# Split ## Create Split Job `SplitCreateResponse split().create(SplitCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/v1/split/jobs` Create a document split job. ### Parameters - `SplitCreateParams params` - `Optional organizationId` - `Optional projectId` - `String fileInput` File ID or parse job ID - `Optional configuration` Split configuration with categories and splitting strategy. - `List categories` Categories to split documents into. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `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. - `FORBID("forbid")` - `INCLUDE("include")` - `OMIT("omit")` - `Optional customInstructions` Free-form guidance for where segment boundaries are placed. - `Optional minPagesPerSplit` Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging. - `Optional configurationId` Saved configuration ID - `Optional transactionId` Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored. - `Optional> webhookConfigurationIds` IDs of saved webhook configurations to notify for this job. - `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. - `BATCH_CANCELLED("batch.cancelled")` - `BATCH_ERROR("batch.error")` - `BATCH_PENDING("batch.pending")` - `BATCH_RUNNING("batch.running")` - `BATCH_SUCCESS("batch.success")` - `CLASSIFY_CANCELLED("classify.cancelled")` - `CLASSIFY_ERROR("classify.error")` - `CLASSIFY_PARTIAL_SUCCESS("classify.partial_success")` - `CLASSIFY_PENDING("classify.pending")` - `CLASSIFY_RUNNING("classify.running")` - `CLASSIFY_SUCCESS("classify.success")` - `EXTRACT_CANCELLED("extract.cancelled")` - `EXTRACT_ERROR("extract.error")` - `EXTRACT_PARTIAL_SUCCESS("extract.partial_success")` - `EXTRACT_PENDING("extract.pending")` - `EXTRACT_SUCCESS("extract.success")` - `PARSE_CANCELLED("parse.cancelled")` - `PARSE_ERROR("parse.error")` - `PARSE_PARTIAL_SUCCESS("parse.partial_success")` - `PARSE_PENDING("parse.pending")` - `PARSE_RUNNING("parse.running")` - `PARSE_SUCCESS("parse.success")` - `SHEETS_CANCELLED("sheets.cancelled")` - `SHEETS_ERROR("sheets.error")` - `SHEETS_PARTIAL_SUCCESS("sheets.partial_success")` - `SHEETS_PENDING("sheets.pending")` - `SHEETS_SUCCESS("sheets.success")` - `SPLIT_CANCELLED("split.cancelled")` - `SPLIT_ERROR("split.error")` - `SPLIT_PENDING("split.pending")` - `SPLIT_PROCESSING("split.processing")` - `SPLIT_SUCCESS("split.success")` - `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 webhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `Optional webhookUrl` URL to receive webhook POST notifications ### Returns - `class SplitCreateResponse:` A split job. - `String id` Unique identifier for the split job. - `List categories` Categories used for splitting. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `DocumentInputType documentInputType` Whether the input was a file or parse job - `FILE_ID("file_id")` - `PARSE_JOB_ID("parse_job_id")` - `URL("url")` - `String fileInput` File ID or parse job ID - `String projectId` Project this job belongs to. - `String status` Current job status. Valid values are: pending, processing, completed, failed, cancelled. - `String userId` User who created this job. - `Optional configurationId` Split configuration ID used for this job. - `Optional createdAt` Creation datetime - `Optional errorMessage` Error message if the job failed. - `Optional result` Result of a completed split job. - `List segments` List of document segments. - `String category` Category name this split belongs to. - `String confidenceCategory` Categorical confidence level. Valid values are: high, medium, low. - `List pages` 1-indexed page numbers in this split. - `Optional splittingStrategy` Strategy used for splitting. - `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. - `FORBID("forbid")` - `INCLUDE("include")` - `OMIT("omit")` - `Optional customInstructions` Free-form guidance for where segment boundaries are placed. - `Optional minPagesPerSplit` Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging. - `Optional transactionId` Idempotency key scoped to the project, if one was provided. - `Optional updatedAt` Update datetime ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.split.SplitCreateParams; import ai.llamaindex.llamacloud.models.split.SplitCreateResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); SplitCreateParams params = SplitCreateParams.builder() .fileInput("dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee") .build(); SplitCreateResponse split = client.split().create(params); } } ``` #### Response ```json { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input_type": "file_id", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "project_id", "status": "status", "user_id": "user_id", "configuration_id": "configuration_id", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "result": { "segments": [ { "category": "category", "confidence_category": "confidence_category", "pages": [ 0 ] } ] }, "splitting_strategy": { "allow_uncategorized": "forbid", "custom_instructions": "Start a new segment at every signature