Ragie integration: operations for AI agents
Ragie connects to Type.com as an integration. This page lists the 54 operations documented for Claude and Codex in Type.com: 25 read, 19 write, 10 destructive.
About Ragie
Fully managed RAG-as-a-Service for developers
Categories: Developer Tools & IT
How to connect Ragie to Type.com
- Access
- Organization connection: one shared account for the workspace.
To add the connection, follow the steps in Space connections.
Documented operations
54 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.
54 operations listed.
Authenticators
- Read
List Authenticators
List all authenticators sorted by created_at in descending order. Results are paginated with a max limit of 100. When more authenticators are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /authenticators - Write
Create Authenticator
Create White labeled connector credentials
POST /authenticators - Write
Create Authenticator Connection
Create a connector for a given authenticator. This requires credentials dependent on the provider. For google drive it is a refresh token.
POST /authenticators/{authenticator_id}/connection - Destructive
Delete Authenticator
Delete an authenticator. This requires all connections created by that authenticator to be deleted first.
DELETE /authenticators/{authenticator_id}
Connections
- Read
Get Connection
Get a connection.
GET /connections/{connection_id} - Read
Get Connection Stats
Lists connection stats: total documents active documents, total active pages.
GET /connections/{connection_id}/stats - Read
List Connections
List all connections sorted by created_at in descending order. Results are paginated with a max limit of 100. When more documents are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /connections - Read
List Connection Source Types
List available connection source types like 'google_drive' and 'notion' along with their metadata
GET /connections/source-type - Write
Create Connection
Create a connection. This is only for non-oauth connections such as S3 compatible connections, Freshdesk, and Zendesk.
POST /connection - Write
Create Oauth Redirect Url
Creates a redirect url to redirect the user to when initializing an embedded connector.
POST /connections/oauth - Write
Set Connection Enabled
Enable or disable the connection. A disabled connection won't sync.
PUT /connections/{connection_id}/enabled - Write
Set Connection Limits
Sets limits on a connection. Limits can be set on the total number of pages a connection can sync. When the limit is reached, the connection will be disabled. Limit may be removed by setting it to `null`.
PUT /connections/{connection_id}/limit - Write
Sync Connection
Schedules a connector to sync as soon as possible.
POST /connections/{connection_id}/sync - Destructive
Delete Connection
Schedules a connection to be deleted. You can choose to keep the files from the connection or delete them all. If you keep the files, they will no longer be associated to the connection. Deleting can take some time, so you will still see files for a bit after this is called.
POST /connections/{connection_id}/delete - Destructive
Update Connection
Updates a connections metadata or mode. These changes will be seen after the next sync.
PUT /connections/{connection_id}
Documents
- Read
Get Document
Returns a document with its status and metadata.
GET /documents/{document_id} - Read
Get Document Chunk
Gets a document chunk by its document and chunk ID.
GET /documents/{document_id}/chunks/{chunk_id} - Read
Get Document Chunk Content
Returns the content of a document chunk in the requested format. Can be used to stream media of the content for audio/video documents.
GET /documents/{document_id}/chunks/{chunk_id}/content - Read
Get Document Chunks
List all document chunks sorted by index in ascending order. May be limited to a range of chunk indices with the `start_index` and `end_index` parameters. Documents created prior to 9/18/2024, which have not been updated since, have chunks which do not include an index and their index will be returned as -1. They will be sorted by their ID instead. Updating the document using the `Update Document File` or `Update Document Raw` endpoint will regenerate document chunks, including their index. Results are paginated with a max limit of 100. When more chunks are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /documents/{document_id}/chunks - Read
Get Document Content
Get the content of a document. The `media_type` parameter can be used to request the content in a different format. When requesting as `application/json` additional metadata about the document will be included. If the original document contained content such as images or other non-textual media, this response will include a text description of that media instead of the original file data. Using mime types such as `audio/mpeg` or `video/mp4` will stream the file in a format that can be provided to an audio video player.
