# Llm Response Evaluator (`fiery_dream/llm-response-evaluator`) Actor Evaluate LLM outputs with comprehensive quality metrics and A/B testing capabilities. Free alternative to Confident AI ($99/mo). - **URL**: https://apify.com/fiery\_dream/llm-response-evaluator.md - **Developed by:** [Cody Churchwell](https://apify.com/fiery_dream) (community) - **Categories:** AI, Developer tools, Other - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $0.01 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. 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 ## LLM Response Evaluator & A/B Tester Evaluate LLM outputs with comprehensive quality metrics and A/B testing capabilities. Free alternative to Confident AI ($99/mo). ### Features - **Multi-Metric Evaluation**: Quality, relevance, coherence, toxicity, bias, factuality, creativity, conciseness - **A/B Testing**: Compare model variants with statistical significance testing - **Response Comparison**: Side-by-side evaluation of multiple responses - **Custom Thresholds**: Set quality gates and pass/fail criteria - **Detailed Reports**: Track evaluation trends and model performance over time ### Operations #### evaluate Evaluate a single LLM response across multiple quality metrics. #### compare Compare multiple responses side-by-side and rank by performance. #### abTest Run A/B tests with statistical significance testing to choose the best model. #### generateReport Generate comprehensive evaluation reports with trends and insights. ### Target Use Cases - **Quality Assurance**: Ensure LLM outputs meet quality standards - **Model Selection**: Compare different models and choose the best performer - **A/B Testing**: Test prompt variations and model configurations - **Bias Detection**: Identify and mitigate bias in AI responses ### Pricing - **Free forever** on Apify (pay only for platform usage) - **Competes with**: Confident AI ($99/mo), Patronus AI ($149/mo) - **Target MAU**: 900 users ### Example Usage ```json { "operation": "evaluate", "response": { "id": "resp_123", "prompt": "Explain quantum computing", "response": "Quantum computing uses quantum bits...", "model": "gpt-4" }, "evaluationMetrics": ["quality", "relevance", "toxicity", "bias"] } ```` ### License MIT # Actor input Schema ## `operation` (type: `string`): Action to perform ## `response` (type: `object`): Response to evaluate (JSON) ## `evaluationMetrics` (type: `array`): Metrics to evaluate ## `referenceResponse` (type: `string`): Expected or ideal response for comparison ## `responsesToCompare` (type: `array`): Array of response objects to compare (JSON) ## `abTestConfig` (type: `object`): A/B testing parameters (JSON) ## `reportPeriod` (type: `string`): Time range for evaluation report ## `filterByModel` (type: `string`): Filter evaluations by specific model ## `thresholds` (type: `object`): Minimum acceptable scores (JSON) ## `weightings` (type: `object`): Relative importance of each metric (JSON) ## Actor input object example ```json { "operation": "evaluate", "response": { "id": "resp_123", "prompt": "Explain quantum computing in simple terms", "response": "Quantum computing uses quantum bits...", "model": "gpt-4", "metadata": { "temperature": 0.7, "timestamp": "2025-01-15T10:30:00Z" } }, "evaluationMetrics": [ "quality", "relevance", "toxicity", "bias" ], "responsesToCompare": [ { "id": "resp_1", "response": "Response from Model A...", "model": "gpt-4" }, { "id": "resp_2", "response": "Response from Model B...", "model": "gpt-3.5-turbo" } ], "abTestConfig": { "variantA": { "id": "variant_a", "model": "gpt-4", "responses": [] }, "variantB": { "id": "variant_b", "model": "gpt-3.5-turbo", "responses": [] }, "testCases": [ { "prompt": "Test prompt 1" }, { "prompt": "Test prompt 2" } ], "significanceLevel": 0.05, "minimumSampleSize": 30 }, "reportPeriod": "week", "thresholds": { "quality": 0.7, "relevance": 0.8, "toxicity": 0.1, "bias": 0.2 }, "weightings": { "quality": 0.3, "relevance": 0.3, "toxicity": 0.2, "bias": 0.2 } } ``` # 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 = { "operation": "evaluate", "evaluationMetrics": [ "quality", "relevance", "toxicity", "bias" ], "reportPeriod": "week" }; // Run the Actor and wait for it to finish const run = await client.actor("fiery_dream/llm-response-evaluator").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 = { "operation": "evaluate", "evaluationMetrics": [ "quality", "relevance", "toxicity", "bias", ], "reportPeriod": "week", } # Run the Actor and wait for it to finish run = client.actor("fiery_dream/llm-response-evaluator").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 '{ "operation": "evaluate", "evaluationMetrics": [ "quality", "relevance", "toxicity", "bias" ], "reportPeriod": "week" }' | apify call fiery_dream/llm-response-evaluator --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=fiery_dream/llm-response-evaluator", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Llm Response Evaluator", "description": "Evaluate LLM outputs with comprehensive quality metrics and A/B testing capabilities. Free alternative to Confident AI ($99/mo).", "version": "1.0", "x-build-id": "AcidBW6xnCctUbve9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fiery_dream~llm-response-evaluator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fiery_dream-llm-response-evaluator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fiery_dream~llm-response-evaluator/runs": { "post": { "operationId": "runs-sync-fiery_dream-llm-response-evaluator", "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/fiery_dream~llm-response-evaluator/run-sync": { "post": { "operationId": "run-sync-fiery_dream-llm-response-evaluator", "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": { "operation": { "title": "Operation", "enum": [ "evaluate", "compare", "abTest", "generateReport" ], "type": "string", "description": "Action to perform", "default": "evaluate" }, "response": { "title": "LLM Response", "type": "object", "description": "Response to evaluate (JSON)" }, "evaluationMetrics": { "title": "Evaluation Metrics", "type": "array", "description": "Metrics to evaluate", "default": [ "quality", "relevance", "toxicity", "bias" ], "items": { "type": "string" } }, "referenceResponse": { "title": "Reference Response", "type": "string", "description": "Expected or ideal response for comparison" }, "responsesToCompare": { "title": "Responses to Compare", "type": "array", "description": "Array of response objects to compare (JSON)" }, "abTestConfig": { "title": "A/B Test Configuration", "type": "object", "description": "A/B testing parameters (JSON)" }, "reportPeriod": { "title": "Report Period", "enum": [ "today", "week", "month", "all" ], "type": "string", "description": "Time range for evaluation report", "default": "week" }, "filterByModel": { "title": "Filter by Model", "type": "string", "description": "Filter evaluations by specific model" }, "thresholds": { "title": "Quality Thresholds", "type": "object", "description": "Minimum acceptable scores (JSON)" }, "weightings": { "title": "Metric Weightings", "type": "object", "description": "Relative importance of each metric (JSON)" } } }, "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 } } } } } } } } } } ```