@aj-archipelago/cortex 1.0.20 → 1.0.21

package/helper_apps/HealthCheck/.funcignore

@@ -0,0 +1,10 @@
+*.js.map
+*.ts
+.git*
+.vscode
+__azurite_db*__.json
+__blobstorage__
+__queuestorage__
+local.settings.json
+test
+tsconfig.json

package/helper_apps/HealthCheck/host.json

@@ -0,0 +1,15 @@
+{
+  "version": "2.0",
+  "logging": {
+    "applicationInsights": {
+      "samplingSettings": {
+        "isEnabled": true,
+        "excludedTypes": "Request"
+      }
+    }
+  },
+  "extensionBundle": {
+    "id": "Microsoft.Azure.Functions.ExtensionBundle",
+    "version": "[3.*, 4.0.0)"
+  }
+}

package/helper_apps/HealthCheck/package-lock.json

@@ -0,0 +1,142 @@
+{
+  "name": "healthcheck",
+  "version": "1.0.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "healthcheck",
+      "version": "1.0.0",
+      "dependencies": {
+        "@azure/functions": "^4.0.0",
+        "axios": "^1.6.0"
+      }
+    },
+    "node_modules/@azure/functions": {
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/@azure/functions/-/functions-4.0.1.tgz",
+      "integrity": "sha512-Ol38b4XOlu6IDkLnO91HaYeo2utMixG0LIA1NR9Qehu17U/cGjNx+bAcOEdNlSJWNYh5ChhzjxA/uFB5dQJtmg==",
+      "dependencies": {
+        "long": "^4.0.0",
+        "undici": "^5.13.0"
+      },
+      "engines": {
+        "node": ">=18.0"
+      }
+    },
+    "node_modules/@fastify/busboy": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/@fastify/busboy/-/busboy-2.0.0.tgz",
+      "integrity": "sha512-JUFJad5lv7jxj926GPgymrWQxxjPYuJNiNjNMzqT+HiuP6Vl3dk5xzG+8sTX96np0ZAluvaMzPsjhHZ5rNuNQQ==",
+      "engines": {
+        "node": ">=14"
+      }
+    },
+    "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/axios": {
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.6.0.tgz",
+      "integrity": "sha512-EZ1DYihju9pwVB+jg67ogm+Tmqc6JmhamRN6I4Zt8DfZu5lbcQGw3ozH9lFejSJgs/ibaef3A9PMXPLeefFGJg==",
+      "dependencies": {
+        "follow-redirects": "^1.15.0",
+        "form-data": "^4.0.0",
+        "proxy-from-env": "^1.1.0"
+      }
+    },
+    "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/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/follow-redirects": {
+      "version": "1.15.3",
+      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.3.tgz",
+      "integrity": "sha512-1VzOtuEM8pC9SFU1E+8KfTjZyMztRsgEfwQl44z8A25uy13jSzTj6dyK2Df52iV0vgHCfBwLhDWevLn95w5v6Q==",
+      "funding": [
+        {
+          "type": "individual",
+          "url": "https://github.com/sponsors/RubenVerborgh"
+        }
+      ],
+      "engines": {
+        "node": ">=4.0"
+      },
+      "peerDependenciesMeta": {
+        "debug": {
+          "optional": true
+        }
+      }
+    },
+    "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/long": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/long/-/long-4.0.0.tgz",
+      "integrity": "sha512-XsP+KhQif4bjX1kbuSiySJFNAehNxgLb6hPRGJ9QsUr8ajHkuXGdrHmFUTUUXhDwVX2R5bY4JNZEwbUiMhV+MA=="
+    },
+    "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/proxy-from-env": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
+      "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="
+    },
+    "node_modules/undici": {
+      "version": "5.27.0",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-5.27.0.tgz",
+      "integrity": "sha512-l3ydWhlhOJzMVOYkymLykcRRXqbUaQriERtR70B9LzNkZ4bX52Fc8wbTDneMiwo8T+AemZXvXaTx+9o5ROxrXg==",
+      "dependencies": {
+        "@fastify/busboy": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=14.0"
+      }
+    }
+  }
+}

package/helper_apps/HealthCheck/package.json

@@ -0,0 +1,14 @@
+{
+  "name": "healthcheck",
+  "version": "1.0.0",
+  "description": "",
+  "scripts": {
+    "start": "func start",
+    "test": "echo \"No tests yet...\""
+  },
+  "dependencies": {
+    "@azure/functions": "^4.0.0",
+    "axios": "^1.6.0"
+  },
+  "main": "src/functions/*.js"
+}

package/helper_apps/HealthCheck/src/functions/timerTrigger.js

@@ -0,0 +1,13 @@
+const { app } = require('@azure/functions');
+const { transcribeHealthCheck } = require('../transcribeHealthCheck');
+
+app.timer('timerTrigger', {
+    schedule: '0 0 * * * *',
+    // schedule: '0 * * * * *',
+    runOnStartup: true,
+    handler: async (myTimer, context) => {
+        context.log('Timer function starting request.');
+        await transcribeHealthCheck(context, 0);
+        context.log('Timer function processed request.');
+    }
+});

