{ "openapi": "3.0.1", "info": { "title": "Fuzzy List Reconciler - VLOOKUP That Tolerates Typos", "description": "Fuzzy-join two lists (CSV/JSON) on a key column with a similarity threshold. Returns matched pairs with scores, plus unmatched and near-match rows.", "version": "0.1", "x-build-id": "WbOQ3ulN1O3VLQtIU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nibble~list-fuzzy-reconciler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nibble-list-fuzzy-reconciler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nibble~list-fuzzy-reconciler/runs": { "post": { "operationId": "runs-sync-nibble-list-fuzzy-reconciler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nibble~list-fuzzy-reconciler/run-sync": { "post": { "operationId": "run-sync-nibble-list-fuzzy-reconciler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "leftData", "rightData", "leftKey", "rightKey" ], "properties": { "leftData": { "title": "Left list (data)", "type": "string", "description": "The FIRST list to reconcile. Paste a JSON array of objects, CSV text (with a header row), an http(s) URL to a JSON/CSV file, or base64 content prefixed with 'base64:'. Format is auto-detected." }, "rightData": { "title": "Right list (data)", "type": "string", "description": "The SECOND list to reconcile against the first. Same accepted formats as the left list (JSON array, CSV text, http(s) URL, or 'base64:' content). Format is auto-detected." }, "leftKey": { "title": "Left key column(s)", "type": "string", "description": "Column name in the left list to match on. For a composite key, list several columns comma-separated (e.g. 'first_name,last_name'). Values are joined before comparison." }, "rightKey": { "title": "Right key column(s)", "type": "string", "description": "Column name in the right list to match on. Must have the same NUMBER of columns as the left key (composite keys are compared position-by-position)." }, "algorithm": { "title": "Similarity algorithm", "enum": [ "jaro_winkler", "levenshtein", "token_sort", "token_set" ], "type": "string", "description": "String-similarity metric. jaro_winkler favours matching prefixes (best for names). levenshtein is classic edit distance. token_sort / token_set ignore word order (good when tokens are reordered or one string is a subset).", "default": "jaro_winkler" }, "threshold": { "title": "Match threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Minimum similarity (0.0-1.0) for a pair to count as a MATCH. 0.85 is a good default; lower it to catch looser matches, raise it to be stricter.", "default": 0.85 }, "matchStrategy": { "title": "Match strategy", "enum": [ "best_one_to_one", "best_per_left", "all_above_threshold" ], "type": "string", "description": "best_one_to_one: each row on either side is used at most once (true reconciliation). best_per_left: each left row takes its best right match (right rows may repeat, like VLOOKUP). all_above_threshold: emit every pair at/above the threshold (many-to-many).", "default": "best_one_to_one" }, "normalize": { "title": "Normalize keys", "type": "boolean", "description": "Fold accents, strip punctuation, collapse whitespace and lowercase key values before comparing. Strongly recommended.", "default": true }, "caseSensitive": { "title": "Case sensitive", "type": "boolean", "description": "Keep letter case when comparing. Ignored effect when Normalize is on (normalization lowercases). Default off.", "default": false }, "nearMatchMargin": { "title": "Near-match margin", "minimum": 0, "maximum": 1, "type": "number", "description": "How far BELOW the threshold a left row's best candidate can be and still be reported as a 'near_match' for manual review. E.g. threshold 0.85 and margin 0.15 reports best candidates scoring 0.70-0.849.", "default": 0.15 }, "includeUnmatched": { "title": "Include unmatched rows", "type": "boolean", "description": "Emit unmatched_left and unmatched_right records (rows with no match). Turn off to output only matched pairs.", "default": true }, "includeNearMatches": { "title": "Include near matches", "type": "boolean", "description": "Emit near_match records (best candidate just below the threshold) to help you tune the threshold.", "default": true }, "leftFormat": { "title": "Left format (advanced)", "enum": [ "auto", "json", "csv" ], "type": "string", "description": "Override auto-detection of the left list format.", "default": "auto" }, "rightFormat": { "title": "Right format (advanced)", "enum": [ "auto", "json", "csv" ], "type": "string", "description": "Override auto-detection of the right list format.", "default": "auto" } } }, "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 } } }, "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 } } } } } } } } } }