# Beta # Indexes ## Get Index `$ llp beta:indexes get` **get** `/api/v1/indexes/{index_id}` Get an index by ID. ### Parameters - `--index-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaIndexGetResponse: object { id, export_config_id, name, 10 more }` A searchable index over a directory of documents. - `id: string` Unique identifier - `export_config_id: string` ID of the export configuration. - `name: string` Index name. - `output_directory_id: string` ID of the output directory holding the indexed files. - `project_id: string` Project this index belongs to. - `source_directory_id: string` ID of the source directory. - `sync_config_id: string` ID of the sync configuration. - `created_at: optional string` Creation datetime - `description: optional string` Index description. - `last_exported_at: optional string` Last export time. - `last_synced_at: optional string` Last sync time. - `metadata: optional map[unknown]` Build state and diagnostic info. - `updated_at: optional string` Update datetime ### Example ```cli llp beta:indexes get \ --api-key 'My API Key' \ --index-id index_id ``` #### Response ```json { "id": "id", "export_config_id": "export_config_id", "name": "name", "output_directory_id": "output_directory_id", "project_id": "project_id", "source_directory_id": "source_directory_id", "sync_config_id": "sync_config_id", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "last_exported_at": "2019-12-27T18:11:19.117Z", "last_synced_at": "2019-12-27T18:11:19.117Z", "metadata": { "foo": "bar" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Index `$ llp beta:indexes delete` **delete** `/api/v1/indexes/{index_id}` Delete an index. ### Parameters - `--index-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Example ```cli llp beta:indexes delete \ --api-key 'My API Key' \ --index-id index_id ``` ## Create Index `$ llp beta:indexes create` **post** `/api/v1/indexes` Create a searchable index over a source directory. ### Parameters - `--source-directory-id: string` Body param: ID of the source directory containing your documents. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--description: optional string` Body param: Optional description of the index. - `--name: optional string` Body param: Optional display name for the index. If omitted, the index is named after the source directory. - `--product: optional array of object { product_config_id, product_type }` Body param: Product configurations for syncing. Omit to use a default parse configuration. Include an explicit entry per product type (e.g. parse, extract) to override the default. - `--store-attachment: optional array of string` Body param: Attachment kinds to store alongside parsed output. Each entry must be one of: screenshots, items. For example, ['screenshots'] renders and stores per-page screenshots; ['items'] stores structured items with bounding boxes. Omit or pass an empty list to skip attachments. - `--sync-frequency: optional string` Body param: How often to re-run the sync. One of: manual, daily, on_source_change. Defaults to manual. - `--vector-target: optional "DEFAULT" or "DISABLED"` Body param: Vector export destination for the index. 'DEFAULT' exports to the managed vector DB destination resolved from configuration. 'DISABLED' skips vector export — the export destination falls back to 'Download'. ### Returns - `BetaIndexNewResponse: object { id, export_config_id, name, 10 more }` A searchable index over a directory of documents. - `id: string` Unique identifier - `export_config_id: string` ID of the export configuration. - `name: string` Index name. - `output_directory_id: string` ID of the output directory holding the indexed files. - `project_id: string` Project this index belongs to. - `source_directory_id: string` ID of the source directory. - `sync_config_id: string` ID of the sync configuration. - `created_at: optional string` Creation datetime - `description: optional string` Index description. - `last_exported_at: optional string` Last export time. - `last_synced_at: optional string` Last sync time. - `metadata: optional map[unknown]` Build state and diagnostic info. - `updated_at: optional string` Update datetime ### Example ```cli llp beta:indexes create \ --api-key 'My API Key' \ --source-directory-id dir-abc123 ``` #### Response ```json { "id": "id", "export_config_id": "export_config_id", "name": "name", "output_directory_id": "output_directory_id", "project_id": "project_id", "source_directory_id": "source_directory_id", "sync_config_id": "sync_config_id", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "last_exported_at": "2019-12-27T18:11:19.117Z", "last_synced_at": "2019-12-27T18:11:19.117Z", "metadata": { "foo": "bar" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Sync Index `$ llp beta:indexes sync` **post** `/api/v1/indexes/{index_id}/sync` Trigger a sync and export for an existing index, re-parsing changed files and exporting updated chunks. ### Parameters - `--index-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaIndexSyncResponse: unknown` ### Example ```cli llp beta:indexes sync \ --api-key 'My API Key' \ --index-id index_id ``` #### Response ```json {} ``` ## List Indexes `$ llp beta:indexes list` **get** `/api/v1/indexes` List indexes for the current project. ### Parameters - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` - `--source-directory-id: optional string` ### Returns - `IndexQueryResponse: object { items, next_page_token, total_size }` Paginated list of indexes. - `items: array of object { id, export_config_id, name, 10 more }` The list of items. - `id: string` Unique identifier - `export_config_id: string` ID of the export configuration. - `name: string` Index name. - `output_directory_id: string` ID of the output directory holding the indexed files. - `project_id: string` Project this index belongs to. - `source_directory_id: string` ID of the source directory. - `sync_config_id: string` ID of the sync configuration. - `created_at: optional string` Creation datetime - `description: optional string` Index description. - `last_exported_at: optional string` Last export time. - `last_synced_at: optional string` Last sync time. - `metadata: optional map[unknown]` Build state and diagnostic info. - `updated_at: optional string` Update datetime - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:indexes list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "id": "id", "export_config_id": "export_config_id", "name": "name", "output_directory_id": "output_directory_id", "project_id": "project_id", "source_directory_id": "source_directory_id", "sync_config_id": "sync_config_id", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "last_exported_at": "2019-12-27T18:11:19.117Z", "last_synced_at": "2019-12-27T18:11:19.117Z", "metadata": { "foo": "bar" }, "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` # Retrieval ## Retrieve `$ llp beta:retrieval retrieve` **post** `/api/v1/retrieval/retrieve` Retrieve relevant chunks via hybrid search (vector + full-text), with filtering on built-in or user-defined metadata. ### Parameters - `--index-id: string` Body param: ID of the index to retrieve against. - `--query: string` Body param: Natural-language query to retrieve relevant chunks. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--custom-filters: optional map[object { operator, value } or array of object { operator, value } ]` Body param: Filters on user-defined metadata fields. - `--full-text-pipeline-weight: optional number` Body param: Weight of the full-text search pipeline (0-1). - `--num-candidates: optional number` Body param: Number of candidates for approximate nearest neighbor search. - `--rerank: optional object { enabled, top_n }` Body param: Reranking configuration applied after hybrid search. Enabled by default. - `--score-threshold: optional number` Body param: Minimum score threshold for returned results. - `--static-filters: optional object { parsed_directory_file_id }` Body param: Filters on built-in document fields (page range, chunk index, etc.). - `--top-k: optional number` Body param: Maximum number of results to return. - `--vector-pipeline-weight: optional number` Body param: Weight of the vector search pipeline (0-1). ### Returns - `BetaRetrievalGetResponse: object { results }` Response containing retrieval results. - `results: array of object { content, metadata, rerank_score, 2 more }` Ordered list of retrieved chunks. - `content: string` Text content of the retrieved chunk. - `metadata: optional map[string or number or number or 3 more]` User-defined metadata associated with the chunk. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `rerank_score: optional number` Relevance score from the reranker, if reranking was applied. - `score: optional number` Hybrid search relevance score. - `static_fields: optional object { attachments, chunk_end_char, chunk_index, 5 more }` Built-in fields stored for every exported chunk. - `attachments: optional array of object { attachment_name, source_id, type }` Attachments associated with the chunk - `attachment_name: string` Attachment-relative path, e.g. 'screenshots/page_7.jpg'. - `source_id: string` File ID to pass as source_id when fetching the attachment. - `type: string` Attachment kind, e.g. 'screenshot', 'items'. - `chunk_end_char: optional number` End character offset of the chunk. - `chunk_index: optional number` Index of the chunk within the file. - `chunk_start_char: optional number` Start character offset of the chunk. - `chunk_token_count: optional number` Token count of the chunk. - `page_range_end: optional number` Last page number covered by this chunk. - `page_range_start: optional number` First page number covered by this chunk. - `parsed_directory_file_id: optional string` ID of the parsed file. ### Example ```cli llp beta:retrieval retrieve \ --api-key 'My API Key' \ --index-id idx-abc123 \ --query 'What are the key findings?' ``` #### Response ```json { "results": [ { "content": "content", "metadata": { "foo": "string" }, "rerank_score": 0, "score": 0, "static_fields": { "attachments": [ { "attachment_name": "attachment_name", "source_id": "source_id", "type": "type" } ], "chunk_end_char": 0, "chunk_index": 0, "chunk_start_char": 0, "chunk_token_count": 0, "page_range_end": 0, "page_range_start": 0, "parsed_directory_file_id": "parsed_directory_file_id" } } ] } ``` ## Find Files `$ llp beta:retrieval find` **post** `/api/v1/retrieval/files/find` Search for files by name. ### Parameters - `--index-id: string` Body param: ID of the index to search within. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--file-name: optional string` Body param: Exact file name to match. - `--file-name-contains: optional string` Body param: Substring match on file name (case-insensitive). - `--page-size: optional number` Body param: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. - `--page-token: optional string` Body param: A page token, received from a previous list call. Provide this to retrieve the subsequent page. ### Returns - `FileFindResult: object { items, next_page_token, total_size }` Paginated file find results. - `items: array of object { file_id, file_name }` The list of items. - `file_id: string` ID of the file. - `file_name: string` Display name of the file. - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:retrieval find \ --api-key 'My API Key' \ --index-id idx-abc123 ``` #### Response ```json { "items": [ { "file_id": "file_id", "file_name": "file_name" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Grep File `$ llp beta:retrieval grep` **post** `/api/v1/retrieval/files/grep` Grep within a file's parsed content using a regex pattern. ### Parameters - `--file-id: string` Body param: ID of the file to grep. - `--index-id: string` Body param: ID of the index the file belongs to. - `--pattern: string` Body param: Regex pattern to search for. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--context-chars: optional number` Body param: Number of characters of context to include before and after the matched pattern in the content field of the response - `--page-size: optional number` Body param: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. - `--page-token: optional string` Body param: A page token, received from a previous list call. Provide this to retrieve the subsequent page. ### Returns - `FileGrepResult: object { items, next_page_token, total_size }` Paginated grep results for a file. - `items: array of object { content, end_char, start_char }` The list of items. - `content: string` Matched text content. - `end_char: number` End character offset of the match. - `start_char: number` Start character offset of the match. - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:retrieval grep \ --api-key 'My API Key' \ --file-id file_id \ --index-id idx-abc123 \ --pattern 'revenue|profit' ``` #### Response ```json { "items": [ { "content": "content", "end_char": 0, "start_char": 0 } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Read File `$ llp beta:retrieval read` **post** `/api/v1/retrieval/files/read` Read the parsed text content of a specific file. ### Parameters - `--file-id: string` Body param: ID of the file to read. - `--index-id: string` Body param: ID of the index the file belongs to. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--max-length: optional number` Body param: Maximum number of characters to read from the offset. - `--offset: optional number` Body param: Starting character offset. ### Returns - `BetaRetrievalReadResponse: object { content }` File read result. - `content: string` Parsed text content of the file. ### Example ```cli llp beta:retrieval read \ --api-key 'My API Key' \ --file-id file_id \ --index-id idx-abc123 ``` #### Response ```json { "content": "content" } ``` # Chat ## List Sessions `$ llp beta:chat list` **get** `/api/v1/chat` List all chat sessions for the current project. ### Parameters - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` ### Returns - `SessionList: object { items, next_page_token }` Paginated list of chat sessions. - `items: array of object { last_updated_at, session_id, generated_title, 2 more }` Chat sessions for the current page. - `last_updated_at: string` ISO-format timestamp showing when the session was last updated. - `session_id: string` Unique session identifier. - `generated_title: optional string` Auto-generated title derived from the first user message. - `index_ids: optional array of string` Indexes this session is bound to. Null on unbound sessions. - `job_metadata: optional object { duration_ms, error, export_config_ids, 4 more }` Token usage and status from the most recent run. Null if the session has not been run yet. - `duration_ms: optional number` - `error: optional string` - `export_config_ids: optional array of string` - `is_error: optional boolean` - `total_input_tokens: optional number` - `total_output_tokens: optional number` - `turns: optional number` - `next_page_token: optional string` Opaque token to retrieve the next page. Omitted when there are no further pages. ### Example ```cli llp beta:chat list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "last_updated_at": "2026-04-22T12:34:41.342245", "session_id": "ses-abc123", "generated_title": "What were the main findings in Q3?...", "index_ids": [ "idx-abc123", "idx-def456" ], "job_metadata": { "duration_ms": 0, "error": "error", "export_config_ids": [ "string" ], "is_error": true, "total_input_tokens": 0, "total_output_tokens": 0, "turns": 0 } } ], "next_page_token": "next_page_token" } ``` ## Create Session `$ llp beta:chat create` **post** `/api/v1/chat` Create a chat session, optionally bound to indexes (locked after the first message). ### Parameters - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--index-id: optional array of string` Body param: Indexes this session will retrieve from. Once set and the first message has been sent, the source set is locked for the session's lifetime. Leave null to create an unbound session. ### Returns - `BetaChatNewResponse: object { last_updated_at, session_id, generated_title, 2 more }` Summary of a chat session, including its title and last run metadata. - `last_updated_at: string` ISO-format timestamp showing when the session was last updated. - `session_id: string` Unique session identifier. - `generated_title: optional string` Auto-generated title derived from the first user message. - `index_ids: optional array of string` Indexes this session is bound to. Null on unbound sessions. - `job_metadata: optional object { duration_ms, error, export_config_ids, 4 more }` Token usage and status from the most recent run. Null if the session has not been run yet. - `duration_ms: optional number` - `error: optional string` - `export_config_ids: optional array of string` - `is_error: optional boolean` - `total_input_tokens: optional number` - `total_output_tokens: optional number` - `turns: optional number` ### Example ```cli llp beta:chat create \ --api-key 'My API Key' ``` #### Response ```json { "last_updated_at": "2026-04-22T12:34:41.342245", "session_id": "ses-abc123", "generated_title": "What were the main findings in Q3?...", "index_ids": [ "idx-abc123", "idx-def456" ], "job_metadata": { "duration_ms": 0, "error": "error", "export_config_ids": [ "string" ], "is_error": true, "total_input_tokens": 0, "total_output_tokens": 0, "turns": 0 } } ``` ## Get Full Session `$ llp beta:chat retrieve` **get** `/api/v1/chat/{session_id}` Retrieve a full session by ID, including its event history. ### Parameters - `--session-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaChatGetResponse: object { events, last_updated_at, session_id, 3 more }` Full chat session including its complete event history. - `events: array of object { error, is_error, usage, type } or object { content, type } or object { content, type } or 5 more` Ordered list of events that make up the conversation history. - `stop: object { error, is_error, usage, type }` - `error: string` - `is_error: boolean` - `usage: object { duration_ms, total_input_tokens, total_output_tokens, turns }` - `duration_ms: optional number` - `total_input_tokens: optional number` - `total_output_tokens: optional number` - `turns: optional number` - `type: optional "stop"` - `"stop"` - `text_delta: object { content, type }` - `content: string` - `type: optional "text_delta"` - `"text_delta"` - `text: object { content, type }` - `content: string` - `type: optional "text"` - `"text"` - `thinking_delta: object { content, type }` - `content: string` - `type: optional "thinking_delta"` - `"thinking_delta"` - `thinking: object { content, type }` - `content: string` - `type: optional "thinking"` - `"thinking"` - `tool_call: object { arguments, call_id, name, type }` - `arguments: map[unknown]` - `call_id: string` - `name: string` - `type: optional "tool_call"` - `"tool_call"` - `tool_result: object { call_id, name, result, 2 more }` - `call_id: string` - `name: string` - `result: unknown` - `image_attachment: optional object { attachment_name, source_id }` Coordinates for lazily resolving a page screenshot presigned URL. - `attachment_name: string` - `source_id: string` - `type: optional "tool_result"` - `"tool_result"` - `user_input: object { content, type }` - `content: string` - `type: optional "user_input"` - `"user_input"` - `last_updated_at: string` ISO-format timestamp showing when the session was last updated. - `session_id: string` Unique session identifier. - `generated_title: optional string` Auto-generated title derived from the first user message. - `index_ids: optional array of string` Indexes this session is bound to. Null on unbound sessions. - `job_metadata: optional object { duration_ms, error, export_config_ids, 4 more }` Token usage and status from the most recent run. Null if the session has not been run yet. - `duration_ms: optional number` - `error: optional string` - `export_config_ids: optional array of string` - `is_error: optional boolean` - `total_input_tokens: optional number` - `total_output_tokens: optional number` - `turns: optional number` ### Example ```cli llp beta:chat retrieve \ --api-key 'My API Key' \ --session-id session_id ``` #### Response ```json { "events": [ { "error": "error", "is_error": true, "usage": { "duration_ms": 0, "total_input_tokens": 0, "total_output_tokens": 0, "turns": 0 }, "type": "stop" } ], "last_updated_at": "2026-04-22T12:34:41.342245", "session_id": "ses-abc123", "generated_title": "What were the main findings in Q3?...", "index_ids": [ "idx-abc123", "idx-def456" ], "job_metadata": { "duration_ms": 0, "error": "error", "export_config_ids": [ "string" ], "is_error": true, "total_input_tokens": 0, "total_output_tokens": 0, "turns": 0 } } ``` ## Delete Session `$ llp beta:chat delete` **delete** `/api/v1/chat/{session_id}` Delete a session. ### Parameters - `--session-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Example ```cli llp beta:chat delete \ --api-key 'My API Key' \ --session-id session_id ``` ## Get Session Summary `$ llp beta:chat get-summary` **get** `/api/v1/chat/{session_id}/summary` Retrieve a session summary by ID. ### Parameters - `--session-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaChatGetSummaryResponse: object { last_updated_at, session_id, generated_title, 2 more }` Summary of a chat session, including its title and last run metadata. - `last_updated_at: string` ISO-format timestamp showing when the session was last updated. - `session_id: string` Unique session identifier. - `generated_title: optional string` Auto-generated title derived from the first user message. - `index_ids: optional array of string` Indexes this session is bound to. Null on unbound sessions. - `job_metadata: optional object { duration_ms, error, export_config_ids, 4 more }` Token usage and status from the most recent run. Null if the session has not been run yet. - `duration_ms: optional number` - `error: optional string` - `export_config_ids: optional array of string` - `is_error: optional boolean` - `total_input_tokens: optional number` - `total_output_tokens: optional number` - `turns: optional number` ### Example ```cli llp beta:chat get-summary \ --api-key 'My API Key' \ --session-id session_id ``` #### Response ```json { "last_updated_at": "2026-04-22T12:34:41.342245", "session_id": "ses-abc123", "generated_title": "What were the main findings in Q3?...", "index_ids": [ "idx-abc123", "idx-def456" ], "job_metadata": { "duration_ms": 0, "error": "error", "export_config_ids": [ "string" ], "is_error": true, "total_input_tokens": 0, "total_output_tokens": 0, "turns": 0 } } ``` ## Stream Messages `$ llp beta:chat stream` **post** `/api/v1/chat/{session_id}/messages/stream` Stream agent events for a chat turn as Server-Sent Events. ### Parameters - `--session-id: string` Path param - `--index-id: array of string` Body param: Indexes to retrieve data from. - `--prompt: string` Body param: User message for this chat turn. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param ### Returns - `BetaChatStreamResponse: unknown` ### Example ```cli llp beta:chat stream \ --api-key 'My API Key' \ --session-id session_id \ --index-id idx-abc123 \ --index-id idx-def456 \ --prompt 'What were the main findings in Q3?' ``` #### Response ```json {} ``` # Agent Data ## Get Agent Data `$ llp beta:agent-data get` **get** `/api/v1/beta/agent-data/{item_id}` Get agent data by ID. ### Parameters - `--item-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `agent_data: object { data, deployment_name, id, 4 more }` API Result for a single agent data item - `data: map[unknown]` - `deployment_name: string` - `id: optional string` - `collection: optional string` - `created_at: optional string` - `project_id: optional string` - `updated_at: optional string` ### Example ```cli llp beta:agent-data get \ --api-key 'My API Key' \ --item-id item_id ``` #### Response ```json { "data": { "foo": "bar" }, "deployment_name": "deployment_name", "id": "id", "collection": "collection", "created_at": "2019-12-27T18:11:19.117Z", "project_id": "project_id", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Agent Data `$ llp beta:agent-data update` **put** `/api/v1/beta/agent-data/{item_id}` Update agent data by ID (overwrites). ### Parameters - `--item-id: string` Path param - `--data: map[unknown]` Body param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param ### Returns - `agent_data: object { data, deployment_name, id, 4 more }` API Result for a single agent data item - `data: map[unknown]` - `deployment_name: string` - `id: optional string` - `collection: optional string` - `created_at: optional string` - `project_id: optional string` - `updated_at: optional string` ### Example ```cli llp beta:agent-data update \ --api-key 'My API Key' \ --item-id item_id \ --data '{foo: bar}' ``` #### Response ```json { "data": { "foo": "bar" }, "deployment_name": "deployment_name", "id": "id", "collection": "collection", "created_at": "2019-12-27T18:11:19.117Z", "project_id": "project_id", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Agent Data `$ llp beta:agent-data delete` **delete** `/api/v1/beta/agent-data/{item_id}` Delete agent data by ID. ### Parameters - `--item-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaAgentDataDeleteResponse: map[string]` ### Example ```cli llp beta:agent-data delete \ --api-key 'My API Key' \ --item-id item_id ``` #### Response ```json { "foo": "string" } ``` ## Create Agent Data `$ llp beta:agent-data create` **post** `/api/v1/beta/agent-data` Create new agent data. ### Parameters - `--data: map[unknown]` Body param - `--deployment-name: string` Body param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--collection: optional string` Body param ### Returns - `agent_data: object { data, deployment_name, id, 4 more }` API Result for a single agent data item - `data: map[unknown]` - `deployment_name: string` - `id: optional string` - `collection: optional string` - `created_at: optional string` - `project_id: optional string` - `updated_at: optional string` ### Example ```cli llp beta:agent-data create \ --api-key 'My API Key' \ --data '{foo: bar}' \ --deployment-name deployment_name ``` #### Response ```json { "data": { "foo": "bar" }, "deployment_name": "deployment_name", "id": "id", "collection": "collection", "created_at": "2019-12-27T18:11:19.117Z", "project_id": "project_id", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Search Agent Data `$ llp beta:agent-data search` **post** `/api/v1/beta/agent-data/:search` Search agent data with filtering, sorting, and pagination. ### Parameters - `--deployment-name: string` Body param: The agent deployment's name to search within - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--collection: optional string` Body param: The logical agent data collection to search within - `--filter: optional map[object { eq, excludes, gt, 5 more } ]` Body param: A filter object or expression that filters resources listed in the response. - `--include-total: optional boolean` Body param: Whether to include the total number of items in the response - `--offset: optional number` Body param: The offset to start from. If not provided, the first page is returned - `--order-by: optional string` Body param: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. - `--page-size: optional number` Body param: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. - `--page-token: optional string` Body param: A page token, received from a previous list call. Provide this to retrieve the subsequent page. ### Returns - `PaginatedResponse_AgentData_: object { items, next_page_token, total_size }` - `items: array of AgentData` The list of items. - `data: map[unknown]` - `deployment_name: string` - `id: optional string` - `collection: optional string` - `created_at: optional string` - `project_id: optional string` - `updated_at: optional string` - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:agent-data search \ --api-key 'My API Key' \ --deployment-name deployment_name ``` #### Response ```json { "items": [ { "data": { "foo": "bar" }, "deployment_name": "deployment_name", "id": "id", "collection": "collection", "created_at": "2019-12-27T18:11:19.117Z", "project_id": "project_id", "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Aggregate