GET /documents/{document_id}/content - Read
Get Document Source
Get the source file of a document. The source file is the original file that was uploaded to create the document. If the document was created from a URL, the source file will be the content of the URL. If the document was created by a connection, the source file will vary based on the type of the connection. For example, a Google Drive connection will return the file that was synced from the Google Drive, while a SalesForce connection would return a JSON file of the data synced from SalesForce.
GET /documents/{document_id}/source - Read
Get Document Summary
Get a LLM generated summary of the document. The summary is created when the document is first created or updated. Documents of types ['xls', 'xlsx', 'csv', 'json'] are not supported for summarization. Documents greater than 1M in token length are not supported. This feature is in beta and may change in the future.
GET /documents/{document_id}/summary - Read
List Documents
List all documents sorted by created_at in descending order. Results are paginated with a max limit of 100. When more documents are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /documents - Write
Create Document
On ingest, the document goes through a series of steps before it is ready for retrieval. Each step is reflected in the status of the document which can be one of [`pending`, `partitioning`, `partitioned`, `refined`, `chunked`, `indexed`, `summary_indexed`, `keyword_indexed`, `ready`, `failed`]. The document is available for retrieval once it is in ready state. The summary index step can take a few seconds. You can optionally use the document for retrieval once it is in `indexed` state. However the summary will only be available once the state has changed to `summary_indexed` or `ready`.
POST /documents - Write
Create Document From Url
Ingest a document from a publicly accessible URL. On ingest, the document goes through a series of steps before it is ready for retrieval. Each step is reflected in the status of the document which can be one of [`pending`, `partitioning`, `partitioned`, `refined`, `chunked`, `indexed`, `summary_indexed`, `keyword_indexed`, `ready`, `failed`]. The document is available for retrieval once it is in ready state. The summary index step can take a few seconds. You can optionally use the document for retrieval once it is in `indexed` state. However the summary will only be available once the state has changed to `summary_indexed` or `ready`. PDF files over 2000 pages are not supported. Other static document files over 10000 pages are not supported.
POST /documents/url - Write
Create Document Raw
Ingest a document as raw text. On ingest, the document goes through a series of steps before it is ready for retrieval. Each step is reflected in the status of the document which can be one of [`pending`, `partitioning`, `partitioned`, `refined`, `chunked`, `indexed`, `summary_indexed`, `keyword_indexed`, `ready`, `failed`]. The document is available for retrieval once it is in ready state. The summary index step can take a few seconds. You can optionally use the document for retrieval once it is in `indexed` state. However the summary will only be available once the state has changed to `summary_indexed` or `ready`.
POST /documents/raw - Write
Patch Document Metadata
Adds, changes, or removes metadata keys on a document.
PATCH /documents/{document_id}/metadata - Destructive
Delete Document
Deletes a document and its indexed content.
DELETE /documents/{document_id} - Destructive
Update Document Url
Updates a document from a publicly accessible URL. On ingest, the document goes through a series of steps before it is ready for retrieval. Each step is reflected in the status of the document which can be one of [`pending`, `partitioning`, `partitioned`, `refined`, `chunked`, `indexed`, `summary_indexed`, `keyword_indexed`, `ready`, `failed`]. The document is available for retrieval once it is in ready state. The summary index step can take a few seconds. You can optionally use the document for retrieval once it is in `indexed` state. However the summary will only be available once the state has changed to `summary_indexed` or `ready`. PDF files over 2000 pages are not supported. Other static document files over 10000 pages are not supported.
PUT /documents/{document_id}/url - Destructive
Update Document File
Replaces the file of an existing document and re-indexes it.
PUT /documents/{document_id}/file - Destructive
Update Document Raw
Replaces the raw text of an existing document and re-indexes it.
PUT /documents/{document_id}/raw
Elements
- Read
Get Element For Document
Returns an element for a specific id
GET /elements/{element_id} - Read
List Elements For Document
List the latest elements for a document. The results are sorted by index in ascending order. Results are paginated with a max limit of 100. When more elements are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page
GET /documents/{document_id}/elements
Entities
- Read
Get Document Extracted Entities
Lists the structured entities extracted from a document.
