Fully managed RAG-as-a-Service for developers
Fully managed RAG-as-a-Service for developers On Nagent, Ragie is exposed as a fully-configurable developer tools integration that any agent can call — 31 actions, and API key authentication. No code is required to wire Ragie into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Ragie to automate the kinds of tasks developer tools teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Ragie into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Ragie, with input parameters and output schema. Drop these into any step of an agent built in Helix.
RAGIE_CREATE_DOCUMENTTool to upload and process a document file in Ragie. Use when you need to create a new document with support for various formats including text, images, and documents. The endpoint accepts multipart/form-data and returns a Document object with processing status and metadata.
Input parameters
The document file to upload. Supported formats: Plain Text (.eml.html.json.md.msg.rst.rtf.txt.xml), Images (.png.webp.jpg.jpeg.tiff.bmp.heic), Documents (.csv.doc.docx.epub.odt.pdf.ppt.pptx.tsv.xlsx.xls). Note: PDFs exceeding 2000 pages are unsupported in hi_res mode. If not provided, use raw_content and raw_filename instead.
Processing strategy for the document. For text documents: 'hi_res' (extracts images/tables) or 'fast' (extracts text only, default). For audio: true/false. For video: 'audio_only', 'video_only', or 'audio_video'. Can specify 'all' for maximum quality across all media types.
Custom document name. Defaults to the file's name if omitted.
Custom key-value pairs for document metadata. Keys must be strings. Values can be strings, numbers, booleans, or string arrays. Maximum 1000 total values allowed.
Partition scope for the document. Must be lowercase alphanumeric with only '_' and '-' allowed.
Inline file content to upload as text or bytes.
Custom identifier for the document (e.g., external system ID or source URL).
Filename for inline content (e.g., 'document.txt'). Required when using raw_content.
MIME type for the inline content (e.g., 'text/plain', 'application/pdf'). Defaults to text/plain.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_CREATE_DOCUMENT_FROM_URLTool to ingest a document from a publicly accessible URL. Use when you need to add documents to Ragie from external sources. The document undergoes processing steps (pending, partitioning, indexed, ready) before becoming available for retrieval.
Input parameters
URL of the file to download. Must be publicly accessible and use HTTP or HTTPS scheme.
Partition strategy (hi_res/fast for text, boolean for audio, audio_only/video_only/audio_video for video); defaults to fast
Optional document name; defaults if omitted
Document metadata with string/number/boolean/array values; max 1000 total values
Optional partition identifier for scoping
Optional external system identifier
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_CREATE_DOCUMENT_RAWTool to ingest a document as raw text or JSON. Use when creating a new document from text or JSON data. The document goes through processing steps and becomes available for retrieval once in the ready state.
Input parameters
Document data in text or JSON format.
An optional name for the document. If not set, defaults to the current timestamp.
Document metadata with string keys and string/number/boolean/array values; maximum 1000 total values.
Document scope identifier; must be lowercase alphanumeric with only '_' and '-' special characters.
An optional identifier for the document. A common value might be an id in an external system or the URL.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_CREATE_INSTRUCTIONTool to create a new instruction that applies natural language directives to documents as they're ingested or updated. Use when you need to define structured data extraction or analysis rules for documents in Ragie.
Input parameters
Unique identifier for the instruction
Scope of instruction: 'document' for full analysis, 'chunk' for granular search (default: 'chunk')
Whether instruction applies to new/updated documents (default: true)
Optional metadata filter matching document metadata before applying instruction
Natural language instruction which will be applied to documents as they are created and updated
Optional partition identifier to scope instruction to specific partition
JSON Schema defining the entity structure generated by the instruction
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_CREATE_OAUTH_REDIRECT_URLTool to create an OAuth redirect URL for initializing embedded connector OAuth flows. Use when you need to set up OAuth authentication for connectors like Google Drive, Notion, or HubSpot.
Input parameters
Processing strategy (hi_res/fast for text, true/false for audio, audio_only/video_only/audio_video for video).
