Convert SchemaInput to a validated JSON schema dictionary.

Wait for and return the results of an extraction job.

Wait for and return the results of an extraction job.

Poll `get_status_fn` until every id in `resource_ids` is finished. Args: resource_ids: Iterable of resource ids to watch

Close all HTTP clients (async)

Create a classify job. Meant to expose lower level access to classifier jobs for advanced use cases. Experimental: This endpo

Create a new spreadsheet parsing job. Args: file_id: ID of the uploaded file config: Parsing configuration R

Download a region result as a pandas DataFrame. Args: job_id: ID of the job region_id: ID of the region r

Asynchronously extract data from one or more files using this agent. Args: files (Union[FileInput, List[FileInput]]): The files t

Download assets (images or charts) from the parsed result.

Download images from the parsed result.

Get the status of a spreadsheet parsing job. Args: job_id: ID of the job include_results_metadata: Whether to include

Get the raw parsed markdown from the job, distinct from the markdown documents. This does not include page separators, e.g. if merge_

Return JobResult object for previously parsed job(s). If the job is still pending, the result will not be returned until it is compl

Get the raw parsed text from the job.

Save all images to files. Args: output_dir: The directory to save the images to Returns: A list of

Upload a file to the Files API. Args: file_obj: File to upload (path, bytes, or file-like object) file_name: Optional

Upload a file to the index.

Upload a file from a URL to the index.

Wait for a job to complete by polling. Args: job_id: ID of the job to wait for Returns: SpreadsheetJobResult

Classify one or more files from various input types (synchronous version). Args: rules: The rules to use for classificat

Create an extraction agent with retry logic for rate limiting.

Delete an extraction run by ID. Args: run_id (str): The ID of the extraction run to delete

* Retrieves the result of a parsing job. * * Uses a polling loop with retry logic. Each API call is retried * up to maxErrorCount times if it

Get the status of a spreadsheet parsing job. Args: job_id: ID of the job include_results_metadata: Whether to include

Parse the input path.

Parse files using LlamaParse and output the results.

Register an agent ID for cleanup at the end of the test session

Run coroutine in a thread with proper client management.

* Search agent data

Search agent data with filtering, sorting, and pagination. Args: filter: Filter conditions to apply to the search. Dict m

Calculate the overall confidence score for the extracted data.

Return directories for all workspace packages from pnpm list JSON output.

Split docs into pages, by separator.

Check if the input is a valid URL. This method checks for: - Proper URL scheme (http/https) - Valid URL structure - N

Check if the input is a valid URL. This method checks for: - Proper S3 scheme (s3://)

Parse the extracted field metadata into a dictionary of field names to field metadata.

Partition a file and run separate parse jobs per partition segment.

Run a command and return stdout as text, raising on failure.

Sync version from package.json to pyproject.toml. Returns True if pyproject was changed, else False.

Ensure filename is provided when needed.

Wait for and return the results of an extraction job.

Deprecated: Use aclassify() instead.

Deprecated: Use aclassify() instead.

Download charts from the parsed result.

Get the full parsed JSON result from the job. Note: This is not the same as JobResult.json(), which is a JSO

Get the markdown documents from the job. Args: split_by_page: Whether to split the pages into separate documents

Get the page screenshot (async).

Get the documents from the job. Args: split_by_page: Whether to split the pages into separate documents

Download xlsx from the parsed result.

Get the XLSX data for the job. Returns: The XLSX data as bytes

* Aggregate agent data into groups

Aggregate agent data into groups according to the group_by fields. Args: filter: Filter conditions to apply to the search

Insert a document.