GET /documents/{document_id}/entities - Read
Get Instruction Extracted Entities
Lists the structured entities extracted by an instruction.
GET /instructions/{instruction_id}/entities - Read
Get Instruction Entity Extraction Logs
List entity extraction logs for an instruction. Results are attempt-level and include both successful and unsuccessful extraction outcomes. Results are sorted by created_at in descending order and paginated. Historical extraction attempts before 2026-03-06 are unavailable in this endpoint.
GET /instructions/{instruction_id}/entity-extraction-logs - Read
List Instructions
List all instructions.
GET /instructions - Write
Create Instruction
Create a new instruction. Instructions are applied to documents as they are created or updated. The results of the instruction are stored as structured data in the schema defined by the `entity_schema` parameter. The `prompt` parameter is a natural language instruction which will be applied to documents. This feature is in beta and may change in the future.
POST /instructions - Write
Patch Instruction
Changes an entity-extraction instruction, for example to turn it on or off.
PATCH /instructions/{instruction_id} - Destructive
Delete Instruction
Delete an instruction. This will delete the instruction and all entities generated by it. This operation is irreversible.
DELETE /instructions/{instruction_id}
Partitions
- Read
Get Partition
Get a partition by its ID. Includes usage information such as the number of documents and pages hosted and processed. The partition's limits are also included.
GET /partitions/{partition_id} - Read
List Partitions
List all partitions sorted by name in ascending order. Results are paginated with a max limit of 100. When more partitions are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /partitions - Write
Create Partition
Create a new partition. Partitions are used to scope documents, connections, and instructions. Partitions must be lowercase alphanumeric and may only include the special characters `_` and `-`. A partition may also be created by creating a document in it. Limits for a partition may optionally be defined when creating.
POST /partitions - Write
Set Partition Limits
Sets limits on a partition. Limits can be set on the total number of pages a partition can host and process. When the limit is reached, the partition will be disabled. A limit may be removed by setting it to `null`.
PUT /partitions/{partition_id}/limits - Write
Update Partition
Updates a partition. This includes the partition's description and metadata schema.
PATCH /partitions/{partition_id} - Destructive
Delete Partition
Deletes a partition and all of its associated data. This includes connections, documents, and partition specific instructions. This operation is irreversible.
DELETE /partitions/{partition_id}
Responses
- Read
Get Response
Get a response by its ID. This will return the response and its status. If the response is still in progress, the status will be `in_progress`. If the response is completed, the status will be `completed`. If the response is failed, the status will be `failed`.
GET /responses/{response_id} - Write
Create Response
Create a response. This will generate an LLM or agentic response. At this time the only supported model is `deep-search`. Responses may be streamed or returned synchronously. The `retrieve` tool is currently the only supported tool, more tools will be added in the future. A single partition may be provided in the retrieve tool. If omitted the `default` partition is used.
POST /responses
Retrievals
- Read
Retrieve
Searches the indexed documents and returns the most relevant chunks for a query.
POST /retrievals
WebhookEndpoints
- Read
Get Webhook Endpoint
Get a webhook endpoint by its id.
GET /webhook_endpoints/{endpoint_id} - Read
List Webhook Endpoints
List all webhook endpoints sorted by created_at in descending order. Results are paginated with a max limit of 100. When more endpoints are available, a `cursor` will be provided. Use the `cursor` parameter to retrieve the subsequent page.
GET /webhook_endpoints - Write
Create Webhook Endpoint
Create a webhook endpoint to receive notifications about document status updates, connection sync progress, partition limits, and other tenant events.
POST /webhook_endpoints - Write
Update Webhook Endpoint
Update a webhook endpoint's name, URL, or active status. Use this to rotate endpoints or temporarily disable delivery without deleting the endpoint.
PATCH /webhook_endpoints/{endpoint_id} - Destructive
Delete Webhook Endpoint
Delete a webhook endpoint to stop delivering webhook notifications to its URL.
DELETE /webhook_endpoints/{endpoint_id}
No operations match.
See How connections work for access and permissions, or browse all integrations.
Reference date: October 28, 2026. Ragie API docs.