.pending")` - `EXTRACT_SUCCESS("extract.success")` - `EXTRACT_ERROR("extract.error")` - `EXTRACT_PARTIAL_SUCCESS("extract.partial_success")` - `EXTRACT_CANCELLED("extract.cancelled")` - `PARSE_PENDING("parse.pending")` - `PARSE_RUNNING("parse.running")` - `PARSE_SUCCESS("parse.success")` - `PARSE_ERROR("parse.error")` - `PARSE_PARTIAL_SUCCESS("parse.partial_success")` - `PARSE_CANCELLED("parse.cancelled")` - `CLASSIFY_PENDING("classify.pending")` - `CLASSIFY_RUNNING("classify.running")` - `CLASSIFY_SUCCESS("classify.success")` - `CLASSIFY_ERROR("classify.error")` - `CLASSIFY_PARTIAL_SUCCESS("classify.partial_success")` - `CLASSIFY_CANCELLED("classify.cancelled")` - `SHEETS_PENDING("sheets.pending")` - `SHEETS_SUCCESS("sheets.success")` - `SHEETS_ERROR("sheets.error")` - `SHEETS_PARTIAL_SUCCESS("sheets.partial_success")` - `SHEETS_CANCELLED("sheets.cancelled")` - `UNMAPPED_EVENT("unmapped_event")` - `Optional webhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `Optional webhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `Optional webhookUrl` URL to receive webhook POST notifications ### Extract V2 Job Query Response - `class ExtractV2JobQueryResponse:` Paginated list of extraction jobs. - `List items` The list of items. - `String id` Unique job identifier (job_id) - `LocalDateTime createdAt` Creation timestamp - `String fileInput` File ID or parse job ID that was extracted - `String projectId` Project this job belongs to - `String status` Current job status. - `PENDING` — queued, not yet started - `RUNNING` — actively processing - `COMPLETED` — finished successfully - `FAILED` — terminated with an error - `CANCELLED` — cancelled by user - `LocalDateTime updatedAt` Last update timestamp - `Optional configuration` Extract configuration combining parse and extract settings. - `DataSchema dataSchema` JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional citeSources` Include citations in results - `Optional confidenceScores` Include confidence scores in results - `Optional extractionTarget` Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `PER_DOC("per_doc")` - `PER_PAGE("per_page")` - `PER_TABLE_ROW("per_table_row")` - `Optional maxPages` Maximum number of pages to process. Omit for no limit. - `Optional parseConfigId` Saved parse configuration ID to control how the document is parsed before extraction - `Optional parseTier` Parse tier to use before extraction. Defaults to the extract tier if not specified. - `Optional systemPrompt` Custom system prompt to guide extraction behavior - `Optional targetPages` Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `Optional tier` Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `COST_EFFECTIVE("cost_effective")` - `AGENTIC("agentic")` - `Optional version` Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `Optional configurationId` Saved extract configuration ID used for this job, if any - `Optional errorMessage` Error details when status is FAILED - `Optional extractMetadata` Extraction metadata. - `Optional fieldMetadata` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional parseJobId` Reference to the ParseJob ID used for parsing - `Optional parseTier` Parse tier used for parsing the document - `Optional extractResult` Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row. - `class UnionMember0:` - `class InnerUnionMember0:` - `List` - `String` - `double` - `boolean` - `List` - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional metadata` Job-level metadata. - `Optional usage` Extraction usage metrics. - `Optional numPagesExtracted` Number of pages extracted - `Optional nextPageToken` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `Optional totalSize` The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. ### Extract V2 Schema Generate Request - `class ExtractV2SchemaGenerateRequest:` Request schema for generating an extraction schema. - `Optional dataSchema` Optional schema to validate, refine, or extend - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional fileId` Optional file ID to analyze for schema generation - `Optional name` Name for the generated configuration (auto-generated if omitted) - `Optional prompt` Natural language description of the data structure to extract ### Extract V2 Schema Validate Request - `class ExtractV2SchemaValidateRequest:` Request schema for validating an extraction schema. - `DataSchema dataSchema` JSON Schema to validate for use with extract jobs - `class UnionMember0:` - `List` - `String` - `double` - `boolean` ### Extract V2 Schema Validate Response - `class ExtractV2SchemaValidateResponse:` Response schema for schema validation. - `DataSchema dataSchema` Validated JSON Schema, ready for use in extract jobs - `class UnionMember0:` - `List` - `String` - `double` - `boolean` ### Extracted Field Metadata - `class ExtractedFieldMetadata:` Metadata for extracted fields including document, page, and row level info. - `Optional documentMetadata` Per-field metadata keyed by field name from your schema. Scalar fields (e.g. `vendor`) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. `items`) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> pageMetadata` Per-page metadata when extraction_target is per_page - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional> rowMetadata` Per-row metadata when extraction_target is per_table_row - `class UnionMember0:` - `List` - `String` - `double` - `boolean`