UI theme preference: 'light', 'dark', or 'system'; defaults to 'system'.
Optional connector-specific configuration.
Document metadata with string/number/boolean/array values; max 1000 total values.
Optional partition identifier to scope the connection.
Maximum pages to sync; connection disables when limit reached.
Connector type (e.g., google_drive, notion, hubspot); defaults to 'google_drive'.
The URI where users return after OAuth authentication.
Optional authenticator ID for white-labeled credentials (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_CREATE_PARTITION_PARTITIONS_POSTTool to create a new partition for scoping documents and connections in Ragie. Use when you need to organize documents and set resource limits for different workspaces or tenants.
Input parameters
Identifier for the partition. This is a required field that uniquely identifies the partition.
Overview text describing the partition's purpose or usage
Optional subset of document metadata defined as JSON Schema. Allows defining custom metadata structure for documents in this partition.
Maximum limit, in MBs, for media hosted
Maximum limit, in pages, for hosted documents
Maximum limit, in MBs, for media streamed
Maximum limit, in minutes, for audio processing
Maximum limit, in pages, for processed documents
Maximum limit, in minutes, for video processing
Monthly limit, in MBs, for media hosted
Monthly limit of hosted pages added in the current month
Monthly limit, in MBs, for media streamed
Monthly limit, in minutes, for audio processing
Monthly limit, in pages, for processed documents
Monthly limit, in minutes, for video processing
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_DELETE_DOCUMENTTool to delete a document from Ragie. Use when you need to remove a document permanently from the system. Supports both synchronous and asynchronous deletion modes.
Input parameters
If true, performs document deletion asynchronously. Default is false for synchronous deletion.
An optional partition to scope the request to.
The unique identifier (UUID) of the document to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_DELETE_INSTRUCTIONTool to delete an instruction and all associated entities. Use when you need to permanently remove an instruction (irreversible operation). Requires the instruction ID (UUID format).
Input parameters
The unique identifier (UUID) of the instruction to delete
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_DELETE_PARTITIONTool to delete a partition and all associated data irreversibly. Use when you need to permanently remove a partition. Returns status 200 for synchronous deletion or 202 for asynchronous deletion.
Input parameters
The partition identifier to delete
When true, performs partition deletion asynchronously. Defaults to false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENTTool to retrieve a specific document by its unique identifier. Use when you need to get document details, metadata, processing status, or check for errors. Returns comprehensive document information including chunk count, page count, and any processing errors.
Input parameters
Scopes the request to a specific partition. If omitted, accounts created after 1/9/2025 will have the request scoped to the default partition.
The unique identifier of the document in UUID format (e.g., 00000000-0000-0000-0000-000000000000).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENT_CHUNKTool to retrieve a specific document chunk by its document and chunk ID. Use when you need detailed information about a specific chunk within a document, including its content, metadata, position index, and optional modality data for audio/video chunks.
Input parameters
The ID of the chunk (UUID format).
Optional partition to scope the request; if omitted, defaults to the default partition for newer accounts.
The ID of the document (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENT_CHUNK_CONTENTTool to retrieve document chunk content in requested format with streaming support for media. Use when you need to get the actual content of a specific chunk from a document.
Input parameters
The unique identifier of the chunk (UUID format).
Whether to return the content as a file download or a raw stream. Default is false.
Optional partition identifier to scope the request for multi-tenant isolation.
Desired output format as MIME type. If not specified, returns the content in its original format.
The unique identifier of the document (UUID format).
Standard HTTP range header for byte-range requests (partial content), e.g., 'bytes=0-1023'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENT_CHUNKSTool to retrieve document chunks with pagination support. Lists all document chunks sorted by index in ascending order (max 100 items per page). Documents created prior to 9/18/2024 that have not been updated since have chunks sorted by ID instead of index.
Input parameters
An opaque cursor for pagination used to retrieve subsequent pages.
The inclusive ending index of the chunk range to list. Omitting both start_index and end_index returns all chunks.
The number of items per page (range: 1-100, default: 10).