Agent Data `$ llp beta:agent-data aggregate` **post** `/api/v1/beta/agent-data/:aggregate` Aggregate agent data with grouping and optional counting/first item retrieval. ### Parameters - `--deployment-name: string` Body param: The agent deployment's name to aggregate data for - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--collection: optional string` Body param: The logical agent data collection to aggregate data for - `--count: optional boolean` Body param: Whether to count the number of items in each group - `--filter: optional map[object { eq, excludes, gt, 5 more } ]` Body param: A filter object or expression that filters resources listed in the response. - `--first: optional boolean` Body param: Whether to return the first item in each group (Sorted by created_at) - `--group-by: optional array of string` Body param: The fields to group by. If empty, the entire dataset is grouped on. e.g. if left out, can be used for simple count operations - `--offset: optional number` Body param: The offset to start from. If not provided, the first page is returned - `--order-by: optional string` Body param: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. - `--page-size: optional number` Body param: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. - `--page-token: optional string` Body param: A page token, received from a previous list call. Provide this to retrieve the subsequent page. ### Returns - `PaginatedResponse_AggregateGroup_: object { items, next_page_token, total_size }` - `items: array of object { group_key, count, first_item }` The list of items. - `group_key: map[unknown]` - `count: optional number` - `first_item: optional map[unknown]` - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:agent-data aggregate \ --api-key 'My API Key' \ --deployment-name deployment_name ``` #### Response ```json { "items": [ { "group_key": { "foo": "bar" }, "count": 0, "first_item": { "foo": "bar" } } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Delete Agent Data By Query `$ llp beta:agent-data delete-by-query` **post** `/api/v1/beta/agent-data/:delete` Bulk delete agent data by query (deployment_name, collection, optional filters). ### Parameters - `--deployment-name: string` Body param: The agent deployment's name to delete data for - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--collection: optional string` Body param: The logical agent data collection to delete from - `--filter: optional map[object { eq, excludes, gt, 5 more } ]` Body param: Optional filters to select which items to delete ### Returns - `BetaAgentDataDeleteByQueryResponse: object { deleted_count }` API response for bulk delete operation - `deleted_count: number` ### Example ```cli llp beta:agent-data delete-by-query \ --api-key 'My API Key' \ --deployment-name deployment_name ``` #### Response ```json { "deleted_count": 0 } ``` ## Domain Types ### Agent Data - `agent_data: object { data, deployment_name, id, 4 more }` API Result for a single agent data item - `data: map[unknown]` - `deployment_name: string` - `id: optional string` - `collection: optional string` - `created_at: optional string` - `project_id: optional string` - `updated_at: optional string` # Sheets ## Create Spreadsheet Job `$ llp beta:sheets create` **post** `/api/v1/beta/sheets/jobs` Create a spreadsheet parsing job. Provide at most one of `configuration` (an inline parsing configuration) or `configuration_id` (a saved configuration preset). If neither is provided, a default configuration is used. Optionally include `webhook_configurations` to receive `sheets.*` status notifications. ### Parameters - `--file-id: string` Body param: The ID of the file to parse - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--config: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Body param: Configuration for spreadsheet parsing and region extraction - `--configuration: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Body param: Configuration for spreadsheet parsing and region extraction - `--configuration-id: optional string` Body param: Saved configuration ID - `--webhook-configuration: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Body param: Outbound webhook endpoints to notify on job status changes ### Returns - `sheets_job: object { id, configuration, created_at, 14 more }` A spreadsheet parsing job. - `id: string` The ID of the job - `configuration: object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration applied to the parsing job (inline or resolved from a saved preset). - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `"strong"` - `"weak"` - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `"agentic"` - `"cost_effective"` - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `created_at: string` When the job was created - `file_id: string` The ID of the input file - `project_id: string` The ID of the project - `status: "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` The status of the parsing job - `"CANCELLED"` - `"ERROR"` - `"PARTIAL_SUCCESS"` - `"PENDING"` - `"SUCCESS"` - `updated_at: string` When the job was last updated - `user_id: string` The ID of the user - `config: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration for spreadsheet parsing and region extraction - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `configuration_id: optional string` The saved product configuration ID used at create time, if any. - `errors: optional array of string` Any errors encountered - `file: optional object { id, name, project_id, 11 more }` Schema for a file. - `id: string` Unique identifier - `name: string` - `project_id: string` The ID of the project that the file belongs to - `created_at: optional string` Creation datetime - `data_source_id: optional string` The ID of the data source that the file belongs to - `expires_at: optional string` The expiration date for the file. Files past this date can be deleted. - `external_file_id: optional string` The ID of the file in the external system - `file_size: optional number` Size of the file in bytes - `file_type: optional string` File type (e.g. pdf, docx, etc.) - `last_modified_at: optional string` The last modified time of the file - `permission_info: optional map[map[unknown] or array of unknown or string or 2 more]` Permission information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `purpose: optional string` The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') - `resource_info: optional map[map[unknown] or array of unknown or string or 2 more]` Resource information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `updated_at: optional string` Update datetime - `metadata_state_transitions: optional map[unknown]` Per-status entry timestamps. Returned only when requested via `?expand=metadata_state_transitions`. - `parameters: optional object { webhook_configurations }` Job-time parameters such as webhook configurations. - `webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Webhook configurations for job status notifications. - `webhook_events: optional array of "classify.cancelled" or "classify.error" or "classify.partial_success" or 25 more` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `webhook_headers: optional map[string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format: optional string` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret: optional string` 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. - `webhook_url: optional string` URL to receive webhook POST notifications - `regions: optional array of object { location, region_type, sheet_name, 3 more }` All extracted regions (populated when job is complete) - `location: string` Location of the region in the spreadsheet - `region_type: string` Type of the extracted region - `sheet_name: string` Worksheet name where region was found - `description: optional string` Generated description for the region - `region_id: optional string` Unique identifier for this region within the file - `title: optional string` Generated title for the region - `success: optional boolean` Whether the job completed successfully - `worksheet_metadata: optional array of object { sheet_name, description, title }` Metadata for each processed worksheet (populated when job is complete) - `sheet_name: string` Name of the worksheet - `description: optional string` Generated description of the worksheet - `title: optional string` Generated title for the worksheet ### Example ```cli llp beta:sheets create \ --api-key 'My API Key' \ --file-id 182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e ``` #### Response ```json { "id": "id", "configuration": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "created_at": "created_at", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "status": "CANCELLED", "updated_at": "updated_at", "user_id": "user_id", "config": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "configuration_id": "configuration_id", "errors": [ "string" ], "file": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "name": "x", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "expires_at": "2019-12-27T18:11:19.117Z", "external_file_id": "external_file_id", "file_size": 0, "file_type": "x", "last_modified_at": "2019-12-27T18:11:19.117Z", "permission_info": { "foo": { "foo": "bar" } }, "purpose": "purpose", "resource_info": { "foo": { "foo": "bar" } }, "updated_at": "2019-12-27T18:11:19.117Z" }, "metadata_state_transitions": { "foo": "bar" }, "parameters": { "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ] }, "regions": [ { "location": "location", "region_type": "region_type", "sheet_name": "sheet_name", "description": "description", "region_id": "region_id", "title": "title" } ], "success": true, "worksheet_metadata": [ { "sheet_name": "sheet_name", "description": "description", "title": "title" } ] } ``` ## List Spreadsheet Jobs `$ llp beta:sheets list` **get** `/api/v1/beta/sheets/jobs` List spreadsheet parsing jobs. ### Parameters - `--configuration-id: optional string` Filter by saved configuration ID - `--created-at-on-or-after: optional string` Include items created at or after this timestamp (inclusive) - `--created-at-on-or-before: optional string` Include items created at or before this timestamp (inclusive) - `--include-results: optional boolean` - `--job-id: optional array of string` Filter by specific job IDs - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` - `--status: optional "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` Filter by job status ### Returns - `PaginatedResponse_SpreadsheetJob_: object { items, next_page_token, total_size }` - `items: array of SheetsJob` The list of items. - `id: string` The ID of the job - `configuration: object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration applied to the parsing job (inline or resolved from a saved preset). - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `"strong"` - `"weak"` - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `"agentic"` - `"cost_effective"` - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `created_at: string` When the job was created - `file_id: string` The ID of the input file - `project_id: string` The ID of the project - `status: "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` The status of the parsing job - `"CANCELLED"` - `"ERROR"` - `"PARTIAL_SUCCESS"` - `"PENDING"` - `"SUCCESS"` - `updated_at: string` When the job was last updated - `user_id: string` The ID of the user - `config: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration for spreadsheet parsing and region extraction - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `configuration_id: optional string` The saved product configuration ID used at create time, if any. - `errors: optional array of string` Any errors encountered - `file: optional object { id, name, project_id, 11 more }` Schema for a file. - `id: string` Unique identifier - `name: string` - `project_id: string` The ID of the project that the file belongs to - `created_at: optional string` Creation datetime - `data_source_id: optional string` The ID of the data source that the file belongs to - `expires_at: optional string` The expiration date for the file. Files past this date can be deleted. - `external_file_id: optional string` The ID of the file in the external system - `file_size: optional number` Size of the file in bytes - `file_type: optional string` File type (e.g. pdf, docx, etc.) - `last_modified_at: optional string` The last modified time of the file - `permission_info: optional map[map[unknown] or array of unknown or string or 2 more]` Permission information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `purpose: optional string` The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') - `resource_info: optional map[map[unknown] or array of unknown or string or 2 more]` Resource information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `updated_at: optional string` Update datetime - `metadata_state_transitions: optional map[unknown]` Per-status entry timestamps. Returned only when requested via `?expand=metadata_state_transitions`. - `parameters: optional object { webhook_configurations }` Job-time parameters such as webhook configurations. - `webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Webhook configurations for job status notifications. - `webhook_events: optional array of "classify.cancelled" or "classify.error" or "classify.partial_success" or 25 more` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `webhook_headers: optional map[string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format: optional string` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret: optional string` 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. - `webhook_url: optional string` URL to receive webhook POST notifications - `regions: optional array of object { location, region_type, sheet_name, 3 more }` All extracted regions (populated when job is complete) - `location: string` Location of the region in the spreadsheet - `region_type: string` Type of the extracted region - `sheet_name: string` Worksheet name where region was found - `description: optional