doc2vec 2.4.0 → 2.5.0

package/README.md

@@ -145,6 +145,9 @@ Configuration is managed through two files:
     OPENAI_API_KEY="sk-..."
     OPENAI_MODEL="text-embedding-3-large"  # Optional, defaults to text-embedding-3-large
 
+    # Optional: Embedding dimension size (defaults to 3072)
+    EMBEDDING_DIMENSION="3072"
+
     # Required: Your Azure OpenAI credentials (if using Azure provider)
     AZURE_OPENAI_KEY="your-azure-key"
     AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
@@ -223,6 +226,10 @@ Configuration is managed through two files:
                     *   `qdrant_port`: (Optional) Port for the Qdrant REST API. Defaults to `443` if `qdrant_url` starts with `https`, otherwise `6333`.
                     *   `collection_name`: (Optional) Name of the Qdrant collection to use. Defaults to `<product_name>_<version>` (lowercased, spaces replaced with underscores).
 
+        Optional embedding configuration:
+        *   `embedding.provider`: Provider for embeddings (`openai` or `azure`).
+        *   `embedding.dimension`: Embedding vector size. Defaults to `3072` when not set.
+
     **Example (`config.yaml`):**
     ```yaml
     # Optional: Configure embedding provider
@@ -230,6 +237,7 @@ Configuration is managed through two files:
     # Defaults to OpenAI if not specified
     embedding:
       provider: 'openai'  # or 'azure'
+      dimension: 3072  # Optional, defaults to 3072
       openai:
         api_key: '${OPENAI_API_KEY}'  # Optional, uses env var by default
         model: 'text-embedding-3-large'  # Optional, defaults to text-embedding-3-large

package/dist/content-processor.js

@@ -586,7 +586,7 @@ class ContentProcessor {
                         logger.debug(`Finding links on page ${url}`);
                         let newLinksFound = 0;
                         for (const href of result.links) {
-                            const fullUrl = utils_1.Utils.buildUrl(href, pageUrlForLinks);
+                            const fullUrl = utils_1.Utils.buildUrl(href, pageUrlForLinks, logger);
                             if (fullUrl.startsWith(sourceConfig.url)) {
                                 addReferrer(fullUrl, pageUrlForLinks);
                                 if (!visitedUrls.has(utils_1.Utils.normalizeUrl(fullUrl))) {

