Fix present diminsions on vectorDBs to be inferred for providers who …

…require it (#605)

server/utils/EmbeddingEngines/azureOpenAi/index.js

@@ -13,7 +13,6 @@ class AzureOpenAiEmbedder {
       new AzureKeyCredential(process.env.AZURE_OPENAI_KEY)
     );
     this.openai = openai;
-    this.dimensions = 1536;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     // https://learn.microsoft.com/en-us/azure/ai-services/openai/faq#i-am-trying-to-use-embeddings-and-received-the-error--invalidrequesterror--too-many-inputs--the-max-number-of-inputs-is-1---how-do-i-fix-this-:~:text=consisting%20of%20up%20to%2016%20inputs%20per%20API%20request

server/utils/EmbeddingEngines/localAi/index.js

@@ -16,10 +16,6 @@ class LocalAiEmbedder {
         : {}),
     });
     this.openai = new OpenAIApi(config);
-    // We don't know this for user's set model so for vectorDB integrations that requires dimensionality
-    // in schema, we will throw an error.
-    // Applies to QDrant and Milvus.
-    this.dimensions = null;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 50;

server/utils/EmbeddingEngines/native/index.js

@@ -13,7 +13,6 @@ class NativeEmbedder {
         : path.resolve(__dirname, `../../../storage/models`)
     );
     this.modelPath = path.resolve(this.cacheDir, "Xenova", "all-MiniLM-L6-v2");
-    this.dimensions = 384;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 25;

server/utils/EmbeddingEngines/openAi/index.js

@@ -9,7 +9,6 @@ class OpenAiEmbedder {
     });
     const openai = new OpenAIApi(config);
     this.openai = openai;
-    this.dimensions = 1536;
 
     // Limit of how many strings we can process in a single pass to stay with resource or network limits
     this.maxConcurrentChunks = 500;

server/utils/vectorDbProviders/milvus/index.js

@@ -81,13 +81,15 @@ const Milvus = {
     await client.dropCollection({ collection_name: namespace });
     return true;
   },
-  getOrCreateCollection: async function (client, namespace) {
+  // Milvus requires a dimension aspect for collection creation
+  // we pass this in from the first chunk to infer the dimensions like other
+  // providers do.
+  getOrCreateCollection: async function (client, namespace, dimensions = null) {
     const isExists = await this.namespaceExists(client, namespace);
     if (!isExists) {
-      const embedder = getEmbeddingEngineSelection();
-      if (!embedder.dimensions)
+      if (!dimensions)
         throw new Error(
-          `Your embedder selection has unknown dimensions output. It should be defined when using ${this.name}. Open an issue on Github for support.`
+          `Milvus:getOrCreateCollection Unable to infer vector dimension from input. Open an issue on Github for support.`
         );
 
       await client.createCollection({
@@ -104,7 +106,7 @@ const Milvus = {
             name: "vector",
             description: "vector",
             data_type: DataType.FloatVector,
-            dim: embedder.dimensions,
+            dim: dimensions,
           },
           {
             name: "metadata",
@@ -131,18 +133,19 @@ const Milvus = {
   ) {
     const { DocumentVectors } = require("../../../models/vectors");
     try {
+      let vectorDimension = null;
       const { pageContent, docId, ...metadata } = documentData;
       if (!pageContent || pageContent.length == 0) return false;
 
       console.log("Adding new vectorized document into namespace", namespace);
       const cacheResult = await cachedVectorInformation(fullFilePath);
       if (cacheResult.exists) {
         const { client } = await this.connect();
-        await this.getOrCreateCollection(client, namespace);
-
         const { chunks } = cacheResult;
         const documentVectors = [];
+        vectorDimension = chunks[0][0].values.length || null;
 
+        await this.getOrCreateCollection(client, namespace, vectorDimension);
         for (const chunk of chunks) {
           // Before sending to Pinecone and saving the records to our db
           // we need to assign the id of each chunk that is stored in the cached file.
@@ -182,6 +185,7 @@ const Milvus = {
 
       if (!!vectorValues && vectorValues.length > 0) {
         for (const [i, vector] of vectorValues.entries()) {
+          if (!vectorDimension) vectorDimension = vector.length;
           const vectorRecord = {
             id: uuidv4(),
             values: vector,
@@ -202,7 +206,7 @@ const Milvus = {
       if (vectors.length > 0) {
         const chunks = [];
         const { client } = await this.connect();
-        await this.getOrCreateCollection(client, namespace);
+        await this.getOrCreateCollection(client, namespace, vectorDimension);
 
         console.log("Inserting vectorized chunks into Milvus.");
         for (const chunk of toChunks(vectors, 100)) {

server/utils/vectorDbProviders/qdrant/index.js

@@ -108,19 +108,20 @@ const QDrant = {
     await client.deleteCollection(namespace);
     return true;
   },
-  getOrCreateCollection: async function (client, namespace) {
+  // QDrant requires a dimension aspect for collection creation
+  // we pass this in from the first chunk to infer the dimensions like other
+  // providers do.
+  getOrCreateCollection: async function (client, namespace, dimensions = null) {
     if (await this.namespaceExists(client, namespace)) {
       return await client.getCollection(namespace);
     }
-
-    const embedder = getEmbeddingEngineSelection();
-    if (!embedder.dimensions)
+    if (!dimensions)
       throw new Error(
-        `Your embedder selection has unknown dimensions output. It should be defined when using ${this.name}. Open an issue on Github for support.`
+        `Qdrant:getOrCreateCollection Unable to infer vector dimension from input. Open an issue on Github for support.`
       );
     await client.createCollection(namespace, {
       vectors: {
-        size: embedder.dimensions,
+        size: dimensions,
         distance: "Cosine",
       },
     });
@@ -133,22 +134,28 @@ const QDrant = {
   ) {
     const { DocumentVectors } = require("../../../models/vectors");
     try {
+      let vectorDimension = null;
       const { pageContent, docId, ...metadata } = documentData;
       if (!pageContent || pageContent.length == 0) return false;
 
       console.log("Adding new vectorized document into namespace", namespace);
       const cacheResult = await cachedVectorInformation(fullFilePath);
       if (cacheResult.exists) {
         const { client } = await this.connect();
-        const collection = await this.getOrCreateCollection(client, namespace);
+        const { chunks } = cacheResult;
+        const documentVectors = [];
+        vectorDimension = chunks[0][0].vector.length || null;
+
+        const collection = await this.getOrCreateCollection(
+          client,
+          namespace,
+          vectorDimension
+        );
         if (!collection)
           throw new Error("Failed to create new QDrant collection!", {
             namespace,
           });
 
-        const { chunks } = cacheResult;
-        const documentVectors = [];
-
         for (const chunk of chunks) {
           const submission = {
             ids: [],
@@ -210,6 +217,7 @@ const QDrant = {
 
       if (!!vectorValues && vectorValues.length > 0) {
         for (const [i, vector] of vectorValues.entries()) {
+          if (!vectorDimension) vectorDimension = vector.length;
           const vectorRecord = {
             id: uuidv4(),
             vector: vector,
@@ -233,7 +241,11 @@ const QDrant = {
       }
 
       const { client } = await this.connect();
-      const collection = await this.getOrCreateCollection(client, namespace);
+      const collection = await this.getOrCreateCollection(
+        client,
+        namespace,
+        vectorDimension
+      );
       if (!collection)
         throw new Error("Failed to create new QDrant collection!", {
           namespace,