string` Generated description for the region - `region_id: optional string` Unique identifier for this region within the file - `title: optional string` Generated title for the region - `success: optional boolean` Whether the job completed successfully - `worksheet_metadata: optional array of object { sheet_name, description, title }` Metadata for each processed worksheet (populated when job is complete) - `sheet_name: string` Name of the worksheet - `description: optional string` Generated description of the worksheet - `title: optional string` Generated title for the worksheet - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:sheets list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "id": "id", "configuration": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "created_at": "created_at", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "status": "CANCELLED", "updated_at": "updated_at", "user_id": "user_id", "config": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "configuration_id": "configuration_id", "errors": [ "string" ], "file": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "name": "x", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "expires_at": "2019-12-27T18:11:19.117Z", "external_file_id": "external_file_id", "file_size": 0, "file_type": "x", "last_modified_at": "2019-12-27T18:11:19.117Z", "permission_info": { "foo": { "foo": "bar" } }, "purpose": "purpose", "resource_info": { "foo": { "foo": "bar" } }, "updated_at": "2019-12-27T18:11:19.117Z" }, "metadata_state_transitions": { "foo": "bar" }, "parameters": { "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ] }, "regions": [ { "location": "location", "region_type": "region_type", "sheet_name": "sheet_name", "description": "description", "region_id": "region_id", "title": "title" } ], "success": true, "worksheet_metadata": [ { "sheet_name": "sheet_name", "description": "description", "title": "title" } ] } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Spreadsheet Job `$ llp beta:sheets get` **get** `/api/v1/beta/sheets/jobs/{spreadsheet_job_id}` Get a spreadsheet parsing job. When `include_results=True` (default), embeds extracted regions and results if complete, skipping the separate `/results` call. ### Parameters - `--spreadsheet-job-id: string` - `--expand: optional array of string` Optional fields to populate on the response. Valid values: metadata_state_transitions. - `--include-results: optional boolean` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `sheets_job: object { id, configuration, created_at, 14 more }` A spreadsheet parsing job. - `id: string` The ID of the job - `configuration: object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration applied to the parsing job (inline or resolved from a saved preset). - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `"strong"` - `"weak"` - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `"agentic"` - `"cost_effective"` - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `created_at: string` When the job was created - `file_id: string` The ID of the input file - `project_id: string` The ID of the project - `status: "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` The status of the parsing job - `"CANCELLED"` - `"ERROR"` - `"PARTIAL_SUCCESS"` - `"PENDING"` - `"SUCCESS"` - `updated_at: string` When the job was last updated - `user_id: string` The ID of the user - `config: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration for spreadsheet parsing and region extraction - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `configuration_id: optional string` The saved product configuration ID used at create time, if any. - `errors: optional array of string` Any errors encountered - `file: optional object { id, name, project_id, 11 more }` Schema for a file. - `id: string` Unique identifier - `name: string` - `project_id: string` The ID of the project that the file belongs to - `created_at: optional string` Creation datetime - `data_source_id: optional string` The ID of the data source that the file belongs to - `expires_at: optional string` The expiration date for the file. Files past this date can be deleted. - `external_file_id: optional string` The ID of the file in the external system - `file_size: optional number` Size of the file in bytes - `file_type: optional string` File type (e.g. pdf, docx, etc.) - `last_modified_at: optional string` The last modified time of the file - `permission_info: optional map[map[unknown] or array of unknown or string or 2 more]` Permission information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `purpose: optional string` The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') - `resource_info: optional map[map[unknown] or array of unknown or string or 2 more]` Resource information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `updated_at: optional string` Update datetime - `metadata_state_transitions: optional map[unknown]` Per-status entry timestamps. Returned only when requested via `?expand=metadata_state_transitions`. - `parameters: optional object { webhook_configurations }` Job-time parameters such as webhook configurations. - `webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Webhook configurations for job status notifications. - `webhook_events: optional array of "classify.cancelled" or "classify.error" or "classify.partial_success" or 25 more` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `webhook_headers: optional map[string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format: optional string` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret: optional string` 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. - `webhook_url: optional string` URL to receive webhook POST notifications - `regions: optional array of object { location, region_type, sheet_name, 3 more }` All extracted regions (populated when job is complete) - `location: string` Location of the region in the spreadsheet - `region_type: string` Type of the extracted region - `sheet_name: string` Worksheet name where region was found - `description: optional string` Generated description for the region - `region_id: optional string` Unique identifier for this region within the file - `title: optional string` Generated title for the region - `success: optional boolean` Whether the job completed successfully - `worksheet_metadata: optional array of object { sheet_name, description, title }` Metadata for each processed worksheet (populated when job is complete) - `sheet_name: string` Name of the worksheet - `description: optional string` Generated description of the worksheet - `title: optional string` Generated title for the worksheet ### Example ```cli llp beta:sheets get \ --api-key 'My API Key' \ --spreadsheet-job-id spreadsheet_job_id ``` #### Response ```json { "id": "id", "configuration": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "created_at": "created_at", "file_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "status": "CANCELLED", "updated_at": "updated_at", "user_id": "user_id", "config": { "extraction_range": "extraction_range", "flatten_hierarchical_tables": true, "generate_additional_metadata": true, "include_hidden_cells": true, "sheet_names": [ "string" ], "specialization": "specialization", "table_merge_sensitivity": "strong", "tier": "agentic", "use_experimental_processing": true }, "configuration_id": "configuration_id", "errors": [ "string" ], "file": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "name": "x", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "data_source_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "expires_at": "2019-12-27T18:11:19.117Z", "external_file_id": "external_file_id", "file_size": 0, "file_type": "x", "last_modified_at": "2019-12-27T18:11:19.117Z", "permission_info": { "foo": { "foo": "bar" } }, "purpose": "purpose", "resource_info": { "foo": { "foo": "bar" } }, "updated_at": "2019-12-27T18:11:19.117Z" }, "metadata_state_transitions": { "foo": "bar" }, "parameters": { "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ] }, "regions": [ { "location": "location", "region_type": "region_type", "sheet_name": "sheet_name", "description": "description", "region_id": "region_id", "title": "title" } ], "success": true, "worksheet_metadata": [ { "sheet_name": "sheet_name", "description": "description", "title": "title" } ] } ``` ## Get Result Region `$ llp beta:sheets get-result-table` **get** `/api/v1/beta/sheets/jobs/{spreadsheet_job_id}/regions/{region_id}/result/{region_type}` Generate a presigned URL to download a specific extracted region. ### Parameters - `--spreadsheet-job-id: string` Path param - `--region-id: string` Path param - `--region-type: "cell_metadata" or "extra" or "table"` Path param - `--expires-at-seconds: optional number` Query param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param ### Returns - `presigned_url: object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request ### Example ```cli llp beta:sheets get-result-table \ --api-key 'My API Key' \ --spreadsheet-job-id spreadsheet_job_id \ --region-id region_id \ --region-type cell_metadata ``` #### Response ```json { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } } ``` ## Delete Spreadsheet Job `$ llp beta:sheets delete-job` **delete** `/api/v1/beta/sheets/jobs/{spreadsheet_job_id}` Delete a spreadsheet parsing job and its associated data. ### Parameters - `--spreadsheet-job-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaSheetDeleteJobResponse: unknown` ### Example ```cli llp beta:sheets delete-job \ --api-key 'My API Key' \ --spreadsheet-job-id spreadsheet_job_id ``` #### Response ```json {} ``` ## Domain Types ### Sheets Job - `sheets_job: object { id, configuration, created_at, 14 more }` A spreadsheet parsing job. - `id: string` The ID of the job - `configuration: object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration applied to the parsing job (inline or resolved from a saved preset). - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `"strong"` - `"weak"` - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `"agentic"` - `"cost_effective"` - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `created_at: string` When the job was created - `file_id: string` The ID of the input file - `project_id: string` The ID of the project - `status: "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` The status of the parsing job - `"CANCELLED"` - `"ERROR"` - `"PARTIAL_SUCCESS"` - `"PENDING"` - `"SUCCESS"` - `updated_at: string` When the job was last updated - `user_id: string` The ID of the user - `config: optional object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration for spreadsheet parsing and region extraction - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. - `configuration_id: optional string` The saved product configuration ID used at create time, if any. - `errors: optional array of string` Any errors encountered - `file: optional object { id, name, project_id, 11 more }` Schema for a file. - `id: string` Unique identifier - `name: string` - `project_id: string` The ID of the project that the file belongs to - `created_at: optional string` Creation datetime - `data_source_id: optional string` The ID of the data source that the file belongs to - `expires_at: optional string` The expiration date for the file. Files past this date can be deleted. - `external_file_id: optional string` The ID of the file in the external system - `file_size: optional number` Size of the file in bytes - `file_type: optional string` File type (e.g. pdf, docx, etc.) - `last_modified_at: optional string` The last modified time of the file - `permission_info: optional map[map[unknown] or array of unknown or string or 2 more]` Permission information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `purpose: optional string` The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') - `resource_info: optional map[map[unknown] or array of unknown or string or 2 more]` Resource information for the file - `union_member_0: map[unknown]` - `union_member_1: array of unknown` - `union_member_2: string` - `union_member_3: number` - `union_member_4: boolean` - `updated_at: optional string` Update datetime - `metadata_state_transitions: optional map[unknown]` Per-status entry timestamps. Returned only when requested via `?expand=metadata_state_transitions`. - `parameters: optional object { webhook_configurations }` Job-time parameters such as webhook configurations. - `webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Webhook configurations for job status notifications. - `webhook_events: optional array of "classify.cancelled" or "classify.error" or "classify.partial_success" or 25 more` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `webhook_headers: optional map[string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format: optional string` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret: optional string` 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. - `webhook_url: optional string` URL to receive webhook POST notifications - `regions: optional array of object { location, region_type, sheet_name, 3 more }` All extracted regions (populated when job is complete) - `location: string` Location of the region in the spreadsheet - `region_type: string` Type of the extracted region - `sheet_name: string` Worksheet name where region was found - `description: optional string` Generated description for the region - `region_id: optional string` Unique identifier for this region within the file - `title: optional string` Generated title for the region - `success: optional boolean` Whether the job completed successfully - `worksheet_metadata: optional array of object { sheet_name, description, title }` Metadata for each processed worksheet (populated when job is complete) - `sheet_name: string` Name of the worksheet - `description: optional string` Generated description of the worksheet - `title: optional string` Generated title for the worksheet ### Sheets Parsing Config - `sheets_parsing_config: object { extraction_range, flatten_hierarchical_tables, generate_additional_metadata, 6 more }` Configuration for spreadsheet parsing and region extraction - `extraction_range: optional string` A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `flatten_hierarchical_tables: optional boolean` Return a flattened dataframe when a detected table is recognized as hierarchical. - `generate_additional_metadata: optional boolean` Deprecated: controlled by `tier`. Whether to generate additional metadata (title, description) for each extracted region. Honored only on `agentic`. - `include_hidden_cells: optional boolean` Whether to include hidden cells when extracting regions from the spreadsheet. - `sheet_names: optional array of string` The names of the sheets to extract regions from. If empty, all sheets will be processed. - `specialization: optional string` Deprecated: controlled by `tier`. Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. Honored only on `agentic`. - `table_merge_sensitivity: optional "strong" or "weak"` Deprecated: controlled by `tier`. Influences how likely similar-looking regions are merged into a single table. Honored only on `agentic`. - `"strong"` - `"weak"` - `tier: optional "agentic" or "cost_effective"` Spreadsheet extraction tier. `cost_effective` uses the rule-based/ML-only pipeline; `agentic` uses the full pipeline. - `"agentic"` - `"cost_effective"` - `use_experimental_processing: optional boolean` Deprecated: controlled by `tier`. Enables experimental processing. Honored only on `agentic`. # Directories ## Create Directory `$ llp beta:directories create` **post** `/api/v1/beta/directories` Create a new directory within the specified project. ### Parameters - `--name: string` Body param: Human-readable name for the directory. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--description: optional string` Body param: Optional description shown to users. - `--system-metadata: optional map[unknown]` Body param: Reserved system-managed metadata. - `--type: optional "ephemeral" or "user"` Body param: Directory type. Use 'ephemeral' for batch processing with automatic cleanup. ### Returns - `BetaDirectoryNewResponse: object { id, name, project_id, 7 more }` API response schema for a directory. - `id: string` Unique identifier for the directory. - `name: string` Human-readable name for the directory. - `project_id: string` Project the directory belongs to. - `created_at: optional string` Creation datetime - `deleted_at: optional string` Optional timestamp of when the directory was deleted. Null if not deleted. - `description: optional string` Optional description shown to users. - `expires_at: optional string` When this directory expires and is eligible for cleanup. - `system_metadata: optional map[unknown]` Reserved system-managed metadata. - `type: optional "ephemeral" or "index" or "user"` Directory type: 'user', 'index', or 'ephemeral'. - `"ephemeral"` - `"index"` - `"user"` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories create \ --api-key 'My API Key' \ --name x ``` #### Response ```json { "id": "id", "name": "x", "project_id": "project_id", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "description": "description", "expires_at": "2019-12-27T18:11:19.117Z", "system_metadata": { "foo": "bar" }, "type": "ephemeral", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## List Directories `$ llp beta:directories list` **get** `/api/v1/beta/directories` List Directories ### Parameters - `--include-deleted: optional boolean` Include deleted directories. - `--name: optional string` Directory name to match. - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` - `--type: optional "ephemeral" or "index" or "user"` Directory type to include. - `--type: optional array of "ephemeral" or "index" or "user"` Filter by one or more directory types. Repeat the parameter for multiple values. ### Returns - `DirectoryQueryResponse: object { items, next_page_token, total_size }` API query response schema for directories. - `items: array of object { id, name, project_id, 7 more }` The list of items. - `id: string` Unique identifier for the directory. - `name: string` Human-readable name for the directory. - `project_id: string` Project the directory belongs to. - `created_at: optional string` Creation datetime - `deleted_at: optional string` Optional timestamp of when the directory was deleted. Null if not deleted. - `description: optional string` Optional description shown to users. - `expires_at: optional string` When this directory expires and is eligible for cleanup. - `system_metadata: optional map[unknown]` Reserved system-managed metadata. - `type: optional "ephemeral" or "index" or "user"` Directory type: 'user', 'index', or 'ephemeral'. - `"ephemeral"` - `"index"` - `"user"` - `updated_at: optional string` Update datetime - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:directories list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "id": "id", "name": "x", "project_id": "project_id", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "description": "description", "expires_at": "2019-12-27T18:11:19.117Z", "system_metadata": { "foo": "bar" }, "type": "ephemeral", "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Directory `$ llp beta:directories get` **get** `/api/v1/beta/directories/{directory_id}` Retrieve a directory by its identifier. ### Parameters - `--directory-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaDirectoryGetResponse: object { id, name, project_id, 7 more }` API response schema for a directory. - `id: string` Unique identifier for the directory. - `name: string` Human-readable name for the directory. - `project_id: string` Project the directory belongs to. - `created_at: optional string` Creation datetime - `deleted_at: optional string` Optional timestamp of when the directory was deleted. Null if not deleted. - `description: optional string` Optional description shown to users. - `expires_at: optional string` When this directory expires and is eligible for cleanup. - `system_metadata: optional map[unknown]` Reserved system-managed metadata. - `type: optional "ephemeral" or "index" or "user"` Directory type: 'user', 'index', or 'ephemeral'. - `"ephemeral"` - `"index"` - `"user"` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories get \ --api-key 'My API Key' \ --directory-id directory_id ``` #### Response ```json { "id": "id", "name": "x", "project_id": "project_id", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "description": "description", "expires_at": "2019-12-27T18:11:19.117Z", "system_metadata": { "foo": "bar" }, "type": "ephemeral", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Directory `$ llp beta:directories update` **patch** `/api/v1/beta/directories/{directory_id}` Update directory metadata. ### Parameters - `--directory-id: string` Path param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--description: optional string` Body param: Updated description for the directory. - `--name: optional string` Body param: Updated name for the directory. ### Returns - `BetaDirectoryUpdateResponse: object { id, name, project_id, 7 more }` API response schema for a directory. - `id: string` Unique identifier for the directory. - `name: string` Human-readable name for the directory. - `project_id: string` Project the directory belongs to. - `created_at: optional string` Creation datetime - `deleted_at: optional string` Optional timestamp of when the directory was deleted. Null if not deleted. - `description: optional string` Optional description shown to users. - `expires_at: optional string` When this directory expires and is eligible for cleanup. - `system_metadata: optional map[unknown]` Reserved system-managed metadata. - `type: optional "ephemeral" or "index" or "user"` Directory type: 'user', 'index', or 'ephemeral'. - `"ephemeral"` - `"index"` - `"user"` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories update \ --api-key 'My API Key' \ --directory-id directory_id ``` #### Response ```json { "id": "id", "name": "x", "project_id": "project_id", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "description": "description", "expires_at": "2019-12-27T18:11:19.117Z", "system_metadata": { "foo": "bar" }, "type": "ephemeral", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Directory `$ llp beta:directories delete` **delete** `/api/v1/beta/directories/{directory_id}` Permanently delete a directory. ### Parameters - `--directory-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Example ```cli llp beta:directories delete \ --api-key 'My API Key' \ --directory-id directory_id ``` # Files ## Add Directory File `$ llp beta:directories:files add` **post** `/api/v1/beta/directories/{directory_id}/files` Create a new file within the specified directory; the directory must exist in the project and `file_id` must reference an existing file. ### Parameters - `--directory-id: string` Path param - `--file-id: string` Body param: File ID for the storage location (required). - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--display-name: optional string` Body param: Display name for the file. If not provided, will use the file's name. - `--metadata: optional map[string or number or number or 3 more]` Body param: User-defined metadata key-value pairs to associate with the file. - `--unique-id: optional string` Body param: Unique identifier for the file in the directory. If not provided, will use the file's external_file_id or name. ### Returns - `BetaDirectoryFileAddResponse: object { id, directory_id, display_name, 8 more }` API response schema for a directory file. - `id: string` Unique identifier for the directory file. - `directory_id: string` Directory the file belongs to. - `display_name: string` Display name for the file. - `project_id: string` Project the directory file belongs to. - `unique_id: string` Unique identifier for the file in the directory - `created_at: optional string` Creation datetime - `deleted_at: optional string` Soft delete marker when the file is removed upstream or by user action. - `download_url: optional object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request - `file_id: optional string` File ID for the storage location. - `metadata: optional map[string or number or number or 3 more]` Merged metadata from all sources. Higher-priority sources override lower. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories:files add \ --api-key 'My API Key' \ --directory-id directory_id \ --file-id file_id ``` #### Response ```json { "id": "id", "directory_id": "directory_id", "display_name": "x", "project_id": "project_id", "unique_id": "x", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "download_url": { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } }, "file_id": "file_id", "metadata": { "foo": "string" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## List Directory Files `$ llp beta:directories:files list` **get** `/api/v1/beta/directories/{directory_id}/files` List all files within the specified directory with optional filtering and pagination. ### Parameters - `--directory-id: string` - `--display-name: optional string` - `--display-name-contains: optional string` - `--expand: optional array of string` Fields to expand on each directory file. - `--file-id: optional string` - `--include-deleted: optional boolean` - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` - `--unique-id: optional string` - `--updated-at-on-or-after: optional string` Include items updated at or after this timestamp (inclusive) - `--updated-at-on-or-before: optional string` Include items updated at or before this timestamp (inclusive) ### Returns - `DirectoryFileQueryResponse: object { items, next_page_token, total_size }` API query response schema for directory files. - `items: array of object { id, directory_id, display_name, 8 more }` The list of items. - `id: string` Unique identifier for the directory file. - `directory_id: string` Directory the file belongs to. - `display_name: string` Display name for the file. - `project_id: string` Project the directory file belongs to. - `unique_id: string` Unique identifier for the file in the directory - `created_at: optional string` Creation datetime - `deleted_at: optional string` Soft delete marker when the file is removed upstream or by user action. - `download_url: optional object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request - `file_id: optional string` File ID for the storage location. - `metadata: optional map[string or number or number or 3 more]` Merged metadata from all sources. Higher-priority sources override lower. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `updated_at: optional string` Update datetime - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:directories:files list \ --api-key 'My API Key' \ --directory-id directory_id ``` #### Response ```json { "items": [ { "id": "id", "directory_id": "directory_id", "display_name": "x", "project_id": "project_id", "unique_id": "x", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "download_url": { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } }, "file_id": "file_id", "metadata": { "foo": "string" }, "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Directory File `$ llp beta:directories:files get` **get** `/api/v1/beta/directories/{directory_id}/files/{directory_file_id}` Get a directory file by `directory_file_id`; to look up by `unique_id`, use the list endpoint with a filter. ### Parameters - `--directory-id: string` Path param - `--directory-file-id: string` Path param - `--expand: optional array of string` Query param: Fields to expand. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param ### Returns - `BetaDirectoryFileGetResponse: object { id, directory_id, display_name, 8 more }` API response schema for a directory file. - `id: string` Unique identifier for the directory file. - `directory_id: string` Directory the file belongs to. - `display_name: string` Display name for the file. - `project_id: string` Project the directory file belongs to. - `unique_id: string` Unique identifier for the file in the directory - `created_at: optional string` Creation datetime - `deleted_at: optional string` Soft delete marker when the file is removed upstream or by user action. - `download_url: optional object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request - `file_id: optional string` File ID for the storage location. - `metadata: optional map[string or number or number or 3 more]` Merged metadata from all sources. Higher-priority sources override lower. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories:files get \ --api-key 'My API Key' \ --directory-id directory_id \ --directory-file-id directory_file_id ``` #### Response ```json { "id": "id", "directory_id": "directory_id", "display_name": "x", "project_id": "project_id", "unique_id": "x", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "download_url": { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } }, "file_id": "file_id", "metadata": { "foo": "string" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Update Directory File `$ llp beta:directories:files update` **patch** `/api/v1/beta/directories/{directory_id}/files/{directory_file_id}` Update directory-file metadata by `directory_file_id`; set `directory_id` to move the file to a different directory. To resolve from `unique_id`, list with a filter first. ### Parameters - `--directory-id: string` Path param - `--directory-file-id: string` Path param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--display-name: optional string` Body param: Updated display name. - `--metadata: optional map[string or number or number or 3 more]` Body param: User-defined metadata key-value pairs. Replaces the user metadata layer. - `--target-directory-id: optional string` Body param: Move file to a different directory. - `--unique-id: optional string` Body param: Updated unique identifier. ### Returns - `BetaDirectoryFileUpdateResponse: object { id, directory_id, display_name, 8 more }` API response schema for a directory file. - `id: string` Unique identifier for the directory file. - `directory_id: string` Directory the file belongs to. - `display_name: string` Display name for the file. - `project_id: string` Project the directory file belongs to. - `unique_id: string` Unique identifier for the file in the directory - `created_at: optional string` Creation datetime - `deleted_at: optional string` Soft delete marker when the file is removed upstream or by user action. - `download_url: optional object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request - `file_id: optional string` File ID for the storage location. - `metadata: optional map[string or number or number or 3 more]` Merged metadata from all sources. Higher-priority sources override lower. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories:files update \ --api-key 'My API Key' \ --directory-id directory_id \ --directory-file-id directory_file_id ``` #### Response ```json { "id": "id", "directory_id": "directory_id", "display_name": "x", "project_id": "project_id", "unique_id": "x", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "download_url": { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } }, "file_id": "file_id", "metadata": { "foo": "string" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Delete Directory File `$ llp beta:directories:files delete` **delete** `/api/v1/beta/directories/{directory_id}/files/{directory_file_id}` Delete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first. ### Parameters - `--directory-id: string` Path param - `--directory-file-id: string` Path param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param ### Example ```cli llp beta:directories:files delete \ --api-key 'My API Key' \ --directory-id directory_id \ --directory-file-id directory_file_id ``` ## Upload File To Directory `$ llp beta:directories:files upload` **post** `/api/v1/beta/directories/{directory_id}/files/upload` Upload a file and create its directory entry in one call; `unique_id` / `display_name` default to values derived from file metadata. ### Parameters - `--directory-id: string` Path param - `--upload-file: string` Body param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--display-name: optional string` Body param - `--external-file-id: optional string` Body param - `--metadata: optional string` Body param: User metadata as a JSON object string. - `--unique-id: optional string` Body param ### Returns - `BetaDirectoryFileUploadResponse: object { id, directory_id, display_name, 8 more }` API response schema for a directory file. - `id: string` Unique identifier for the directory file. - `directory_id: string` Directory the file belongs to. - `display_name: string` Display name for the file. - `project_id: string` Project the directory file belongs to. - `unique_id: string` Unique identifier for the file in the directory - `created_at: optional string` Creation datetime - `deleted_at: optional string` Soft delete marker when the file is removed upstream or by user action. - `download_url: optional object { expires_at, url, form_fields }` Schema for a presigned URL. - `expires_at: string` The time at which the presigned URL expires - `url: string` A presigned URL for IO operations against a private file - `form_fields: optional map[string]` Form fields for a presigned POST request - `file_id: optional string` File ID for the storage location. - `metadata: optional map[string or number or number or 3 more]` Merged metadata from all sources. Higher-priority sources override lower. - `union_member_0: string` - `union_member_1: number` - `union_member_2: number` - `union_member_3: boolean` - `union_member_4: unknown` - `MetadataListValue: array of string` - `updated_at: optional string` Update datetime ### Example ```cli llp beta:directories:files upload \ --api-key 'My API Key' \ --directory-id directory_id \ --upload-file 'Example data' ``` #### Response ```json { "id": "id", "directory_id": "directory_id", "display_name": "x", "project_id": "project_id", "unique_id": "x", "created_at": "2019-12-27T18:11:19.117Z", "deleted_at": "2019-12-27T18:11:19.117Z", "download_url": { "expires_at": "2019-12-27T18:11:19.117Z", "url": "https://example.com", "form_fields": { "foo": "string" } }, "file_id": "file_id", "metadata": { "foo": "string" }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` # Batch ## Create Batch Job `$ llp beta:batch create` **post** `/api/v1/beta/batch-processing` Create a batch processing job. Processes files from a directory or a specific list of item IDs. Supports batch parsing and classification operations. Provide either `directory_id` to process all files in a directory, or `item_ids` for specific items. The job runs asynchronously — poll `GET /batch/{job_id}` for progress. ### Parameters - `--job-config: object { correlation_id, job_name, parameters, 6 more } or ClassifyJob` Body param: Job configuration — either a parse or classify config - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--continue-as-new-threshold: optional number` Body param: Maximum files to process per execution cycle in directory mode. Defaults to page_size. - `--directory-id: optional string` Body param: ID of the directory containing files to process - `--item-id: optional array of string` Body param: List of specific item IDs to process. Either this or directory_id must be provided. - `--page-size: optional number` Body param: Number of files to process per batch when using directory mode - `--temporal-namespace: optional string` Header param ### Returns - `BetaBatchNewResponse: object { id, job_type, project_id, 14 more }` Response schema for a batch processing job. - `id: string` Unique identifier for the batch job - `job_type: "classify" or "extract" or "parse"` Type of processing operation (parse or classify) - `"classify"` - `"extract"` - `"parse"` - `project_id: string` Project this job belongs to - `status: "cancelled" or "completed" or "dispatched" or 3 more` Current job status - `"cancelled"` - `"completed"` - `"dispatched"` - `"failed"` - `"pending"` - `"running"` - `total_items: number` Total number of items in the job - `completed_at: optional string` Timestamp when job completed - `created_at: optional string` Creation datetime - `directory_id: optional string` Directory being processed - `effective_at: optional string` - `error_message: optional string` Error message for the latest job attempt, if any. - `failed_items: optional number` Number of items that failed processing - `job_record_id: optional string` The job record ID associated with this status, if any. - `processed_items: optional number` Number of items processed so far - `skipped_items: optional number` Number of items skipped (already processed or size limit) - `started_at: optional string` Timestamp when job processing started - `updated_at: optional string` Update datetime - `workflow_id: optional string` Async job tracking ID ### Example ```cli llp beta:batch create \ --api-key 'My API Key' \ --job-config '{}' ``` #### Response ```json { "id": "bjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "job_type": "classify", "project_id": "proj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "cancelled", "total_items": 0, "completed_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "directory_id": "dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "effective_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "failed_items": 0, "job_record_id": "job_record_id", "processed_items": 0, "skipped_items": 0, "started_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z", "workflow_id": "workflow_id" } ``` ## List Batch Jobs `$ llp beta:batch list` **get** `/api/v1/beta/batch-processing` List batch processing jobs with optional filtering. Filter by `directory_id`, `job_type`, or `status`. Results are paginated with configurable `limit` and `offset`. ### Parameters - `--directory-id: optional string` Filter by directory ID - `--job-type: optional "classify" or "extract" or "parse"` Filter by job type (PARSE, EXTRACT, CLASSIFY) - `--limit: optional number` Maximum number of jobs to return - `--offset: optional number` Number of jobs to skip for pagination - `--organization-id: optional string` - `--project-id: optional string` - `--status: optional "cancelled" or "completed" or "dispatched" or 3 more` Filter by job status (PENDING, RUNNING, COMPLETED, FAILED, CANCELLED) ### Returns - `BatchJobQueryResponse: object { items, next_page_token, total_size }` Response schema for paginated batch job queries. - `items: array of object { id, job_type, project_id, 14 more }` The list of items. - `id: string` Unique identifier for the batch job - `job_type: "classify" or "extract" or "parse"` Type of processing operation (parse or classify) - `"classify"` - `"extract"` - `"parse"` - `project_id: string` Project this job belongs to - `status: "cancelled" or "completed" or "dispatched" or 3 more` Current job status - `"cancelled"` - `"completed"` - `"dispatched"` - `"failed"` - `"pending"` - `"running"` - `total_items: number` Total number of items in the job - `completed_at: optional string` Timestamp when job completed - `created_at: optional string` Creation datetime - `directory_id: optional string` Directory being processed - `effective_at: optional string` - `error_message: optional string` Error message for the latest job attempt, if any. - `failed_items: optional number` Number of items that failed processing - `job_record_id: optional string` The job record ID associated with this status, if any. - `processed_items: optional number` Number of items processed so far - `skipped_items: optional number` Number of items skipped (already processed or size limit) - `started_at: optional string` Timestamp when job processing started - `updated_at: optional string` Update datetime - `workflow_id: optional string` Async job tracking ID - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:batch list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "id": "bjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "job_type": "classify", "project_id": "proj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "cancelled", "total_items": 0, "completed_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "directory_id": "dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "effective_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "failed_items": 0, "job_record_id": "job_record_id", "processed_items": 0, "skipped_items": 0, "started_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z", "workflow_id": "workflow_id" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Batch Job Status `$ llp beta:batch get-status` **get** `/api/v1/beta/batch-processing/{job_id}` Get detailed status of a batch processing job. Returns current progress percentage, file counts (total, processed, failed, skipped), and timestamps. ### Parameters - `--job-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaBatchGetStatusResponse: object { job, progress_percentage }` Detailed status response for a batch processing job. - `job: object { id, job_type, project_id, 14 more }` Response schema for a batch processing job. - `id: string` Unique identifier for the batch job - `job_type: "classify" or "extract" or "parse"` Type of processing operation (parse or classify) - `"classify"` - `"extract"` - `"parse"` - `project_id: string` Project this job belongs to - `status: "cancelled" or "completed" or "dispatched" or 3 more` Current job status - `"cancelled"` - `"completed"` - `"dispatched"` - `"failed"` - `"pending"` - `"running"` - `total_items: number` Total number of items in the job - `completed_at: optional string` Timestamp when job completed - `created_at: optional string` Creation datetime - `directory_id: optional string` Directory being processed - `effective_at: optional string` - `error_message: optional string` Error message for the latest job attempt, if any. - `failed_items: optional number` Number of items that failed processing - `job_record_id: optional string` The job record ID associated with this status, if any. - `processed_items: optional number` Number of items processed so far - `skipped_items: optional number` Number of items skipped (already processed or size limit) - `started_at: optional string` Timestamp when job processing started - `updated_at: optional