package/dist/database.js

@@ -44,7 +44,7 @@ const sqliteVec = __importStar(require("sqlite-vec"));
 const js_client_rest_1 = require("@qdrant/js-client-rest");
 const utils_1 = require("./utils");
 class DatabaseManager {
-    static async initDatabase(config, parentLogger) {
+    static async initDatabase(config, parentLogger, embeddingDimension) {
         const logger = parentLogger.child('database');
         const dbConfig = config.database_config;
         if (dbConfig.type === 'sqlite') {
@@ -53,10 +53,10 @@ class DatabaseManager {
             logger.info(`Opening SQLite database at ${dbPath}`);
             const db = new better_sqlite3_1.default(dbPath, { allowExtension: true });
             sqliteVec.load(db);
-            logger.debug(`Creating vec_items table if it doesn't exist`);
+            logger.debug(`Creating vec_items table if it doesn't exist (dimension: ${embeddingDimension})`);
             db.exec(`
                 CREATE VIRTUAL TABLE IF NOT EXISTS vec_items USING vec0(
-                    embedding FLOAT[3072],
+                    embedding FLOAT[${embeddingDimension}],
                     product_name TEXT,
                     version TEXT,
                     branch TEXT,
@@ -81,7 +81,7 @@ class DatabaseManager {
             const collectionName = params.collection_name || `${config.product_name.toLowerCase().replace(/\s+/g, '_')}_${config.version}`;
             logger.info(`Connecting to Qdrant at ${qdrantUrl}:${qdrantPort}, collection: ${collectionName}`);
             const qdrantClient = new js_client_rest_1.QdrantClient({ url: qdrantUrl, apiKey: process.env.QDRANT_API_KEY, port: qdrantPort });
-            await this.createCollectionQdrant(qdrantClient, collectionName, logger);
+            await this.createCollectionQdrant(qdrantClient, collectionName, logger, embeddingDimension);
             logger.info(`Qdrant connection established successfully`);
             return { client: qdrantClient, collectionName, type: 'qdrant' };
         }
@@ -91,7 +91,7 @@ class DatabaseManager {
             throw new Error(errMsg);
         }
     }
-    static async createCollectionQdrant(qdrantClient, collectionName, logger) {
+    static async createCollectionQdrant(qdrantClient, collectionName, logger, embeddingDimension) {
         try {
             logger.debug(`Checking if collection ${collectionName} exists`);
             const collections = await qdrantClient.getCollections();
@@ -100,10 +100,10 @@ class DatabaseManager {
                 logger.info(`Collection ${collectionName} already exists`);
                 return;
             }
-            logger.info(`Creating new collection ${collectionName}`);
+            logger.info(`Creating new collection ${collectionName} with dimension ${embeddingDimension}`);
             await qdrantClient.createCollection(collectionName, {
                 vectors: {
-                    size: 3072,
+                    size: embeddingDimension,
                     distance: "Cosine",
                 },
             });
@@ -181,7 +181,7 @@ class DatabaseManager {
         }
         return defaultValue;
     }
-    static async setMetadataValue(dbConnection, key, value, logger) {
+    static async setMetadataValue(dbConnection, key, value, logger, embeddingDimension) {
         try {
             if (dbConnection.type === 'sqlite') {
                 const stmt = dbConnection.db.prepare(`
@@ -193,8 +193,7 @@ class DatabaseManager {
             }
             else if (dbConnection.type === 'qdrant') {
                 const metadataUUID = utils_1.Utils.generateMetadataUUID(key);
-                const dummyEmbeddingSize = 3072;
-                const dummyEmbedding = new Array(dummyEmbeddingSize).fill(0);
+                const dummyEmbedding = new Array(embeddingDimension).fill(0);
                 const metadataPoint = {
                     id: metadataUUID,
                     vector: dummyEmbedding,
@@ -258,7 +257,7 @@ class DatabaseManager {
         logger.info(`No saved run date found for ${repo}, using default: ${defaultDate}`);
         return defaultDate;
     }
-    static async updateLastRunDate(dbConnection, repo, logger) {
+    static async updateLastRunDate(dbConnection, repo, logger, embeddingDimension) {
         const now = new Date().toISOString();
         try {
             if (dbConnection.type === 'sqlite') {
@@ -276,8 +275,7 @@ class DatabaseManager {
                 const metadataKey = `last_run_${repo.replace('/', '_')}`;
                 logger.debug(`Using UUID: ${metadataUUID} for metadata`);
                 // Generate a dummy embedding (all zeros)
-                const dummyEmbeddingSize = 3072; // Same size as your content embeddings
-                const dummyEmbedding = new Array(dummyEmbeddingSize).fill(0);
+                const dummyEmbedding = new Array(embeddingDimension).fill(0);
                 // Create a point with special metadata payload
                 const metadataPoint = {
                     id: metadataUUID,