page.", "min_pages_per_split": 1 }, "transaction_id": "transaction_id", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## List Split Jobs `SplitListPage split().list(SplitListParamsparams = SplitListParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **get** `/api/v1/split/jobs` List document split jobs. ### Parameters - `SplitListParams params` - `Optional createdAtOnOrAfter` Include items created at or after this timestamp (inclusive) - `Optional createdAtOnOrBefore` Include items created at or before this timestamp (inclusive) - `Optional> jobIds` Filter by specific job IDs - `Optional organizationId` - `Optional pageSize` - `Optional pageToken` - `Optional projectId` - `Optional status` Filter by job status (pending, processing, completed, failed, cancelled) - `CANCELLED("cancelled")` - `COMPLETED("completed")` - `FAILED("failed")` - `PENDING("pending")` - `PROCESSING("processing")` ### Returns - `class SplitListResponse:` A split job. - `String id` Unique identifier for the split job. - `List categories` Categories used for splitting. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `DocumentInputType documentInputType` Whether the input was a file or parse job - `FILE_ID("file_id")` - `PARSE_JOB_ID("parse_job_id")` - `URL("url")` - `String fileInput` File ID or parse job ID - `String projectId` Project this job belongs to. - `String status` Current job status. Valid values are: pending, processing, completed, failed, cancelled. - `String userId` User who created this job. - `Optional configurationId` Split configuration ID used for this job. - `Optional createdAt` Creation datetime - `Optional errorMessage` Error message if the job failed. - `Optional result` Result of a completed split job. - `List segments` List of document segments. - `String category` Category name this split belongs to. - `String confidenceCategory` Categorical confidence level. Valid values are: high, medium, low. - `List pages` 1-indexed page numbers in this split. - `Optional splittingStrategy` Strategy used for splitting. - `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. - `FORBID("forbid")` - `INCLUDE("include")` - `OMIT("omit")` - `Optional customInstructions` Free-form guidance for where segment boundaries are placed. - `Optional minPagesPerSplit` Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging. - `Optional transactionId` Idempotency key scoped to the project, if one was provided. - `Optional updatedAt` Update datetime ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.split.SplitListPage; import ai.llamaindex.llamacloud.models.split.SplitListParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); SplitListPage page = client.split().list(); } } ``` #### Response ```json { "items": [ { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input_type": "file_id", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "project_id", "status": "status", "user_id": "user_id", "configuration_id": "configuration_id", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "result": { "segments": [ { "category": "category", "confidence_category": "confidence_category", "pages": [ 0 ] } ] }, "splitting_strategy": { "allow_uncategorized": "forbid", "custom_instructions": "Start a new segment at every signature page.", "min_pages_per_split": 1 }, "transaction_id": "transaction_id", "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Split Job `SplitGetResponse split().get(SplitGetParamsparams = SplitGetParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **get** `/api/v1/split/jobs/{split_job_id}` Get a document split job. ### Parameters - `SplitGetParams params` - `Optional splitJobId` - `Optional organizationId` - `Optional projectId` ### Returns - `class SplitGetResponse:` A split job. - `String id` Unique identifier for the split job. - `List categories` Categories used for splitting. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `DocumentInputType documentInputType` Whether the input was a file or parse job - `FILE_ID("file_id")` - `PARSE_JOB_ID("parse_job_id")` - `URL("url")` - `String fileInput` File ID or parse job ID - `String projectId` Project this job belongs to. - `String status` Current job status. Valid values are: pending, processing, completed, failed, cancelled. - `String userId` User who created this job. - `Optional configurationId` Split configuration ID used for this job. - `Optional createdAt` Creation datetime - `Optional errorMessage` Error message if the job failed. - `Optional result` Result of a completed split job. - `List segments` List of document segments. - `String category` Category name this split belongs to. - `String confidenceCategory` Categorical confidence level. Valid values are: high, medium, low. - `List pages` 1-indexed page numbers in this split. - `Optional splittingStrategy` Strategy used for splitting. - `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. - `FORBID("forbid")` - `INCLUDE("include")` - `OMIT("omit")` - `Optional customInstructions` Free-form guidance for where segment