{ "openapi": "3.0.1", "info": { "title": "Lead Enrichment Pipeline — Email, Firmographics & ICP", "description": "Takes raw lead lists from any source and returns deduplicated, enriched, scored records. The value-add layer that sits on top of your scrapers.", "version": "1.0", "x-build-id": "LRgLLfsj1ZH9KseKZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/prooflio~lead-enrichment-pipeline/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-prooflio-lead-enrichment-pipeline", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/prooflio~lead-enrichment-pipeline/runs": { "post": { "operationId": "runs-sync-prooflio-lead-enrichment-pipeline", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/prooflio~lead-enrichment-pipeline/run-sync": { "post": { "operationId": "run-sync-prooflio-lead-enrichment-pipeline", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "records": { "title": "Inline lead records", "type": "array", "description": "Raw lead objects to process. Field names are auto-mapped (e.g. company / organization / companyName all map to companyName). Combine with 'inputDatasetId' to merge sources." }, "inputDatasetId": { "title": "Input dataset ID", "type": "string", "description": "ID of an existing dataset (e.g. the output of a scraper Actor) whose items are loaded as leads and merged with any inline records. This is the 'chain on top of your scrapers' input." }, "fieldMap": { "title": "Custom field mapping", "type": "object", "description": "Override or extend the default field aliasing. Keys are source field names, values are one of: fullName, firstName, lastName, jobTitle, email, phone, linkedinUrl, companyName, website, country, city, source." }, "dedupEnabled": { "title": "Deduplicate / resolve entities", "type": "boolean", "description": "Merge duplicate leads (same email globally, or same company + fuzzy-matched name). Field values are merged with provenance tracking.", "default": true }, "fuzzyThreshold": { "title": "Fuzzy name match threshold", "minimum": 0.5, "maximum": 1, "type": "number", "description": "Jaro-Winkler similarity (0-1) above which two names within the same company are treated as the same person. Higher = stricter.", "default": 0.92 }, "findMissingEmails": { "title": "Guess missing emails", "type": "boolean", "description": "When a lead has a name + company domain but no email, generate ranked candidate addresses from common patterns (first.last@, flast@, etc.). Guessed emails are flagged isGuessed=true and never claimed as verified.", "default": true }, "verifyEmails": { "title": "Verify emails", "type": "boolean", "description": "Validate syntax, check the domain's MX records (real DNS lookup), and flag disposable / role-based addresses. Mailbox-level (SMTP) verification requires a provider — see emailVerifierApiKey.", "default": true }, "emailVerifierApiKey": { "title": "Email verifier API key (optional)", "type": "string", "description": "Optional. If set, enables mailbox-level verification via your provider hook in src/email.ts (e.g. ZeroBounce, NeverBounce). Leave empty to use free MX + heuristic verification only." }, "enrichFirmographics": { "title": "Enrich firmographics", "type": "boolean", "description": "Resolve company-level attributes from the domain: industry classification, detected tech stack, and MX presence. Results are cached per domain so overlapping lists don't re-pay.", "default": true }, "fetchHomepage": { "title": "Fetch company homepage", "type": "boolean", "description": "Allow firmographics to fetch the company homepage to infer industry and detect tech signals. Disable for a faster, network-free run that uses only DNS-level signals.", "default": true }, "firmographicsApiKey": { "title": "Firmographics provider API key (optional)", "type": "string", "description": "Optional. If set, enables your paid firmographics provider hook in src/firmographics.ts (e.g. People Data Labs, Clearbit) for headcount, revenue, etc. Leave empty to use free inference only." }, "icp": { "title": "Ideal Customer Profile (scoring config)", "type": "object", "description": "Defines how each enriched lead is scored 0-100. Omit to skip scoring." }, "suppressionList": { "title": "Suppression list", "type": "array", "description": "Emails or domains to drop entirely (compliance / opt-outs / competitors). Matching leads are excluded from the output.", "default": [], "items": { "type": "string" } }, "maxRecords": { "title": "Max records to process", "minimum": 0, "type": "integer", "description": "Hard cap on input records after loading (0 = no limit). Useful for test runs.", "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel enrichment workers. Keep modest when fetching homepages to be polite.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used when fetching company homepages. Recommended on the platform to avoid blocks.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }