Currently we only have the standard meeting document and the config right now prevents the programm from running. Can be adapted later

REST API & Auto Naming

See merge request proj-wise2526-video2document/video2document!31

main.js

@@ -183,7 +183,9 @@ electron.ipcMain.on("file_submit", async (event, args) => {
         // TODO implement documentation module
         // This code handles the Text to Document processing module call
         for (let i = 0; i < args.document.styles.length; i++) {
-            await mapFunctions.get("module-handler").function(args.document.module, {prompt: args.document.styles[i].prompt, transcript: transcriptpath}).then(resp => {
+            console.log(`\n\n Running the LLM for Document Style ${i+1}`);
+
+            await mapFunctions.get("module-handler").function(args.document.module, {inputTranscriptPath: transcriptpath, documentTypePath: "/Users/mikehughes/PROJ/video2document/storage/documentType/meetingReport.json", language: "en"}).then(resp => {
                 console.log(resp);
                 transcriptpath = resp
                 curstep++

package-lock.json

@@ -451,22 +451,27 @@
       }
     },
     "node_modules/body-parser": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.2.0.tgz",
-      "integrity": "sha512-02qvAaxv8tp7fBa/mw1ga98OGm+eCbqzJOKoRt70sLmfEEi+jyBYVTDGfCL/k06/4EMk/z01gCe7HoCH/f2LTg==",
+      "version": "2.2.1",
+      "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.2.1.tgz",
+      "integrity": "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw==",
+      "license": "MIT",
       "dependencies": {
         "bytes": "^3.1.2",
         "content-type": "^1.0.5",
-        "debug": "^4.4.0",
+        "debug": "^4.4.3",
         "http-errors": "^2.0.0",
-        "iconv-lite": "^0.6.3",
+        "iconv-lite": "^0.7.0",
         "on-finished": "^2.4.1",
         "qs": "^6.14.0",
-        "raw-body": "^3.0.0",
-        "type-is": "^2.0.0"
+        "raw-body": "^3.0.1",
+        "type-is": "^2.0.1"
       },
       "engines": {
         "node": ">=18"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/express"
       }
     },
     "node_modules/boolean": {
@@ -1612,14 +1617,19 @@
       }
     },
     "node_modules/iconv-lite": {
-      "version": "0.6.3",
-      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
-      "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
+      "version": "0.7.0",
+      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.0.tgz",
+      "integrity": "sha512-cf6L2Ds3h57VVmkZe+Pn+5APsT7FpqJtEhhieDCvrE2MK5Qk9MyffgQyuxQTm6BChfeZNtcOLHp9IcWRVcIcBQ==",
+      "license": "MIT",
       "dependencies": {
         "safer-buffer": ">= 2.1.2 < 3.0.0"
       },
       "engines": {
         "node": ">=0.10.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/express"
       }
     },
     "node_modules/inherits": {
@@ -1708,11 +1718,12 @@
       }
     },
     "node_modules/jws": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/jws/-/jws-4.0.0.tgz",
-      "integrity": "sha512-KDncfTmOZoOMTFG4mBlG0qUIOlc03fmzH+ru6RgYVZhPkyiy/92Owlt/8UEN+a4TXR1FQetfIpJE8ApdvdVxTg==",
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/jws/-/jws-4.0.1.tgz",
+      "integrity": "sha512-EKI/M/yqPncGUUh44xz0PxSidXFr/+r0pA70+gIYhjv+et7yxM+s29Y+VGDkovRofQem0fs7Uvf4+YmAdyRduA==",
+      "license": "MIT",
       "dependencies": {
-        "jwa": "^2.0.0",
+        "jwa": "^2.0.1",
         "safe-buffer": "^5.0.1"
       }
     },
@@ -2077,21 +2088,6 @@
         "node": ">= 0.10"
       }
     },
-    "node_modules/raw-body/node_modules/iconv-lite": {
-      "version": "0.7.0",
-      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.0.tgz",
-      "integrity": "sha512-cf6L2Ds3h57VVmkZe+Pn+5APsT7FpqJtEhhieDCvrE2MK5Qk9MyffgQyuxQTm6BChfeZNtcOLHp9IcWRVcIcBQ==",
-      "dependencies": {
-        "safer-buffer": ">= 2.1.2 < 3.0.0"
-      },
-      "engines": {
-        "node": ">=0.10.0"
-      },
-      "funding": {
-        "type": "opencollective",
-        "url": "https://opencollective.com/express"
-      }
-    },
     "node_modules/readable-stream": {
       "version": "3.6.2",
       "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",

services/modules/llm-gemini/gemini.js

@@ -4,9 +4,10 @@ if (!fs.existsSync(outputDir)) {
     fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
 }
 
-const ai = new genai.GoogleGenAI({ 
-    apiKey: process.env.GOOGLE_API_KEY // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
-});
+// Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+
+const GEMINI_API_KEY = process.env.GOOGLE_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; //URL for the REST call, used model and action
 
 module.exports = {
     name: "llm-gemini",
@@ -31,19 +32,39 @@ module.exports = {
 
     createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
         try {
-            const transcript = await fs.promises.readFile(transcriptPath, "utf-8");
-            const documentType = await fs.promises.readFile(documentTypePath, "utf-8");
+            const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
+            const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
+            const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed
 
-            const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`;
-
-            const response = await ai.models.generateContent({
-                model: "gemini-2.5-flash", // Specify the Gemini model to use
-                contents: promptText // Input prompt for content generation
+            // --- REST CALL ---
+            const response = await fetch(`${GEMINI_URL}?key=${GEMINI_API_KEY}`, { //safe model response in variable
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/json"
+                },
+                body: JSON.stringify({
+                    contents: [
+                        {
+                            parts: [
+                                { text: promptText } // Input prompt for content generation
+                            ]
+                        }
+                    ]
+                })
             });
 
-            const output = response.text || ""; // Get generated text from response or default to empty string (if null)
+            if (!response.ok) { //ok is true when a responce was successfull
+                const text = await response.text();
+                throw new Error(`Gemini API error (${response.status}): ${text}`);
+            }
 
-            const outPath = path.join(outputDir, "test.md"); // Output file path & name TO BE DONE to make dynamic out of input transcript name
+            const data = await response.json();
+
+            // Get generated text from response or default to empty string (if null)
+            const output = data?.candidates?.[0]?.content?.parts?.[0]?.text || "";
+            let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file 
+            console.log(inputTranscriptName);
+            const outPath = path.join(outputDir, `${inputTranscriptName}.md`); // Output file path & name to make naming dynamic. Pulled from input transcript name
             fs.writeFileSync(outPath, output, "utf8"); // Write output to file
 
             console.log("Generated document written to:", outPath);