community[patch]: VoyageAI embedding with input_type parameter (#5493)

* added input_type

* input_type set to "none" by default , then choose between document or query

* Updated input_type for Voyage embeddings

* Update voyage.ts

* Update voyageai.mdx

* Update voyageai.mdx

* Update voyage.ts

* Update voyageai.mdx

¯\_(ツ)_/¯

* Update voyage.int.test.ts

With document to make sure it works

* Format

* Update voyageai.mdx

is it the space ? (sorry...)

* Format

* Fix types

---------

Co-authored-by: jacoblee93 <jacoblee93@gmail.com>

docs/core_docs/docs/integrations/text_embedding/voyageai.mdx

@@ -2,10 +2,17 @@
 
 The `VoyageEmbeddings` class uses the Voyage AI REST API to generate embeddings for a given text.
 
+The `inputType` parameter allows you to specify the type of input text for better embedding results. You can set it to `query`, `document`, or leave it undefined (which is equivalent to `None`).
+
+- `query`: Use this for search or retrieval queries. Voyage AI will prepend a prompt to optimize the embeddings for query use cases.
+- `document`: Use this for documents or content that you want to be retrievable. Voyage AI will prepend a prompt to optimize the embeddings for document use cases.
+- `None` (default): The input text will be directly encoded without any additional prompt.
+
 ```typescript
-import { VoyageEmbeddings } from "langchain/embeddings/voyage";
+import { VoyageEmbeddings } from "@langchain/community/embeddings/voyage";
 
 const embeddings = new VoyageEmbeddings({
   apiKey: "YOUR-API-KEY", // In Node.js defaults to process.env.VOYAGEAI_API_KEY
+  inputType: "document", // Optional: specify input type as 'query', 'document', or omit for None / Undefined / Null
 });
 ```

libs/langchain-community/src/embeddings/tests/voyage.int.test.ts

@@ -1,25 +1,26 @@
 import { test, expect } from "@jest/globals";
 import { VoyageEmbeddings } from "../voyage.js";
 
-test.skip("Test VoyageEmbeddings.embedQuery", async () => {
-  const embeddings = new VoyageEmbeddings();
+test.skip("Test VoyageEmbeddings.embedQuery with input_type", async () => {
+  const embeddings = new VoyageEmbeddings({ inputType: "document" });
   const res = await embeddings.embedQuery("Hello world");
 
   expect(typeof res[0]).toBe("number");
 });
 
-test.skip("Test VoyageEmbeddings.embedDocuments", async () => {
-  const embeddings = new VoyageEmbeddings();
+test.skip("Test VoyageEmbeddings.embedDocuments with input_type", async () => {
+  const embeddings = new VoyageEmbeddings({ inputType: "document" });
   const res = await embeddings.embedDocuments(["Hello world", "Bye bye"]);
   expect(res).toHaveLength(2);
   expect(typeof res[0][0]).toBe("number");
   expect(typeof res[1][0]).toBe("number");
 });
 
-test.skip("Test VoyageEmbeddings concurrency", async () => {
+test.skip("Test VoyageEmbeddings concurrency with input_type", async () => {
   const embeddings = new VoyageEmbeddings({
     batchSize: 1,
     maxConcurrency: 2,
+    inputType: "document",
   });
   const res = await embeddings.embedDocuments([
     "Hello world",
@@ -34,3 +35,11 @@ test.skip("Test VoyageEmbeddings concurrency", async () => {
     undefined
   );
 });
+
+test.skip("Test VoyageEmbeddings without input_type", async () => {
+  const embeddings = new VoyageEmbeddings();
+  const res = await embeddings.embedDocuments(["Hello world", "Bye bye"]);
+  expect(res).toHaveLength(2);
+  expect(typeof res[0][0]).toBe("number");
+  expect(typeof res[1][0]).toBe("number");
+});

libs/langchain-community/src/embeddings/voyage.ts

@@ -14,6 +14,11 @@ export interface VoyageEmbeddingsParams extends EmbeddingsParams {
    * limited by the Voyage AI API to a maximum of 8.
    */
   batchSize?: number;
+
+  /**
+   * Input type for the embeddings request.
+   */
+  inputType?: string;
 }
 
 /**
@@ -32,6 +37,11 @@ export interface CreateVoyageEmbeddingRequest {
    * @memberof CreateVoyageEmbeddingRequest
    */
   input: string | string[];
+
+  /**
+   * Input type for the embeddings request.
+   */
+  input_type?: string;
 }
 
 /**
@@ -53,6 +63,8 @@ export class VoyageEmbeddings
 
   headers?: Record<string, string>;
 
+  inputType?: string;
+
   /**
    * Constructor for the VoyageEmbeddings class.
    * @param fields - An optional object with properties to configure the instance.
@@ -61,6 +73,7 @@ export class VoyageEmbeddings
     fields?: Partial<VoyageEmbeddingsParams> & {
       verbose?: boolean;
       apiKey?: string;
+      inputType?: string; // Make inputType optional
     }
   ) {
     const fieldsWithDefaults = { ...fields };
@@ -78,6 +91,7 @@ export class VoyageEmbeddings
     this.batchSize = fieldsWithDefaults?.batchSize ?? this.batchSize;
     this.apiKey = apiKey;
     this.apiUrl = `${this.basePath}/embeddings`;
+    this.inputType = fieldsWithDefaults?.inputType;
   }
 
   /**
@@ -92,6 +106,7 @@ export class VoyageEmbeddings
       this.embeddingWithRetry({
         model: this.modelName,
         input: batch,
+        input_type: this.inputType,
       })
     );
 
@@ -119,6 +134,7 @@ export class VoyageEmbeddings
     const { data } = await this.embeddingWithRetry({
       model: this.modelName,
       input: text,
+      input_type: this.inputType,
     });
 
     return data[0].embedding;