Header parameter scoping results to a specific partition.
The UUID of the document to retrieve chunks from.
The inclusive starting index of the chunk range to list. Omitting both start_index and end_index returns all chunks.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENT_CONTENTTool to retrieve the content of a document by its ID. Use when you need to access the full content of a specific document. The media_type parameter can be used to request content in different formats.
Input parameters
HTTP range header for partial content requests.
Whether to return content as file download. Defaults to false.
An optional partition to scope the request to.
Format to return content in. Accepts: text/plain, audio/mpeg, video/mp4, image/webp, image/heic, image/bmp, image/png, image/jpeg, image/tiff, or application/json. Default returns content with text descriptions of non-textual media.
The UUID of the document to retrieve content for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_DOCUMENT_SUMMARYTool to retrieve an LLM-generated summary of a document by its ID. Use when you need to get a concise summary of a document's content.
Input parameters
Optional partition scope. If omitted, accounts created after 1/9/2025 default to the default partition; older accounts scope to all partitions.
The unique identifier of the document (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_PARTITIONTool to retrieve a partition by ID with usage statistics and resource limits. Use when you need to get detailed information about a specific partition.
Input parameters
The identifier for the partition being retrieved
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_GET_RESPONSETool to retrieve a response by its unique identifier. Use when you need to check the status or details of a previously created response.
Input parameters
The unique identifier (UUID format) for the response to retrieve
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_CONNECTIONS_CONNECTIONS_GETTool to list all connections sorted by creation date descending with pagination support. Use when you need to retrieve connections, optionally filtered by metadata.
Input parameters
Pagination token for navigating to next page.
Metadata filter supporting operators ($eq, $ne, $gt, $gte, $lt, $lte, $in, $nin) with AND/OR logic.
Number of items per page, range 1-100, defaults to 10.
Partition identifier to scope the request. Defaults to default partition if omitted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_CONNECTION_SOURCE_TYPESTool to list available connection source types like 'google_drive' and 'notion' along with their metadata. Use when you need to discover what connector types are available in Ragie.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_DOCUMENTSTool to list all documents sorted by creation date (descending) with pagination support. Use when you need to browse or retrieve document metadata. Supports filtering and pagination up to 100 items per page.
Input parameters
An opaque cursor for pagination. Use the next_cursor from previous response to get next page.
Filter expression for documents. Supports operators: $eq, $ne, $gt, $gte, $lt, $lte, $in, $nin. Can combine with AND/OR logic.
The number of items per page. Must be between 1 and 100. Default is 10.
Scopes request to specific partition. If not provided, default behavior varies by account creation date.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_ENTITIES_BY_DOCUMENTTool to retrieve all extracted entities from a specific document with pagination support. Use when you need to access structured data that has been extracted from a document by Ragie's entity extraction instructions.
Input parameters
An opaque cursor for pagination. Use the next_cursor from a previous response to fetch the next page of results.
Number of items per page. Must be between 1 and 100. Defaults to 10 if not specified.
An optional partition to scope the request to. If omitted, scoped to default partition.
The ID of the document from which to retrieve entities. Must be a valid UUID.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_ENTITIES_BY_INSTRUCTIONTool to retrieve entities generated by a specific instruction. Use when you need to fetch entities extracted from documents based on a specific instruction's processing.
Input parameters
An opaque cursor for pagination to fetch the next page of results.
The number of items per page. Must be between 1 and 100. Default is 10.
An optional partition to scope the request to.
The ID of the instruction (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_INSTRUCTIONSTool to retrieve all instruction records from the Ragie system. Use when you need to view all available instructions that define natural language prompts and entity schemas applied to documents.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_LIST_PARTITIONSTool to retrieve a paginated list of all partitions sorted by name in ascending order. Use when you need to list available partitions with their configurations and limits.
Input parameters
An opaque cursor for pagination to retrieve the next page of results
The number of items per page (must be greater than 0 and less than or equal to 100). Defaults to 10.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_PATCH_DOCUMENT_METADATATool to update metadata for a specific document with partial update support. Use when you need to modify document metadata fields without replacing the entire metadata object. Supports both synchronous and asynchronous updates.