package/dist/doc2vec.js

@@ -72,6 +72,7 @@ class Doc2Vec {
         // Check environment variable if not specified in config
         const embeddingProvider = this.config.embedding?.provider || process.env.EMBEDDING_PROVIDER || 'openai';
         const embeddingConfig = this.config.embedding || { provider: embeddingProvider };
+        this.embeddingDimension = this.resolveEmbeddingDimension(embeddingConfig);
         if (embeddingProvider === 'azure') {
             const azureApiKey = embeddingConfig.azure?.api_key || process.env.AZURE_OPENAI_KEY;
             const azureEndpoint = embeddingConfig.azure?.endpoint || process.env.AZURE_OPENAI_ENDPOINT;
@@ -88,7 +89,7 @@ class Doc2Vec {
                 apiVersion: azureApiVersion,
             });
             this.embeddingModel = azureDeploymentName;
-            this.logger.info(`Using Azure OpenAI with deployment: ${azureDeploymentName}`);
+            this.logger.info(`Using Azure OpenAI with deployment: ${azureDeploymentName} (${this.embeddingDimension} dimensions)`);
         }
         else {
             const openaiApiKey = embeddingConfig.openai?.api_key || process.env.OPENAI_API_KEY;
@@ -99,7 +100,7 @@ class Doc2Vec {
             }
             this.openai = new openai_1.OpenAI({ apiKey: openaiApiKey });
             this.embeddingModel = openaiModel;
-            this.logger.info(`Using OpenAI with model: ${openaiModel}`);
+            this.logger.info(`Using OpenAI with model: ${openaiModel} (${this.embeddingDimension} dimensions)`);
         }
         this.contentProcessor = new content_processor_1.ContentProcessor(this.logger);
     }
@@ -144,6 +145,21 @@ class Doc2Vec {
             process.exit(1);
         }
     }
+    resolveEmbeddingDimension(embeddingConfig) {
+        const defaultDimension = 3072;
+        const rawConfigValue = embeddingConfig?.dimension;
+        const rawEnvValue = process.env.EMBEDDING_DIMENSION;
+        const candidate = rawConfigValue ?? (rawEnvValue ? Number(rawEnvValue) : undefined);
+        if (candidate === undefined) {
+            return defaultDimension;
+        }
+        const parsedValue = typeof candidate === 'string' ? Number(candidate) : candidate;
+        if (!Number.isFinite(parsedValue) || parsedValue <= 0 || !Number.isInteger(parsedValue)) {
+            this.logger.warn(`Invalid embedding dimension provided (${candidate}), falling back to ${defaultDimension}`);
+            return defaultDimension;
+        }
+        return parsedValue;
+    }
     async run() {
         this.logger.section('PROCESSING SOURCES');
         for (const sourceConfig of this.config.sources) {
@@ -373,13 +389,13 @@ class Doc2Vec {
             await processIssue(issues[i]);
         }
         // Update the last run date in the database after processing all issues
-        await database_1.DatabaseManager.updateLastRunDate(dbConnection, repo, logger);
+        await database_1.DatabaseManager.updateLastRunDate(dbConnection, repo, logger, this.embeddingDimension);
         logger.info(`Successfully processed ${issues.length} issues`);
     }
     async processGithubRepo(config, parentLogger) {
         const logger = parentLogger.child('process');
         logger.info(`Starting processing for GitHub repo: ${config.repo}`);
-        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger);
+        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger, this.embeddingDimension);
         // Initialize metadata storage
         await database_1.DatabaseManager.initDatabaseMetadata(dbConnection, logger);
         logger.section('GITHUB ISSUES');
@@ -390,7 +406,7 @@ class Doc2Vec {
     async processWebsite(config, parentLogger) {
         const logger = parentLogger.child('process');
         logger.info(`Starting processing for website: ${config.url}`);
-        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger);
+        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger, this.embeddingDimension);
         await database_1.DatabaseManager.initDatabaseMetadata(dbConnection, logger);
         const validChunkIds = new Set();
         const visitedUrls = new Set();
@@ -420,7 +436,7 @@ class Doc2Vec {
                 return database_1.DatabaseManager.getMetadataValue(dbConnection, `etag:${url}`, undefined, logger);
             },
             set: async (url, etag) => {
-                await database_1.DatabaseManager.setMetadataValue(dbConnection, `etag:${url}`, etag, logger);
+                await database_1.DatabaseManager.setMetadataValue(dbConnection, `etag:${url}`, etag, logger, this.embeddingDimension);
             },
         };
         const lastmodStore = {
@@ -428,7 +444,7 @@ class Doc2Vec {
                 return database_1.DatabaseManager.getMetadataValue(dbConnection, `lastmod:${url}`, undefined, logger);
             },