package/helper_apps/HealthCheck/src/transcribeHealthCheck.js

@@ -0,0 +1,93 @@
+const axios = require('axios');
+
+const API_URL = process.env.API_URL;
+const API_SUBSCRIPTION_KEY = process.env.API_SUBSCRIPTION_KEY;
+
+async function transcribeHealthCheck(context, runCount) {
+    try {
+        const query = `
+            query Transcribe($file: String!, $text: String, $wordTimestamped: Boolean, $responseFormat: String, $async: Boolean) {
+                transcribe(
+                    file: $file
+                    text: $text
+                    wordTimestamped: $wordTimestamped
+                    responseFormat: $responseFormat
+                    async: $async
+                ) {
+                    result
+                    __typename
+                }
+            }
+        `;
+
+        const variables = {
+            "file": "https://www.youtube.com/watch?v=SCvWXEFb8jE",
+            "wordTimestamped": true,
+            "responseFormat": "srt",
+            "async": false
+        };
+
+        const response = await axios({
+            url: API_URL,
+            method: 'post',
+            data: {
+                query: query,
+                variables: variables
+            },
+            headers: {
+                'Ocp-Apim-Subscription-Key': API_SUBSCRIPTION_KEY
+            },
+        });
+
+        context.log(response.data);
+
+        const transcribeText =  response.data.data.transcribe.result;
+
+        if (!validateTranscribeText(transcribeText)) {
+            throw new Error("Invalid transcribe text");
+        } else {
+            context.log("Transcribe text is valid");
+        }        
+
+    } catch (error) {
+        context.error(error);
+        if(runCount < 1){
+            transcribeHealthCheck(context, runCount + 1);
+        }else{
+            throw new Error("Error in transcribeHealthCheck");
+        }
+    }
+}
+
+
+//validate transcribeText similar to below str:
+/*
+'1
+00:00:00,140 --> 00:00:00,640
+You
+
+2
+00:00:00,640 --> 00:00:00,820
+may
+...cor
+*/
+// Validate transcribeText
+const validateTranscribeText = (text) => {
+    let numberLineRegex = /^\d+$/m;
+    let timeFormatRegex = /^\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3}$/m;
+    let wordLineRegex = /^\w+$/m;
+    
+    let hasNumberLine = numberLineRegex.test(text);
+    let hasTimeFormatLine = timeFormatRegex.test(text);
+    let hasWordLine = wordLineRegex.test(text);
+    
+    if(hasNumberLine && hasTimeFormatLine && hasWordLine){
+        return true;
+    }
+    return false;
+}
+
+
+
+
+module.exports = { transcribeHealthCheck };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aj-archipelago/cortex",
-  "version": "1.0.20",
+  "version": "1.0.21",
   "description": "Cortex is a GraphQL API for AI. It provides a simple, extensible interface for using AI services from OpenAI, Azure and others.",
   "repository": {
     "type": "git",

package/pathways/cognitive_insert.js

@@ -2,6 +2,8 @@ export default {
     prompt: `{{text}}`,
     model: 'azure-cognitive',
     inputParameters: {
+        calculateInputVector: false,
+        indexName: ``,
         inputVector: ``,
         file: ``,
         privateData: true,

package/server/plugins/azureCognitivePlugin.js

@@ -17,11 +17,22 @@ class AzureCognitivePlugin extends ModelPlugin {
         super(config, pathway, modelName, model);
     }
 
+    async getInputVector (text) {
+        try{
+            if(!text || !text.trim()){
+                return;
+            }
+            return JSON.parse(await callPathway(this.config, 'embeddings', { text }))[0];
+        }catch(err){
+            console.log(`Error in calculating input vector for text: ${text}, error: ${err}`);
+        }
+    }
+
     // Set up parameters specific to the Azure Cognitive API
     async getRequestParameters(text, parameters, prompt, mode, indexName, savedContextId,  {headers, requestId, pathway, url}) {
         const combinedParameters = { ...this.promptParameters, ...parameters };
         const { modelPromptText } = this.getCompiledPrompt(text, combinedParameters, prompt);
-        const { inputVector, filter, docId } = combinedParameters;
+        const { inputVector, calculateInputVector, privateData, filter, docId } = combinedParameters;
         const data = {};
 
         if (mode == 'delete') {
@@ -54,30 +65,22 @@ class AzureCognitivePlugin extends ModelPlugin {
 
         if (mode == 'index') {
 
-            /*
-            const calculateInputVector = async () => {
-                try{
-                    if(!text || !text.trim()){
-                        return;
-                    }
-                    return JSON.parse(await callPathway(this.config, 'embeddings', { text }))[0];
-                }catch(err){
-                    console.log(`Error in calculating input vector for text: ${text}, error: ${err}`);
-                }
-            }
-            */
-
             const doc = {
                 id: uuidv4(),
                 content: text,
-                //contentVector: inputVector || (await calculateInputVector()),
                 owner: savedContextId,
                 docId: docId || uuidv4(),
                 createdAt: new Date().toISOString()
             }
-            // if(!privateData){
-            //     delete doc.owner;
-            // }
+
+            if(inputVector || calculateInputVector){ //if input vector is provided or needs to be calculated
+                doc.contentVector = inputVector ? inputVector : await this.getInputVector(text);
+            }
+
+            if(!privateData){ //if public, remove owner
+                delete doc.owner;
+            }
+            
             data.value = [doc];
             return { data };
         }