string` Update datetime - `workflow_id: optional string` Async job tracking ID - `progress_percentage: number` Percentage of items processed (0-100) ### Example ```cli llp beta:batch get-status \ --api-key 'My API Key' \ --job-id job_id ``` #### Response ```json { "job": { "id": "bjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "job_type": "classify", "project_id": "proj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "status": "cancelled", "total_items": 0, "completed_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "directory_id": "dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", "effective_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "failed_items": 0, "job_record_id": "job_record_id", "processed_items": 0, "skipped_items": 0, "started_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z", "workflow_id": "workflow_id" }, "progress_percentage": 0 } ``` ## Cancel Batch Job `$ llp beta:batch cancel` **post** `/api/v1/beta/batch-processing/{job_id}/cancel` Cancel a running batch processing job. Stops processing and marks pending items as cancelled. Items currently being processed may still complete. ### Parameters - `--job-id: string` Path param - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--reason: optional string` Body param: Optional reason for cancelling the job - `--temporal-namespace: optional string` Header param ### Returns - `BetaBatchCancelResponse: object { job_id, message, processed_items, status }` Response after cancelling a batch job. - `job_id: string` ID of the cancelled job - `message: string` Confirmation message - `processed_items: number` Number of items processed before cancellation - `status: "cancelled" or "completed" or "dispatched" or 3 more` New status (should be 'cancelled') - `"cancelled"` - `"completed"` - `"dispatched"` - `"failed"` - `"pending"` - `"running"` ### Example ```cli llp beta:batch cancel \ --api-key 'My API Key' \ --job-id job_id ``` #### Response ```json { "job_id": "job_id", "message": "message", "processed_items": 0, "status": "cancelled" } ``` # Job Items ## List Batch Job Items `$ llp beta:batch:job-items list` **get** `/api/v1/beta/batch-processing/{job_id}/items` List items in a batch job with optional status filtering. Useful for finding failed items, viewing completed items, or debugging processing issues. ### Parameters - `--job-id: string` - `--limit: optional number` Maximum number of items to return - `--offset: optional number` Number of items to skip - `--organization-id: optional string` - `--project-id: optional string` - `--status: optional "cancelled" or "completed" or "failed" or 3 more` Filter items by status ### Returns - `BatchItemListResponse: object { items, next_page_token, total_size }` Paginated response containing batch job item details. - `items: optional array of object { item_id, item_name, status, 7 more }` List of item details - `item_id: string` ID of the item - `item_name: string` Name of the item - `status: "cancelled" or "completed" or "failed" or 3 more` Processing status of this item - `"cancelled"` - `"completed"` - `"failed"` - `"pending"` - `"processing"` - `"skipped"` - `completed_at: optional string` When processing completed for this item - `effective_at: optional string` - `error_message: optional string` Error message for the latest job attempt, if any. - `job_id: optional string` Job ID for the underlying processing job (links to parse/extract job results) - `job_record_id: optional string` The job record ID associated with this status, if any. - `skip_reason: optional string` Reason item was skipped (e.g., 'already_processed', 'size_limit_exceeded') - `started_at: optional string` When processing started for this item - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:batch:job-items list \ --api-key 'My API Key' \ --job-id job_id ``` #### Response ```json { "items": [ { "item_id": "item_id", "item_name": "item_name", "status": "cancelled", "completed_at": "2019-12-27T18:11:19.117Z", "effective_at": "2019-12-27T18:11:19.117Z", "error_message": "error_message", "job_id": "job_id", "job_record_id": "job_record_id", "skip_reason": "skip_reason", "started_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Item Processing Results `$ llp beta:batch:job-items get-processing-results` **get** `/api/v1/beta/batch-processing/items/{item_id}/processing-results` Get all processing results for a specific item. Returns the complete processing history for an item including what operations were performed, parameters used, and where outputs are stored. Optionally filter by `job_type`. ### Parameters - `--item-id: string` - `--job-type: optional "classify" or "extract" or "parse"` Filter results by job type - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaBatchJobItemGetProcessingResultsResponse: object { item_id, item_name, processing_results }` Response containing all processing results for an item. - `item_id: string` ID of the source item - `item_name: string` Name of the source item - `processing_results: optional array of object { item_id, job_config, job_type, 5 more }` List of all processing operations performed on this item - `item_id: string` Source item that was processed - `job_config: object { correlation_id, job_name, parameters, 6 more } or ClassifyJob` Job configuration used for processing - `BatchParseJobRecordCreate: object { correlation_id, job_name, parameters, 6 more }` Batch-specific parse job record for batch processing. This model contains the metadata and configuration for a batch parse job, but excludes file-specific information. It's used as input to the batch parent workflow and combined with DirectoryFile data to create full ParseJobRecordCreate instances for each file. Attributes: job_name: Must be PARSE_RAW_FILE partitions: Partitions for job output location parameters: Generic parse configuration (BatchParseJobConfig) session_id: Upstream request ID for tracking correlation_id: Correlation ID for cross-service tracking parent_job_execution_id: Parent job execution ID if nested user_id: User who created the job project_id: Project this job belongs to webhook_url: Optional webhook URL for job completion notifications - `correlation_id: optional string` The correlation ID for this job. Used for tracking the job across services. - `job_name: optional "parse_raw_file_job"` - `"parse_raw_file_job"` - `parameters: optional object { adaptive_long_table, aggressive_table_extraction, annotate_links, 123 more }` Generic parse job configuration for batch processing. This model contains the parsing configuration that applies to all files in a batch, but excludes file-specific fields like file_name, file_id, etc. Those file-specific fields are populated from DirectoryFile data when creating individual ParseJobRecordCreate instances for each file. The fields in this model should be generic settings that apply uniformly to all files being processed in the batch. - `adaptive_long_table: optional boolean` - `aggressive_table_extraction: optional boolean` - `annotate_links: optional boolean` - `auto_mode: optional boolean` - `auto_mode_configuration_json: optional string` - `auto_mode_trigger_on_image_in_page: optional boolean` - `auto_mode_trigger_on_regexp_in_page: optional string` - `auto_mode_trigger_on_table_in_page: optional boolean` - `auto_mode_trigger_on_text_in_page: optional string` - `azure_openai_api_version: optional string` - `azure_openai_deployment_name: optional string` - `azure_openai_endpoint: optional string` - `azure_openai_key: optional string` - `bbox_bottom: optional number` - `bbox_left: optional number` - `bbox_right: optional number` - `bbox_top: optional number` - `bounding_box: optional string` - `compact_markdown_table: optional boolean` - `complemental_formatting_instruction: optional string` - `confidence_score_effort: optional string` - `content_guideline_instruction: optional string` - `continuous_mode: optional boolean` - `custom_metadata: optional map[unknown]` The custom metadata to attach to the documents. - `disable_image_extraction: optional boolean` - `disable_ocr: optional boolean` - `disable_reconstruction: optional boolean` - `do_not_cache: optional boolean` - `do_not_unroll_columns: optional boolean` - `enable_cost_optimizer: optional boolean` - `extract_charts: optional boolean` - `extract_layout: optional boolean` - `extract_printed_page_number: optional boolean` - `fast_mode: optional boolean` - `formatting_instruction: optional string` - `gpt4o_api_key: optional string` - `gpt4o_mode: optional boolean` - `guess_xlsx_sheet_name: optional boolean` - `hide_footers: optional boolean` - `hide_headers: optional boolean` - `high_res_ocr: optional boolean` - `html_make_all_elements_visible: optional boolean` - `html_remove_fixed_elements: optional boolean` - `html_remove_navigation_elements: optional boolean` - `http_proxy: optional string` - `ignore_document_elements_for_layout_detection: optional boolean` - `images_to_save: optional array of "embedded" or "layout" or "screenshot"` - `"embedded"` - `"layout"` - `"screenshot"` - `inline_images_in_markdown: optional boolean` - `input_s3_path: optional string` - `input_s3_region: optional string` The region for the input S3 bucket. - `input_url: optional string` - `internal_is_screenshot_job: optional boolean` - `invalidate_cache: optional boolean` - `is_formatting_instruction: optional boolean` - `job_timeout_extra_time_per_page_in_seconds: optional number` - `job_timeout_in_seconds: optional number` - `keep_page_separator_when_merging_tables: optional boolean` - `lang: optional string` The language. - `languages: optional array of ParsingLanguages` - `"abq"` - `"ady"` - `"af"` - `"ang"` - `"ar"` - `"as"` - `"ava"` - `"az"` - `"be"` - `"bg"` - `"bgc"` - `"bh"` - `"bho"` - `"bn"` - `"bs"` - `"ch_sim"` - `"ch_tra"` - `"che"` - `"cs"` - `"cy"` - `"da"` - `"dar"` - `"de"` - `"en"` - `"es"` - `"et"` - `"fa"` - `"fr"` - `"ga"` - `"gom"` - `"hi"` - `"hr"` - `"hu"` - `"id"` - `"inh"` - `"is"` - `"it"` - `"ja"` - `"kbd"` - `"kn"` - `"ko"` - `"ku"` - `"la"` - `"lbe"` - `"lez"` - `"lt"` - `"lv"` - `"mah"` - `"mai"` - `"mi"` - `"mn"` - `"mni"` - `"mr"` - `"ms"` - `"mt"` - `"ne"` - `"new"` - `"nl"` - `"no"` - `"oc"` - `"pi"` - `"pl"` - `"pt"` - `"ro"` - `"rs_cyrillic"` - `"rs_latin"` - `"ru"` - `"sa"` - `"sck"` - `"sk"` - `"sl"` - `"sq"` - `"sv"` - `"sw"` - `"ta"` - `"tab"` - `"te"` - `"th"` - `"tjk"` - `"tl"` - `"tr"` - `"ug"` - `"uk"` - `"ur"` - `"uz"` - `"vi"` - `layout_aware: optional boolean` - `line_level_bounding_box: optional boolean` - `markdown_table_multiline_header_separator: optional string` - `max_pages: optional number` - `max_pages_enforced: optional number` - `merge_tables_across_pages_in_markdown: optional boolean` - `model: optional string` - `outlined_table_extraction: optional boolean` - `output_pdf_of_document: optional boolean` - `output_s3_path_prefix: optional string` If specified, llamaParse will save the output to the specified path. All output file will use this 'prefix' should be a valid s3:// url - `output_s3_region: optional string` The region for the output S3 bucket. - `output_tables_as_HTML: optional boolean` - `outputBucket: optional string` The output bucket. - `page_error_tolerance: optional number` - `page_footer_prefix: optional string` - `page_footer_suffix: optional string` - `page_header_prefix: optional string` - `page_header_suffix: optional string` - `page_prefix: optional string` - `page_separator: optional string` - `page_suffix: optional string` - `parse_mode: optional "parse_document_with_agent" or "parse_document_with_llm" or "parse_document_with_lvm" or 5 more` Enum for representing the mode of parsing to be used. - `"parse_document_with_agent"` - `"parse_document_with_llm"` - `"parse_document_with_lvm"` - `"parse_page_with_agent"` - `"parse_page_with_layout_agent"` - `"parse_page_with_llm"` - `"parse_page_with_lvm"` - `"parse_page_without_llm"` - `parsing_instruction: optional string` - `pipeline_id: optional string` The pipeline ID. - `precise_bounding_box: optional boolean` - `premium_mode: optional boolean` - `presentation_out_of_bounds_content: optional boolean` - `presentation_skip_embedded_data: optional boolean` - `preserve_layout_alignment_across_pages: optional boolean` - `preserve_very_small_text: optional boolean` - `preset: optional string` - `priority: optional "critical" or "high" or "low" or "medium"` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `"critical"` - `"high"` - `"low"` - `"medium"` - `project_id: optional string` - `remove_hidden_text: optional boolean` - `replace_failed_page_mode: optional "blank_page" or "error_message" or "raw_text"` Enum for representing the different available page error handling modes. - `"blank_page"` - `"error_message"` - `"raw_text"` - `replace_failed_page_with_error_message_prefix: optional string` - `replace_failed_page_with_error_message_suffix: optional string` - `resource_info: optional map[unknown]` The resource info about the file - `save_images: optional boolean` - `skip_diagonal_text: optional boolean` - `specialized_chart_parsing_agentic: optional boolean` - `specialized_chart_parsing_efficient: optional boolean` - `specialized_chart_parsing_plus: optional boolean` - `specialized_image_parsing: optional boolean` - `spreadsheet_extract_sub_tables: optional boolean` - `spreadsheet_force_formula_computation: optional boolean` - `spreadsheet_include_hidden_sheets: optional boolean` - `strict_mode_buggy_font: optional boolean` - `strict_mode_image_extraction: optional boolean` - `strict_mode_image_ocr: optional boolean` - `strict_mode_reconstruction: optional boolean` - `structured_output: optional boolean` - `structured_output_json_schema: optional string` - `structured_output_json_schema_name: optional string` - `system_prompt: optional string` - `system_prompt_append: optional string` - `take_screenshot: optional boolean` - `target_pages: optional string` - `tier: optional string` - `type: optional "parse"` - `"parse"` - `use_vendor_multimodal_model: optional boolean` - `user_prompt: optional string` - `vendor_multimodal_api_key: optional string` - `vendor_multimodal_model_name: optional