Skip to content

Upload File

FileCreateResponse Files.Create(FileCreateParamsparameters, CancellationTokencancellationToken = default)
POST/api/v1/beta/files

Upload a file using multipart/form-data.

Set purpose to indicate how the file will be used: user_data, parse, extract, classify, split, sheet, or agent_app.

Returns the created file metadata including its ID for use in subsequent parse, extract, or classify operations.

ParametersExpand Collapse
FileCreateParams parameters
required string file

Body param: The file to upload

required string purpose

Body param: The intended purpose of the file. Valid values: ‘user_data’, ‘parse’, ‘extract’, ‘split’, ‘classify’, ‘sheet’, ‘agent_app’. This determines the storage and retention policy for the file.

string? organizationID

Query param

formatuuid
string? projectID

Query param

formatuuid
string? externalFileID

Body param: The ID of the file in the external system

ReturnsExpand Collapse
class FileCreateResponse:

An uploaded file.

required string ID

Unique file identifier

required string Name

File name including extension

maxLength3000
minLength1
required string ProjectID

Project this file belongs to

formatuuid
PresignedUrl? DownloadUrl

Schema for a presigned URL.

required DateTimeOffset ExpiresAt

The time at which the presigned URL expires

formatdate-time
required string Url

A presigned URL for IO operations against a private file

formaturi
minLength1
IReadOnlyDictionary<string, string>? FormFields

Form fields for a presigned POST request

DateTimeOffset? ExpiresAt

When the file expires and may be automatically removed. Null means no expiration.

formatdate-time
string? ExternalFileID

Optional ID for correlating with an external system

string? FileType

File extension (pdf, docx, png, etc.)

maxLength3000
minLength1
DateTimeOffset? LastModifiedAt

When the file was last modified (ISO 8601)

formatdate-time
string? Purpose

How the file will be used: user_data, parse, extract, classify, split, sheet, or agent_app

Upload File

FileCreateParams parameters = new()
{
    File = Encoding.UTF8.GetBytes("Example data"),
    Purpose = "purpose",
};

var file = await client.Files.Create(parameters);

Console.WriteLine(file);
{
  "id": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "name": "invoice.pdf",
  "project_id": "123e4567-e89b-12d3-a456-426614174000",
  "download_url": {
    "expires_at": "2019-12-27T18:11:19.117Z",
    "url": "https://example.com",
    "form_fields": {
      "foo": "string"
    }
  },
  "expires_at": "2019-12-27T18:11:19.117Z",
  "external_file_id": "ext-12345",
  "file_type": "pdf",
  "last_modified_at": "2019-12-27T18:11:19.117Z",
  "purpose": "parse"
}
Returns Examples
{
  "id": "dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "name": "invoice.pdf",
  "project_id": "123e4567-e89b-12d3-a456-426614174000",
  "download_url": {
    "expires_at": "2019-12-27T18:11:19.117Z",
    "url": "https://example.com",
    "form_fields": {
      "foo": "string"
    }
  },
  "expires_at": "2019-12-27T18:11:19.117Z",
  "external_file_id": "ext-12345",
  "file_type": "pdf",
  "last_modified_at": "2019-12-27T18:11:19.117Z",
  "purpose": "parse"
}
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/