diff --git a/netlify/functions/handleMetadata.js b/netlify/functions/handleMetadata.js deleted file mode 100644 index 5ed0d49..0000000 --- a/netlify/functions/handleMetadata.js +++ /dev/null @@ -1,146 +0,0 @@ -const fetch = require('node-fetch'); // Import for webscraping in fetchContentFromURL() -import { OpenAIApi, Configuration } from 'openai'; -// const { Configuration, OpenAIApi } = require('openai'); - -// Function to fetch content from URL using a web scraping service -async function fetchContentFromURL(url) { - try { - const response = await fetch(url); - if (!response.ok) { - throw new Error(`HTTP error! status: ${response.status}`); - } - return await response.text(); - } catch (error) { - console.error(`Could not fetch content from URL: ${error}`); - throw error; - } -} - -function simplifyContent(content) { - // Denote headings with a marker (like '###') and add a line break - content = content.replace(/(.*?)<\/h[1-6]>/g, '\n### $1\n'); - // Remove script and style elements and their content - let simplifiedContent = content.replace(/.*?<\/script>/gms, ''); - simplifiedContent = simplifiedContent.replace(/.*?<\/style>/gms, ''); - // Remove all remaining HTML tags, leaving the inner text - simplifiedContent = simplifiedContent.replace(/<[^>]+>/g, ''); - // Manually replace common HTML entities - simplifiedContent = simplifiedContent - .replace(/&/g, '&') - .replace(/</g, '<') - .replace(/>/g, '>') - .replace(/"/g, '"') - .replace(/'/g, "'"); - // Remove inline CSS and JavaScript event handlers - simplifiedContent = simplifiedContent.replace(/style\s*=\s*'.*?'/gi, ''); - simplifiedContent = simplifiedContent.replace(/on\w+\s*=\s*".*?"/gi, ''); - // Normalize whitespace without removing sentence punctuation - simplifiedContent = simplifiedContent.replace(/\s+/g, ' ').trim(); - // Condense multiple line breaks into a single one - simplifiedContent = simplifiedContent.replace(/(\r\n|\r|\n){2,}/g, '\n'); - return simplifiedContent; -} - - -// Placeholder function to perform GPT analysis for media type and topics using Mistral-7b via OpenRouter -async function performGPTAnalysis(simplifiedContent, apiKey) { - // Implement logic to send content to Mistral-7b via OpenRouter for GPT analysis - // Send content and receive GPT analysis response - - // this is the code that we tried to use for the GPT Analysis - // try { - // const configuration = new Configuration({ - // apiKey: apiKey, // Use the provided API key - // baseURL: "https://openrouter.ai/api/v1" // Your custom API endpoint - // }); - - // const openai = new OpenAIApi(configuration); - - // // Using the specified prompt - // const prompt = `Analyze the following text and provide the media type and key topics: ${simplifiedContent}`; - - // const completion = await openai.createCompletion({ - // model: "mistralai/mistral-7b-instruct", - // prompt: prompt, - // max_tokens: 150 // Adjust as needed - // }); - - // //return completion.data.choices[0].text.trim(); - // return inferredMediaType; - // } catch (error) { - // console.error('Error with OpenAI completion:', error); - // throw error; - // } - // however, it gives the error below: - // { "error": "Something went wrong", "details": "Configuration is not a constructor" } - - // Placeholder code - const inferredMediaType = ["article"]; - const extractedTopics = ["topic1", "topic2"]; - return { inferredMediaType, extractedTopics }; -} - -// Placeholder function to map inferred values to predefined formats and topics -function mapInferredValues(mediaType, topics) { - // Implement logic to map inferred media type and topics to predefined formats and topics - // Match inferred values with predefined taxonomy - // Placeholder code - const predefinedMediaType = "Article"; - const predefinedTopics = ["Topic 1", "Topic 2"]; - return { predefinedMediaType, predefinedTopics }; -} - -// Placeholder function to format the response -function formatResponse(predefinedMediaType, predefinedTopics) { - // Implement logic to format the extracted metadata into the desired response structure - // Construct the response object - // Placeholder code - const response = { - format: predefinedMediaType, - topics: predefinedTopics, - }; - return response; -} - -export async function handler(event) { - try { - // Extract URL and API Key from the request body - const { url, apiKey } = JSON.parse(event.body); - - // Validate if URL and API Key are present - if (!url || !apiKey) { - return { - statusCode: 400, - body: JSON.stringify({ error: 'URL and API Key are required' }), - }; - } - - // Step 1: Fetch content from the URL using a web scraping service - const fetchedContent = await fetchContentFromURL(url); - - // Step 2: Simplify the fetched content for GPT analysis - const simplifiedContent = simplifyContent(fetchedContent); - - // Step 