string` - `version: optional string` - `webhook_configurations: optional array of object { webhook_events, webhook_headers, webhook_output_format, 2 more }` Outbound webhook endpoints to notify on job status changes - `webhook_events: optional array of "classify.cancelled" or "classify.error" or "classify.partial_success" or 25 more` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `webhook_headers: optional map[string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format: optional string` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret: optional string` 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. - `webhook_url: optional string` URL to receive webhook POST notifications - `webhook_url: optional string` - `parent_job_execution_id: optional string` The ID of the parent job execution. - `partitions: optional map[string]` The partitions for this execution. Used for determining where to save job output. - `project_id: optional string` The ID of the project this job belongs to. - `session_id: optional string` The upstream request ID that created this job. Used for tracking the job across services. - `user_id: optional string` The ID of the user that created this job - `webhook_url: optional string` The URL that needs to be called at the end of the parsing job. - `classify_job: object { id, project_id, rules, 9 more }` A classify job. - `id: string` Unique identifier - `project_id: string` The ID of the project - `rules: array of ClassifierRule` The rules to classify the files - `description: string` Natural language description of what to classify. Be specific about the content characteristics that identify this document type. - `type: string` The document type to assign when this rule matches (e.g., 'invoice', 'receipt', 'contract') - `status: "CANCELLED" or "ERROR" or "PARTIAL_SUCCESS" or 2 more` The status of the classify job - `"CANCELLED"` - `"ERROR"` - `"PARTIAL_SUCCESS"` - `"PENDING"` - `"SUCCESS"` - `user_id: string` The ID of the user - `created_at: optional string` Creation datetime - `effective_at: optional string` - `error_message: optional string` Error message for the latest job attempt, if any. - `job_record_id: optional string` The job record ID associated with this status, if any. - `mode: optional "FAST" or "MULTIMODAL"` The classification mode to use - `"FAST"` - `"MULTIMODAL"` - `parsing_configuration: optional object { lang, max_pages, target_pages }` The configuration for the parsing job - `lang: optional "abq" or "ady" or "af" or 83 more` The language to parse the files in - `"abq"` - `"ady"` - `"af"` - `"ang"` - `"ar"` - `"as"` - `"ava"` - `"az"` - `"be"` - `"bg"` - `"bgc"` - `"bh"` - `"bho"` - `"bn"` - `"bs"` - `"ch_sim"` - `"ch_tra"` - `"che"` - `"cs"` - `"cy"` - `"da"` - `"dar"` - `"de"` - `"en"` - `"es"` - `"et"` - `"fa"` - `"fr"` - `"ga"` - `"gom"` - `"hi"` - `"hr"` - `"hu"` - `"id"` - `"inh"` - `"is"` - `"it"` - `"ja"` - `"kbd"` - `"kn"` - `"ko"` - `"ku"` - `"la"` - `"lbe"` - `"lez"` - `"lt"` - `"lv"` - `"mah"` - `"mai"` - `"mi"` - `"mn"` - `"mni"` - `"mr"` - `"ms"` - `"mt"` - `"ne"` - `"new"` - `"nl"` - `"no"` - `"oc"` - `"pi"` - `"pl"` - `"pt"` - `"ro"` - `"rs_cyrillic"` - `"rs_latin"` - `"ru"` - `"sa"` - `"sck"` - `"sk"` - `"sl"` - `"sq"` - `"sv"` - `"sw"` - `"ta"` - `"tab"` - `"te"` - `"th"` - `"tjk"` - `"tl"` - `"tr"` - `"ug"` - `"uk"` - `"ur"` - `"uz"` - `"vi"` - `max_pages: optional number` The maximum number of pages to parse - `target_pages: optional array of number` The pages to target for parsing (0-indexed, so first page is at 0) - `updated_at: optional string` Update datetime - `job_type: "classify" or "extract" or "parse"` Type of processing performed - `"classify"` - `"extract"` - `"parse"` - `output_s3_path: string` Location of the processing output - `parameters_hash: string` Content hash of the job configuration for dedup - `processed_at: string` When this processing occurred - `result_id: string` Unique identifier for this result - `output_metadata: optional unknown` Metadata about processing output. Currently empty - will be populated with job-type-specific metadata fields in the future. ### Example ```cli llp beta:batch:job-items get-processing-results \ --api-key 'My API Key' \ --item-id item_id ``` #### Response ```json { "item_id": "item_id", "item_name": "item_name", "processing_results": [ { "item_id": "item_id", "job_config": { "correlation_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "job_name": "parse_raw_file_job", "parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "confidence_score_effort": "confidence_score_effort", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "custom_metadata": { "foo": "bar" }, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "embedded" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "lang": "lang", "languages": [ "abq" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "outputBucket": "outputBucket", "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_document_with_agent", "parsing_instruction": "parsing_instruction", "pipeline_id": "pipeline_id", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "critical", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "blank_page", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "resource_info": { "foo": "bar" }, "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "type": "parse", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_signing_secret": "whsec_...", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "parent_job_execution_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "partitions": { "foo": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e" }, "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "session_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "user_id": "user_id", "webhook_url": "webhook_url" }, "job_type": "classify", "output_s3_path": "output_s3_path", "parameters_hash": "parameters_hash", "processed_at": "2019-12-27T18:11:19.117Z", "result_id": "result_id", "output_metadata": {} } ] } ``` # Split ## Create Split Job `$ llp beta:split create` **post** `/api/v1/beta/split/jobs` Create a document split job. ### Parameters - `--document-input: object { type, value }` Body param: Document to be split. - `--organization-id: optional string` Query param - `--project-id: optional string` Query param - `--configuration: optional object { categories, splitting_strategy }` Body param: Split configuration with categories and splitting strategy. - `--configuration-id: optional string` Body param: Saved split configuration ID. ### Returns - `BetaSplitNewResponse: object { id, categories, document_input, 8 more }` Beta response — uses nested document_input object. - `id: string` Unique identifier for the split job. - `categories: array of SplitCategory` Categories used for splitting. - `name: string` Name of the category. - `description: optional string` Optional description of what content belongs in this category. - `document_input: object { type, value }` Document that was split. - `type: string` Type of document input. Valid values are: file_id - `value: string` Document identifier. - `project_id: string` Project ID this job belongs to. - `status: string` Current status of the job. Valid values are: pending, processing, completed, failed, cancelled. - `user_id: string` User ID who created this job. - `configuration_id: optional string` Split configuration ID used for this job. - `created_at: optional string` Creation datetime - `error_message: optional string` Error message if the job failed. - `result: optional object { segments }` Result of a completed split job. - `segments: array of SplitSegmentResponse` List of document segments. - `category: string` Category name this split belongs to. - `confidence_category: string` Categorical confidence level. Valid values are: high, medium, low. - `pages: array of number` 1-indexed page numbers in this split. - `updated_at: optional string` Update datetime ### Example ```cli llp beta:split create \ --api-key 'My API Key' \ --document-input '{type: type, value: value}' ``` #### Response ```json { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input": { "type": "type", "value": "value" }, "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 ] } ] }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## List Split Jobs `$ llp beta:split list` **get** `/api/v1/beta/split/jobs` List document split jobs. ### Parameters - `--created-at-on-or-after: optional string` Include items created at or after this timestamp (inclusive) - `--created-at-on-or-before: optional string` Include items created at or before this timestamp (inclusive) - `--job-id: optional array of string` Filter by specific job IDs - `--organization-id: optional string` - `--page-size: optional number` - `--page-token: optional string` - `--project-id: optional string` - `--status: optional "cancelled" or "completed" or "failed" or 2 more` Filter by job status (pending, processing, completed, failed, cancelled) ### Returns - `SplitJobQueryResponseBeta: object { items, next_page_token, total_size }` Beta paginated list of split jobs. - `items: array of object { id, categories, document_input, 8 more }` The list of items. - `id: string` Unique identifier for the split job. - `categories: array of SplitCategory` Categories used for splitting. - `name: string` Name of the category. - `description: optional string` Optional description of what content belongs in this category. - `document_input: object { type, value }` Document that was split. - `type: string` Type of document input. Valid values are: file_id - `value: string` Document identifier. - `project_id: string` Project ID this job belongs to. - `status: string` Current status of the job. Valid values are: pending, processing, completed, failed, cancelled. - `user_id: string` User ID who created this job. - `configuration_id: optional string` Split configuration ID used for this job. - `created_at: optional string` Creation datetime - `error_message: optional string` Error message if the job failed. - `result: optional object { segments }` Result of a completed split job. - `segments: array of SplitSegmentResponse` List of document segments. - `category: string` Category name this split belongs to. - `confidence_category: string` Categorical confidence level. Valid values are: high, medium, low. - `pages: array of number` 1-indexed page numbers in this split. - `updated_at: optional string` Update datetime - `next_page_token: optional string` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size: optional number` 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. ### Example ```cli llp beta:split list \ --api-key 'My API Key' ``` #### Response ```json { "items": [ { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input": { "type": "type", "value": "value" }, "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 ] } ] }, "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Get Split Job `$ llp beta:split get` **get** `/api/v1/beta/split/jobs/{split_job_id}` Get a document split job. ### Parameters - `--split-job-id: string` - `--organization-id: optional string` - `--project-id: optional string` ### Returns - `BetaSplitGetResponse: object { id, categories, document_input, 8 more }` Beta response — uses nested document_input object. - `id: string` Unique identifier for the split job. - `categories: array of SplitCategory` Categories used for splitting. - `name: string` Name of the category. - `description: optional string` Optional description of what content belongs in this category. - `document_input: object { type, value }` Document that was split. - `type: string` Type of document input. Valid values are: file_id - `value: string` Document identifier. - `project_id: string` Project ID this job belongs to. - `status: string` Current status of the job. Valid values are: pending, processing, completed, failed, cancelled. - `user_id: string` User ID who created this job. - `configuration_id: optional string` Split configuration ID used for this job. - `created_at: optional string` Creation datetime - `error_message: optional string` Error message if the job failed. - `result: optional object { segments }` Result of a completed split job. - `segments: array of SplitSegmentResponse` List of document segments. - `category: string` Category name this split belongs to. - `confidence_category: string` Categorical confidence level. Valid values are: high, medium, low. - `pages: array of number` 1-indexed page numbers in this split. - `updated_at: optional string` Update datetime ### Example ```cli llp beta:split get \ --api-key 'My API Key' \ --split-job-id split_job_id ``` #### Response ```json { "id": "id", "categories": [ { "name": "x", "description": "x" } ], "document_input": { "type": "type", "value": "value" }, "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 ] } ] }, "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Domain Types ### Split Category - `split_category: object { name, description }` Category definition for document splitting. - `name: string` Name of the category. - `description: optional string` Optional description of what content belongs in this category. ### Split Document Input - `split_document_input: object { type, value }` Document input specification for beta API. - `type: string` Type of document input. Valid values are: file_id - `value: string` Document identifier. ### Split Result Response - `split_result_response: object { segments }` Result of a completed split job. - `segments: array of SplitSegmentResponse` List of document segments. - `category: string` Category name this split belongs to. - `confidence_category: string` Categorical confidence level. Valid values are: high, medium, low. - `pages: array of number` 1-indexed page numbers in this split. ### Split Segment Response - `split_segment_response: object { category, confidence_category, pages }` A segment of the split document. - `category: string` Category name this split belongs to. - `confidence_category: string` Categorical confidence level. Valid values are: high, medium, low. - `pages: array of number` 1-indexed page numbers in this split.