boundaries are placed. - `Optional minPagesPerSplit` Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging. - `Optional transactionId` Idempotency key scoped to the project, if one was provided. - `Optional updatedAt` Update datetime ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.split.SplitGetParams; import ai.llamaindex.llamacloud.models.split.SplitGetResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); SplitGetResponse split = client.split().get("split_job_id"); } } ``` #### Response ```json { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input_type": "file_id", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "project_id", "status": "status", "user_id": "user_id", "configuration_id": "configuration_id", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "result": { "segments": [ { "category": "category", "confidence_category": "confidence_category", "pages": [ 0 ] } ] }, "splitting_strategy": { "allow_uncategorized": "forbid", "custom_instructions": "Start a new segment at every signature page.", "min_pages_per_split": 1 }, "transaction_id": "transaction_id", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Split Job `JsonValue split().delete(SplitDeleteParamsparams = SplitDeleteParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **delete** `/api/v1/split/jobs/{split_job_id}` Delete a split job and its results. ### Parameters - `SplitDeleteParams params` - `Optional splitJobId` - `Optional organizationId` - `Optional projectId` ### Returns - `class SplitDeleteResponse:` ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.split.SplitDeleteParams; import ai.llamaindex.llamacloud.models.split.SplitDeleteResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); SplitDeleteResponse split = client.split().delete("split_job_id"); } } ``` #### Response ```json {} ``` ## Cancel Split Job `SplitCancelResponse split().cancel(SplitCancelParamsparams = SplitCancelParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/v1/split/jobs/{split_job_id}/cancel` Cancel a running split job. Requests cancellation; the job transitions to CANCELLED asynchronously once processing stops. Returns the job, which may still be in its current non-terminal state. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled. ### Parameters - `SplitCancelParams params` - `Optional splitJobId` - `Optional organizationId` - `Optional projectId` ### Returns - `class SplitCancelResponse:` A split job. - `String id` Unique identifier for the split job. - `List categories` Categories used for splitting. - `String name` Name of the category. - `Optional description` Optional description of what content belongs in this category. - `DocumentInputType documentInputType` Whether the input was a file or parse job - `FILE_ID("file_id")` - `PARSE_JOB_ID("parse_job_id")` - `URL("url")` - `String fileInput` File ID or parse job ID - `String projectId` Project this job belongs to. - `String status` Current job status. Valid values are: pending, processing, completed, failed, cancelled. - `String userId` User who created this job. - `Optional configurationId` Split configuration ID used for this job. - `Optional createdAt` Creation datetime - `Optional errorMessage` Error message if the job failed. - `Optional result` Result of a completed split job. - `List segments` List of document segments. - `String category` Category name this split belongs to. - `String confidenceCategory` Categorical confidence level. Valid values are: high, medium, low. - `List pages` 1-indexed page numbers in this split. - `Optional splittingStrategy` Strategy used for splitting. - `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. - `FORBID("forbid")` - `INCLUDE("include")` - `OMIT("omit")` - `Optional customInstructions` Free-form guidance for where segment boundaries are placed. - `Optional minPagesPerSplit` Minimum pages per segment. Shorter segments are merged into an adjacent segment; 1 disables merging. - `Optional transactionId` Idempotency key scoped to the project, if one was provided. - `Optional updatedAt` Update datetime ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.split.SplitCancelParams; import ai.llamaindex.llamacloud.models.split.SplitCancelResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); SplitCancelResponse response = client.split().cancel("split_job_id"); } } ``` #### Response ```json { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input_type": "file_id", "file_input": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "project_id": "project_id", "status": "status", "user_id": "user_id", "configuration_id": "configuration_id", "created_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "result": { "segments": [ { "category": "category", "confidence_category": "confidence_category", "pages": [ 0 ] } ] }, "splitting_strategy": { "allow_uncategorized": "forbid", "custom_instructions": "Start a new segment at every signature page.", "min_pages_per_split": 1 }, "transaction_id": "transaction_id", "updated_at": "2019-12-27T18:11:19.117Z" } ```