3: Perform GPT analysis for media type and topics - const { inferredMediaType, extractedTopics } = await performGPTAnalysis(simplifiedContent, apiKey); - - // Step 4: Map inferred values to predefined formats and topics - const { predefinedMediaType, predefinedTopics } = mapInferredValues(inferredMediaType, extractedTopics); - - // Step 5: Format the response - const formattedResponse = formatResponse(predefinedMediaType, predefinedTopics); - - // Return the formatted response - return { - statusCode: 200, - // returning the output of the simplifyContent function, to test the function - body: JSON.stringify(simplifiedContent), - }; - } catch (error) { - console.error('Error occurred:', error.message); - return { - statusCode: 500, - body: JSON.stringify({ error: 'Something went wrong', details: error.message }), - }; - } -} \ No newline at end of file diff --git a/netlify/functions/package-lock.json b/netlify/functions/package-lock.json deleted file mode 100644 index eb2c8b3..0000000 --- a/netlify/functions/package-lock.json +++ /dev/null @@ -1,299 +0,0 @@ -{ - "name": "handle-metadata-function", - "version": "1.0.0", - "lockfileVersion": 3, - "requires": true, - "packages": { - "": { - "name": "handle-metadata-function", - "version": "1.0.0", - "dependencies": { - "he": "^1.2.0", - "node-fetch": "^2.7.0", - "openai": "4.20.0" - } - }, - "node_modules/@types/node": { - "version": "18.18.13", - "resolved": "https://registry.npmjs.org/@types/node/-/node-18.18.13.tgz", - "integrity": "sha512-vXYZGRrSCreZmq1rEjMRLXJhiy8MrIeVasx+PCVlP414N7CJLHnMf+juVvjdprHyH+XRy3zKZLHeNueOpJCn0g==", - "dependencies": { - "undici-types": "~5.26.4" - } - }, - "node_modules/@types/node-fetch": { - "version": "2.6.9", - "resolved": "https://registry.npmjs.org/@types/node-fetch/-/node-fetch-2.6.9.tgz", - "integrity": "sha512-bQVlnMLFJ2d35DkPNjEPmd9ueO/rh5EiaZt2bhqiSarPjZIuIV6bPQVqcrEyvNo+AfTrRGVazle1tl597w3gfA==", - "dependencies": { - "@types/node": "*", - "form-data": "^4.0.0" - } - }, - "node_modules/abort-controller": { - "version": "3.0.0", - "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz", - "integrity": "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==", - "dependencies": { - "event-target-shim": "^5.0.0" - }, - "engines": { - "node": ">=6.5" - } - }, - "node_modules/agentkeepalive": { - "version": "4.5.0", - "resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz", - "integrity": "sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==", - "dependencies": { - "humanize-ms": "^1.2.1" - }, - "engines": { - "node": ">= 8.0.0" - } - }, - "node_modules/asynckit": { - "version": "0.4.0", - "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz", - "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==" - }, - "node_modules/base-64": { - "version": "0.1.0", - "resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz", - "integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA==" - }, - "node_modules/charenc": { - "version": "0.0.2", - "resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz", - "integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==", - "engines": { - "node": "*" - } - }, - "node_modules/combined-stream": { - "version": "1.0.8", - "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz", - "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==", - "dependencies": { - "delayed-stream": "~1.0.0" - }, - "engines": { - "node": ">= 0.8" - } - }, - "node_modules/crypt": { - "version": "0.0.2", - "resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz", - "integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==", - "engines": { - "node": "*" - } - }, - "node_modules/delayed-stream": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz", - "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==", - "engines": { - "node": ">=0.4.0" - } - }, - "node_modules/digest-fetch": { - "version": "1.3.0", - "resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz", - "integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==", - "dependencies": { - "base-64": "^0.1.0", - "md5": "^2.3.0" - } - }, - "node_modules/event-target-shim": { - "version": "5.0.1", - "resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz", - "integrity": "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ==", - "engines": { - "node": ">=6" - } - }, - "node_modules/form-data": { - "version": "4.0.0", - "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz", - "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==", - "dependencies": { - "asynckit": "^0.4.0", - "combined-stream": "^1.0.8", - "mime-types": "^2.1.12" - }, - "engines": { - "node": ">= 