Input parameters
Whether to run the metadata update asynchronously. If true, the metadata update will be run in the background and the response will be 202 Accepted.
The metadata to update on the document. Performs a partial update. Supports string, number, boolean, and string array values. Keys set to null are deleted. Maximum 1000 total values allowed.
Optional partition scope. If omitted, accounts created after 1/9/2025 default to the default partition.
The unique identifier of the document (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_RETRIEVETool to retrieve relevant document chunks based on a query. Use when you need to search and retrieve document content that matches a specific query, with optional filtering and reranking capabilities.
Input parameters
The query to search with when retrieving document chunks.
The maximum number of chunks to return. Defaults to 8.
Metadata search filter supporting operators: $eq (equal), $ne (not equal), $gt (greater than), $gte (greater than or equal), $lt (less than), $lte (less than or equal), $in (in array), $nin (not in array). Example: {"department": {"$in": \["sales", "marketing"\]}}.
Reranks the chunks for semantic relevancy post cosine similarity.
The partition to scope a retrieval to. If omitted, the retrieval will be scoped to the default partition.
Enables recency bias which will favor more recent documents vs older documents.
Maximum number of chunks to retrieve per document.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_SET_PARTITION_LIMITSTool to set usage limits on partition pages and media. Use when you need to configure monthly or maximum limits for pages processed/hosted, video/audio processing, or media streaming/hosting for a specific partition.
Input parameters
The identifier for the partition being modified.
Maximum media hosting limit in megabytes.
Absolute maximum for hosted document pages.
Maximum media streaming limit in megabytes.
Maximum audio processing limit in minutes.
Absolute maximum for processed document pages.
Maximum video processing limit in minutes.
Monthly media hosting limit in megabytes.
Monthly cap for newly added hosted pages.
Monthly media streaming limit in megabytes.
Monthly audio processing limit in minutes.
Monthly cap for processed document pages.
Monthly video processing limit in minutes.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_UPDATE_DOCUMENT_FROM_URLTool to update an existing document by fetching content from a publicly accessible URL. Use when you need to refresh or replace a document's content with data from a web URL. The document goes through processing steps before it is ready for retrieval.
Input parameters
URL of the file to download. Must be publicly accessible and use HTTP or HTTPS scheme.
Processing strategy for different file types. Can be 'hi_res', 'fast', or a media configuration object. Defaults to 'fast'.
Scopes the request to a specific partition
The unique identifier (UUID) of the document to update
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_UPDATE_DOCUMENT_RAWTool to update a document's content from raw text or JSON data. Use when modifying existing document content. The document undergoes processing and becomes available for retrieval once it reaches the ready state.
Input parameters
The document content in text or JSON format. Must be at least 1 character long.
UUID of the document to update
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_UPDATE_INSTRUCTIONTool to update an instruction's active status. Use when you need to activate or deactivate an existing instruction.
Input parameters
Whether the instruction is active. Active instructions are applied to documents when they're created or when their file is updated
The UUID of the instruction to update
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
RAGIE_UPDATE_PARTITIONTool to update a partition's configuration including description, context-aware settings, and metadata schema. Use when you need to modify an existing partition's settings.
Input parameters
A text description explaining the purpose or contents of the partition.
The unique identifier of the partition to update
Enable context-aware descriptions for the partition. When enabled, the partition will generate contextual descriptions for content.
A JSON Schema subset defining the metadata fields for documents in this partition. Providing detailed descriptions of fields helps LLMs generate filters dynamically.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 80 agents privately built on Nagent that already use Ragie.
Build on Nagent
Connect Ragie to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Ragie, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Ragie is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Ragie is connected, you configure its 31 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Ragie steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Ragie event fires, the agent kicks off automatically.
Every Ragie action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Ragie ships with 31 pre-built developer tools actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Ragie together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Ragie-based workflows tailored to your business.