             set: async (url, lastmod) => {
-                await database_1.DatabaseManager.setMetadataValue(dbConnection, `lastmod:${url}`, lastmod, logger);
+                await database_1.DatabaseManager.setMetadataValue(dbConnection, `lastmod:${url}`, lastmod, logger, this.embeddingDimension);
             },
         };
         const crawlResult = await this.contentProcessor.crawlWebsite(config.url, config, async (url, content) => {
@@ -502,7 +518,7 @@ class Doc2Vec {
     async processLocalDirectory(config, parentLogger) {
         const logger = parentLogger.child('process');
         logger.info(`Starting processing for local directory: ${config.path}`);
-        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger);
+        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger, this.embeddingDimension);
         const validChunkIds = new Set();
         const processedFiles = new Set();
         logger.section('FILE SCANNING AND EMBEDDING');
@@ -560,7 +576,7 @@ class Doc2Vec {
     async processCodeSource(config, parentLogger) {
         const logger = parentLogger.child('process');
         logger.info(`Starting processing for code source (${config.source})`);
-        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger);
+        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger, this.embeddingDimension);
         const validChunkIds = new Set();
         const processedFiles = new Set();
         let basePath;
@@ -692,10 +708,10 @@ class Doc2Vec {
                             await database_1.DatabaseManager.removeChunksByUrlQdrant(dbConnection, url, logger);
                         }
                     }
-                    await database_1.DatabaseManager.setMetadataValue(dbConnection, fileListKey, JSON.stringify(currentList), logger);
+                    await database_1.DatabaseManager.setMetadataValue(dbConnection, fileListKey, JSON.stringify(currentList), logger, this.embeddingDimension);
                     if (lastMtimeKey) {
                         const nextMtime = maxObservedMtime > 0 ? maxObservedMtime : Date.now();
-                        await database_1.DatabaseManager.setMetadataValue(dbConnection, lastMtimeKey, `${nextMtime}`, logger);
+                        await database_1.DatabaseManager.setMetadataValue(dbConnection, lastMtimeKey, `${nextMtime}`, logger, this.embeddingDimension);
                     }
                 }
             }
@@ -713,7 +729,7 @@ class Doc2Vec {
                 const headSha = await this.getRepoHeadSha(basePath, logger);
                 if (headSha) {
                     const shaKey = this.buildCodeShaMetadataKey(config.repo, repoBranch);
-                    await database_1.DatabaseManager.setMetadataValue(dbConnection, shaKey, headSha, logger);
+                    await database_1.DatabaseManager.setMetadataValue(dbConnection, shaKey, headSha, logger, this.embeddingDimension);
                 }
             }
             if (tempDir) {
@@ -876,7 +892,7 @@ class Doc2Vec {
     async processZendesk(config, parentLogger) {
         const logger = parentLogger.child('process');
         logger.info(`Starting processing for Zendesk: ${config.zendesk_subdomain}.zendesk.com`);
-        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger);
+        const dbConnection = await database_1.DatabaseManager.initDatabase(config, logger, this.embeddingDimension);
         // Initialize metadata storage
         await database_1.DatabaseManager.initDatabaseMetadata(dbConnection, logger);
         const fetchTickets = config.fetch_tickets !== false; // default true
@@ -1051,7 +1067,7 @@ class Doc2Vec {
             }
         }
         // Update the last run date in the database
-        await database_1.DatabaseManager.updateLastRunDate(dbConnection, `zendesk_tickets_${config.zendesk_subdomain}`, logger);
+        await database_1.DatabaseManager.updateLastRunDate(dbConnection, `zendesk_tickets_${config.zendesk_subdomain}`, logger, this.embeddingDimension);
         logger.info(`Successfully processed ${totalTickets} tickets`);
     }
     async fetchAndProcessZendeskArticles(config, dbConnection, logger) {

package/dist/utils.js

@@ -69,12 +69,14 @@ class Utils {
             return url;
         }
     }
-    static buildUrl(href, currentUrl) {
+    static buildUrl(href, currentUrl, logger) {
         try {
             return new URL(href, currentUrl).toString();
         }
         catch (error) {
-            console.warn(`Invalid URL found: ${href}`);
+            if (logger) {
+                logger.warn(`Invalid URL found: ${href}`);
+            }
             return '';
         }
     }

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "doc2vec",
-    "version": "2.4.0",
+    "version": "2.5.0",
     "type": "commonjs",
     "description": "",
     "main": "dist/doc2vec.js",