6" - } - }, - "node_modules/form-data-encoder": { - "version": "1.7.2", - "resolved": "https://registry.npmjs.org/form-data-encoder/-/form-data-encoder-1.7.2.tgz", - "integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A==" - }, - "node_modules/formdata-node": { - "version": "4.4.1", - "resolved": "https://registry.npmjs.org/formdata-node/-/formdata-node-4.4.1.tgz", - "integrity": "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ==", - "dependencies": { - "node-domexception": "1.0.0", - "web-streams-polyfill": "4.0.0-beta.3" - }, - "engines": { - "node": ">= 12.20" - } - }, - "node_modules/formdata-node/node_modules/web-streams-polyfill": { - "version": "4.0.0-beta.3", - "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz", - "integrity": "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug==", - "engines": { - "node": ">= 14" - } - }, - "node_modules/he": { - "version": "1.2.0", - "resolved": "https://registry.npmjs.org/he/-/he-1.2.0.tgz", - "integrity": "sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==", - "bin": { - "he": "bin/he" - } - }, - "node_modules/humanize-ms": { - "version": "1.2.1", - "resolved": "https://registry.npmjs.org/humanize-ms/-/humanize-ms-1.2.1.tgz", - "integrity": "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ==", - "dependencies": { - "ms": "^2.0.0" - } - }, - "node_modules/is-buffer": { - "version": "1.1.6", - "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz", - "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w==" - }, - "node_modules/md5": { - "version": "2.3.0", - "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz", - "integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==", - "dependencies": { - "charenc": "0.0.2", - "crypt": "0.0.2", - "is-buffer": "~1.1.6" - } - }, - "node_modules/mime-db": { - "version": "1.52.0", - "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz", - "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==", - "engines": { - "node": ">= 0.6" - } - }, - "node_modules/mime-types": { - "version": "2.1.35", - "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz", - "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==", - "dependencies": { - "mime-db": "1.52.0" - }, - "engines": { - "node": ">= 0.6" - } - }, - "node_modules/ms": { - "version": "2.1.3", - "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz", - "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==" - }, - "node_modules/node-domexception": { - "version": "1.0.0", - "resolved": "https://registry.npmjs.org/node-domexception/-/node-domexception-1.0.0.tgz", - "integrity": "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==", - "funding": [ - { - "type": "github", - "url": "https://github.com/sponsors/jimmywarting" - }, - { - "type": "github", - "url": "https://paypal.me/jimmywarting" - } - ], - "engines": { - "node": ">=10.5.0" - } - }, - "node_modules/node-fetch": { - "version": "2.7.0", - "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz", - "integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==", - "dependencies": { - "whatwg-url": "^5.0.0" - }, - "engines": { - "node": "4.x || >=6.0.0" - }, - "peerDependencies": { - "encoding": "^0.1.0" - }, - "peerDependenciesMeta": { - "encoding": { - "optional": true - } - } - }, - "node_modules/openai": { - "version": "4.20.0", - "resolved": "https://registry.npmjs.org/openai/-/openai-4.20.0.tgz", - "integrity": "sha512-VbAYerNZFfIIeESS+OL9vgDkK8Mnri55n+jN0UN/HZeuM0ghGh6nDN6UGRZxslNgyJ7XmY/Ca9DO4YYyvrszGA==", - "dependencies": { - "@types/node": "^18.11.18", - "@types/node-fetch": "^2.6.4", - "abort-controller": "^3.0.0", - "agentkeepalive": "^4.2.1", - "digest-fetch": "^1.3.0", - "form-data-encoder": "1.7.2", - "formdata-node": "^4.3.2", - "node-fetch": "^2.6.7", - "web-streams-polyfill": "^3.2.1" - }, - "bin": { - "openai": "bin/cli" - } - }, - "node_modules/tr46": { - "version": "0.0.3", - "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz", - "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==" - }, - "node_modules/undici-types": { - "version": "5.26.5", - "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz", - "integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==" - }, - "node_modules/web-streams-polyfill": { - "version": "3.2.1", - "resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.2.1.tgz", - "integrity": "sha512-e0MO3wdXWKrLbL0DgGnUV7WHVuw9OUvL4hjgnPkIeEvESk74gAITi5G606JtZPp39cd8HA9VQzCIvA49LpPN5Q==", - "engines": { - "node": ">= 8" - } - }, - "node_modules/webidl-conversions": { - "version": "3.0.1", - "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz", - "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==" - }, - "node_modules/whatwg-url": { - "version": "5.0.0", - "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz", - "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==", - "dependencies": { - "tr46": "~0.0.3", - "webidl-conversions": "^3.0.0" - } - } - } -}