Knowledge Delta | RAG Knowledge Base Change Detection
Pricing
$0.10 / complete sync plan
Compare crawler exports and saved snapshots. Generate stable chunk upserts, metadata updates and guarded deletes for RAG pipelines. Process up to 1,000 documents per plan; no model API required.
You can access the Knowledge Delta | RAG Knowledge Base Change Detection programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "E7p9SrVNpKxNoDZWN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/futurefortune~knowledge-delta/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-futurefortune-knowledge-delta", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/futurefortune~knowledge-delta/runs": { "post": { "operationId": "runs-sync-futurefortune-knowledge-delta", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/futurefortune~knowledge-delta/run-sync": { "post": { "operationId": "run-sync-futurefortune-knowledge-delta", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode" ], "properties": { "mode": { "title": "Source mode", "enum": [ "demo", "documents", "dataset" ], "type": "string", "description": "Demo is a free synthetic comparison. Documents accepts pasted exports; Dataset reads an existing finished crawler dataset in your account.", "default": "demo" }, "documents": { "title": "Content documents", "type": "array", "description": "JSON rows with id or url and markdown or text. Optional title. Maximum 1,000 documents and 2 million total text characters. Used in Documents mode.", "items": { "type": "object" } }, "sourceDatasetId": { "title": "Source dataset ID", "type": "string", "description": "17-character ID of an immutable dataset from a finished crawl. Used only in Dataset mode." }, "namespace": { "title": "Knowledge base namespace", "pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,79}$", "type": "string", "description": "Stable name identifying one destination knowledge base. Keep unchanged on repeat runs; isolate different sources.", "default": "my-knowledge-base" }, "previousSnapshot": { "title": "Previous committed snapshot", "type": "object", "description": "Paste a SNAPSHOT produced by this Actor only after its actions were successfully applied. Omit for a first import. Use either this field or a snapshot store ID." }, "previousSnapshotStoreId": { "title": "Previous committed snapshot store ID", "type": "string", "description": "17-character key-value store ID from the last fully applied plan; reads its SNAPSHOT record. Do not use the latest run unless the destination applied it." }, "chunkSize": { "title": "Maximum chunk characters", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Paragraph-based chunk limit, in characters rather than tokens. Keep unchanged when reusing a snapshot.", "default": 1600 }, "completeSource": { "title": "Source is complete", "type": "boolean", "description": "Assert only when the export contains every document in this namespace. Never assert for limited, failed or partial crawls.", "default": false }, "removeMissing": { "title": "Remove missing documents", "type": "boolean", "description": "Emit delete instructions for absent documents only with a complete source. Default keeps missing documents. Replaced chunks inside present documents are always removed.", "default": false }, "maxDeletionRatio": { "title": "Maximum document deletion fraction", "minimum": 0, "maximum": 1, "type": "number", "description": "Block the entire plan if missing-document deletions exceed this fraction of the prior document count. 0.2 means 20%. Raise only after verifying completeness.", "default": 0.2 }, "allowEmptySource": { "title": "Allow intentional empty source", "type": "boolean", "description": "Permit an empty documents array. Removing the whole knowledge base also requires complete source, remove missing and a deletion fraction of 1.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Knowledge Delta | RAG Knowledge Base Change Detection from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: