# RFP Opportunity Scout (`amcllc/rfp-opportunity-scout`) Actor Find RFPs/tenders from user-provided procurement pages, extract details, and use AI to summarize and qualify matches. - **URL**: https://apify.com/amcllc/rfp-opportunity-scout.md - **Developed by:** [AMCLLC](https://apify.com/amcllc) (community) - **Categories:** AI, Other - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $0.01 / 1,000 results This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## RFP Opportunity Scout Find and qualify RFPs from your procurement portals, fast. RFP Opportunity Scout crawls the procurement pages you provide, extracts opportunity detail pages, and uses AI to produce a clean dataset: summaries, due dates, requirements, deliverables, and a match score against your keywords. ### Who It's For - Consultants and contractors who bid on RFPs - Agencies looking for new inbound opportunities - Sales teams monitoring procurement channels ### What You Get (Per Opportunity) - Opportunity URL, title, buyer/agency (when available) - Due date / posted date (when available) - Documents (PDF/DOC links) and contact emails (when found) - AI fields: match score + reason, summary, requirements, deliverables, confidence ### LLM Configuration (Ollama Cloud / Ollama) Recommended: manage the model + credentials via Actor environment variables (Secrets): ```bash LLM_API_STYLE=ollama LLM_BASE_URL=http://localhost:11434 ## or your Ollama Cloud base URL LLM_MODEL=llama3.1:8b LLM_API_KEY=... ## optional (cloud endpoints often require it) ```` You can also override per-run via input: `llmApiStyle`, `llmBaseUrl`, `llmModel`, `llmApiKey`. ### Notes - Works best on portals that expose opportunities in static HTML. For JavaScript-heavy portals, a browser-based version is typically required. - Respect target sites' terms and robots rules. # Actor input Schema ## `startUrls` (type: `array`): Procurement listing pages to crawl (e.g., a portal 'opportunities' page). Provide multiple sources if needed. ## `maxRequestsPerCrawl` (type: `integer`): Maximum number of requests that can be made by this crawler. ## `maxDepth` (type: `integer`): Maximum link depth from the start URLs. Depth 0 = listing page only. Depth 1 includes detail pages. ## `sameHostnameOnly` (type: `boolean`): If enabled, the crawler only enqueues links from the same hostname as each start URL. ## `detailUrlIncludes` (type: `array`): Optional list of substrings. If set, only links whose URL contains one of these values are treated as opportunity detail pages. ## `keywords` (type: `array`): Keyword pre-filter for detail pages (used before AI). If empty, all detail pages are considered. ## `excludeKeywords` (type: `array`): If any exclude keyword is present, the opportunity is skipped. ## `minMatchScore` (type: `integer`): Minimum AI match score (0-100) for an opportunity to be considered qualified. ## `maxConcurrency` (type: `integer`): Maximum number of concurrent requests. ## `requestDelayMillis` (type: `integer`): Optional delay applied at the start of each request handler to reduce load on target servers. ## `proxyConfiguration` (type: `object`): Use Apify Proxy for IP rotation to prevent blocking. ## `debugLog` (type: `boolean`): Enable verbose logging (useful for development). ## `aiEnrichmentEnabled` (type: `boolean`): When enabled, the Actor uses an LLM (Ollama Cloud or local Ollama) to summarize and qualify opportunities. ## `llmApiStyle` (type: `string`): Which API format to use: 'ollama' (native /api/chat) or 'openai' (OpenAI-compatible /v1/chat/completions). ## `llmBaseUrl` (type: `string`): Base URL for the LLM API. For local Ollama: http://localhost:11434. For Ollama Cloud, set the Cloud base URL here or via LLM\_BASE\_URL env var. ## `llmApiKey` (type: `string`): API key for the LLM provider. Prefer setting LLM\_API\_KEY (or OLLAMA\_API\_KEY) as an Actor secret instead of passing it in input. ## `llmModel` (type: `string`): Model used for structured enrichment. Manage this via LLM\_MODEL/OLLAMA\_MODEL env vars if you prefer. ## `llmChatCompletionsUrl` (type: `string`): Optional full URL override for OpenAI-compatible chat completions (e.g., https://.../v1/chat/completions). Takes precedence over llmBaseUrl when llmApiStyle='openai'. ## `aiMaxOpportunities` (type: `integer`): Maximum number of opportunities that will be sent to the AI model for enrichment. ## `aiConcurrency` (type: `integer`): How many AI enrichment requests can run in parallel. ## `aiMaxInputCharsPerOpportunity` (type: `integer`): Maximum characters sent to the AI model per opportunity. ## `aiMaxOutputTokens` (type: `integer`): Maximum output tokens requested from the AI model per opportunity. ## `aiTemperature` (type: `number`): Sampling temperature for AI enrichment. Lower values are more deterministic. ## `apifyPpeEnabled` (type: `boolean`): Enable if monetized with Apify pay-per-event. Disable for local development. ## `apifyPpeEventName` (type: `string`): Event to charge for each qualified opportunity. ## `apifyPpeStopOnLimit` (type: `boolean`): If enabled, the Actor stops further AI enrichments when the user's max cost limit is reached. ## `apifyPpeChargeOnlyIfQualified` (type: `boolean`): If enabled, charges only when AI matchScore >= minMatchScore (recommended for buyer-friendly pricing). ## Actor input object example ```json { "startUrls": [ { "url": "https://example.com/procurement/opportunities" } ], "maxRequestsPerCrawl": 200, "maxDepth": 1, "sameHostnameOnly": true, "detailUrlIncludes": [ "rfp", "tender", "solicitation", "opportunity", "procurement" ], "keywords": [], "excludeKeywords": [], "minMatchScore": 60, "maxConcurrency": 20, "requestDelayMillis": 0, "debugLog": false, "aiEnrichmentEnabled": true, "llmApiStyle": "ollama", "llmBaseUrl": "http://localhost:11434", "llmModel": "llama3.1:8b", "aiMaxOpportunities": 50, "aiConcurrency": 3, "aiMaxInputCharsPerOpportunity": 14000, "aiMaxOutputTokens": 900, "aiTemperature": 0.2, "apifyPpeEnabled": true, "apifyPpeEventName": "qualified-opportunity", "apifyPpeStopOnLimit": true, "apifyPpeChargeOnlyIfQualified": true } ``` # Actor output Schema ## `overview` (type: `string`): No description ## `report` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "startUrls": [ { "url": "https://example.com/procurement/opportunities" } ] }; // Run the Actor and wait for it to finish const run = await client.actor("amcllc/rfp-opportunity-scout").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "startUrls": [{ "url": "https://example.com/procurement/opportunities" }] } # Run the Actor and wait for it to finish run = client.actor("amcllc/rfp-opportunity-scout").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "startUrls": [ { "url": "https://example.com/procurement/opportunities" } ] }' | apify call amcllc/rfp-opportunity-scout --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=amcllc/rfp-opportunity-scout", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "RFP Opportunity Scout", "description": "Find RFPs/tenders from user-provided procurement pages, extract details, and use AI to summarize and qualify matches.", "version": "0.1", "x-build-id": "SPC7kMjeN9sy05LJx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/amcllc~rfp-opportunity-scout/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-amcllc-rfp-opportunity-scout", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/amcllc~rfp-opportunity-scout/runs": { "post": { "operationId": "runs-sync-amcllc-rfp-opportunity-scout", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/amcllc~rfp-opportunity-scout/run-sync": { "post": { "operationId": "run-sync-amcllc-rfp-opportunity-scout", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Procurement pages (start URLs)", "type": "array", "description": "Procurement listing pages to crawl (e.g., a portal 'opportunities' page). Provide multiple sources if needed.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "type": "integer", "description": "Maximum number of requests that can be made by this crawler.", "default": 200 }, "maxDepth": { "title": "Max Crawl Depth", "type": "integer", "description": "Maximum link depth from the start URLs. Depth 0 = listing page only. Depth 1 includes detail pages.", "default": 1 }, "sameHostnameOnly": { "title": "Same Hostname Only", "type": "boolean", "description": "If enabled, the crawler only enqueues links from the same hostname as each start URL.", "default": true }, "detailUrlIncludes": { "title": "Detail URL includes (optional)", "type": "array", "description": "Optional list of substrings. If set, only links whose URL contains one of these values are treated as opportunity detail pages.", "default": [ "rfp", "tender", "solicitation", "opportunity", "procurement" ], "items": { "type": "string" } }, "keywords": { "title": "Keywords (optional)", "type": "array", "description": "Keyword pre-filter for detail pages (used before AI). If empty, all detail pages are considered.", "default": [], "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords (optional)", "type": "array", "description": "If any exclude keyword is present, the opportunity is skipped.", "default": [], "items": { "type": "string" } }, "minMatchScore": { "title": "Minimum match score", "type": "integer", "description": "Minimum AI match score (0-100) for an opportunity to be considered qualified.", "default": 60 }, "maxConcurrency": { "title": "Max Concurrency", "type": "integer", "description": "Maximum number of concurrent requests.", "default": 20 }, "requestDelayMillis": { "title": "Request Delay (ms)", "type": "integer", "description": "Optional delay applied at the start of each request handler to reduce load on target servers.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Use Apify Proxy for IP rotation to prevent blocking." }, "debugLog": { "title": "Debug logging", "type": "boolean", "description": "Enable verbose logging (useful for development).", "default": false }, "aiEnrichmentEnabled": { "title": "AI enrichment enabled", "type": "boolean", "description": "When enabled, the Actor uses an LLM (Ollama Cloud or local Ollama) to summarize and qualify opportunities.", "default": true }, "llmApiStyle": { "title": "LLM API style", "enum": [ "ollama", "openai" ], "type": "string", "description": "Which API format to use: 'ollama' (native /api/chat) or 'openai' (OpenAI-compatible /v1/chat/completions).", "default": "ollama" }, "llmBaseUrl": { "title": "LLM base URL", "type": "string", "description": "Base URL for the LLM API. For local Ollama: http://localhost:11434. For Ollama Cloud, set the Cloud base URL here or via LLM_BASE_URL env var.", "default": "http://localhost:11434" }, "llmApiKey": { "title": "LLM API key (optional)", "type": "string", "description": "API key for the LLM provider. Prefer setting LLM_API_KEY (or OLLAMA_API_KEY) as an Actor secret instead of passing it in input." }, "llmModel": { "title": "LLM model", "type": "string", "description": "Model used for structured enrichment. Manage this via LLM_MODEL/OLLAMA_MODEL env vars if you prefer.", "default": "llama3.1:8b" }, "llmChatCompletionsUrl": { "title": "LLM chat completions URL (advanced)", "type": "string", "description": "Optional full URL override for OpenAI-compatible chat completions (e.g., https://.../v1/chat/completions). Takes precedence over llmBaseUrl when llmApiStyle='openai'." }, "aiMaxOpportunities": { "title": "Max AI-enriched opportunities", "type": "integer", "description": "Maximum number of opportunities that will be sent to the AI model for enrichment.", "default": 50 }, "aiConcurrency": { "title": "AI concurrency", "type": "integer", "description": "How many AI enrichment requests can run in parallel.", "default": 3 }, "aiMaxInputCharsPerOpportunity": { "title": "AI input chars per opportunity", "type": "integer", "description": "Maximum characters sent to the AI model per opportunity.", "default": 14000 }, "aiMaxOutputTokens": { "title": "AI max output tokens", "type": "integer", "description": "Maximum output tokens requested from the AI model per opportunity.", "default": 900 }, "aiTemperature": { "title": "AI temperature", "type": "number", "description": "Sampling temperature for AI enrichment. Lower values are more deterministic.", "default": 0.2 }, "apifyPpeEnabled": { "title": "Pay per event (PPE) enabled", "type": "boolean", "description": "Enable if monetized with Apify pay-per-event. Disable for local development.", "default": true }, "apifyPpeEventName": { "title": "PPE event name", "type": "string", "description": "Event to charge for each qualified opportunity.", "default": "qualified-opportunity" }, "apifyPpeStopOnLimit": { "title": "Stop when user limit reached", "type": "boolean", "description": "If enabled, the Actor stops further AI enrichments when the user's max cost limit is reached.", "default": true }, "apifyPpeChargeOnlyIfQualified": { "title": "Charge only if qualified", "type": "boolean", "description": "If enabled, charges only when AI matchScore >= minMatchScore (recommended for buyer-friendly pricing).", "default": 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 } } } } } } } } } } ```