upsert examples multipart in JS

js/src/client.ts

@@ -35,6 +35,8 @@
   AnnotationQueue,
   RunWithAnnotationQueueInfo,
   Attachments,
+  ExampleUpsertWithAttachments,
+  UpsertExamplesResponse
 } from "./schemas.js";
 import {
   convertLangChainMessageToExample,
@@ -420,7 +422,7 @@
     // If there is an item on the queue we were unable to pop,
     // just return it as a single batch.
     if (popped.length === 0 && this.items.length > 0) {
       const item = this.items.shift()!;
       popped.push(item);
       poppedSizeBytes += item.size;
       this.sizeBytes -= item.size;
@@ -836,7 +838,7 @@
         if (this._serverInfo === undefined) {
           try {
             this._serverInfo = await this._getServerInfo();
           } catch (e) {
             console.warn(
               `[WARNING]: LangSmith failed to fetch info on supported operations. Falling back to batch operations and default limits.`
             );
@@ -1536,7 +1538,7 @@
     treeFilter?: string;
     isRoot?: boolean;
     dataSourceType?: string;
   }): Promise<any> {
     let projectIds_ = projectIds || [];
     if (projectNames) {
       projectIds_ = [
@@ -1824,7 +1826,7 @@
         `Failed to list shared examples: ${response.status} ${response.statusText}`
       );
     }
     return result.map((example: any) => ({
       ...example,
       _hostUrl: this.getHostUrl(),
     }));
@@ -1961,7 +1963,7 @@
       }
       // projectId querying
       return true;
     } catch (e) {
       return false;
     }
   }
@@ -3301,7 +3303,7 @@
   async _logEvaluationFeedback(
     evaluatorResponse: EvaluationResult | EvaluationResults,
     run?: Run,
     sourceInfo?: { [key: string]: any }
   ): Promise<[results: EvaluationResult[], feedbacks: Feedback[]]> {
     const evalResults: Array<EvaluationResult> =
       this._selectEvalResults(evaluatorResponse);
@@ -3340,7 +3342,7 @@
   public async logEvaluationFeedback(
     evaluatorResponse: EvaluationResult | EvaluationResults,
     run?: Run,
     sourceInfo?: { [key: string]: any }
   ): Promise<EvaluationResult[]> {
     const [results] = await this._logEvaluationFeedback(
       evaluatorResponse,
@@ -3790,7 +3792,7 @@
 
   public async createCommit(
     promptIdentifier: string,
     object: any,
     options?: {
       parentCommitHash?: string;
     }
@@ -3832,6 +3834,75 @@
     );
   }
 
+  /**
+   * Upsert examples with attachments using multipart form data.
+   * @param upserts List of ExampleUpsertWithAttachments objects to upsert
+   * @returns Promise with the upsert response
+   */
+  public async upsertExamplesMultipart({
+    upserts = [],
+  }: {
+    upserts?: ExampleUpsertWithAttachments[];
+  }): Promise<UpsertExamplesResponse> {
+    const formData = new FormData();
+
+  for (const example of upserts) {
+    const exampleId = (example.id ?? uuid.v4()).toString();
+
+    // Prepare the main example body
+    const exampleBody = {
+      dataset_id: example.dataset_id,
+      created_at: example.created_at,
+      ...(example.metadata && { metadata: example.metadata }),
+      ...(example.split && { split: example.split }),
+    };
+
+    // Add main example data
+    const stringifiedExample = stringifyForTracing(exampleBody);
+    const exampleBlob = new Blob([stringifiedExample], { 
+      type: "application/json"
+    });
+    formData.append(exampleId, exampleBlob);
+
+    // Add inputs
+    const stringifiedInputs = stringifyForTracing(example.inputs);
+    const inputsBlob = new Blob([stringifiedInputs], { 
+      type: "application/json"
+    });
+    formData.append(`${exampleId}.inputs`, inputsBlob);
+
+    // Add outputs if present
+    if (example.outputs) {
+      const stringifiedOutputs = stringifyForTracing(example.outputs);
+      const outputsBlob = new Blob([stringifiedOutputs], { 
+        type: "application/json"
+      });
+      formData.append(`${exampleId}.outputs`, outputsBlob);
+    }
+
+    // Add attachments if present
+    if (example.attachments) {
+      for (const [name, [mimeType, data]] of Object.entries(example.attachments)) {
+        const attachmentBlob = new Blob([data], { type: `${mimeType}; length=${data.byteLength}` });
+        formData.append(`${exampleId}.attachment.${name}`, attachmentBlob);
+      }
+    }
+  }
+
+  const response = await this.caller.call(
+    _getFetchImplementation(),
+    `${this.apiUrl}/v1/platform/examples/multipart`,
+    {
+      method: "POST",
+      headers: this.headers,
+      body: formData,
+    }
+  );
+  const result = await response.json();
+  return result;
+
+  }
+
   public async updatePrompt(
     promptIdentifier: string,
     options?: {
@@ -3841,7 +3912,7 @@
       isPublic?: boolean;
       isArchived?: boolean;
     }
   ): Promise<Record<string, any>> {
     if (!(await this.promptExists(promptIdentifier))) {
       throw new Error("Prompt does not exist, you must create it first.");
     }
@@ -3852,7 +3923,7 @@
       throw await this._ownerConflictError("update a prompt", owner);
     }
 
     const payload: Record<string, any> = {};
 
     if (options?.description !== undefined)
       payload.description = options.description;

js/src/schemas.ts

@@ -248,6 +248,15 @@ export interface ExampleCreate extends BaseExample {
   split?: string | string[];
 }
 
+export interface ExampleUpsertWithAttachments extends ExampleCreate {
+  attachments?: Attachments;
+}
+
+export interface UpsertExamplesResponse {
+  count: number;
+  example_ids: string[];
+}
+
 export interface Example extends BaseExample {
   id: string;
   created_at: string;

js/src/tests/client.test.ts

@@ -1,5 +1,6 @@
 /* eslint-disable @typescript-eslint/no-explicit-any */
 import { jest } from "@jest/globals";
+import { v4 as uuidv4 } from "uuid";
 import { Client } from "../client.js";
 import {
   getEnvironmentVariables,
@@ -10,6 +11,10 @@ import {
   isVersionGreaterOrEqual,
   parsePromptIdentifier,
 } from "../utils/prompts.js";
+import { ExampleUpsertWithAttachments } from "../schemas.js";
+import * as fs from "node:fs";
+import * as path from "node:path";
+import { fileURLToPath } from "node:url";
 
 describe("Client", () => {
   describe("createLLMExample", () => {
@@ -249,4 +254,121 @@ describe("Client", () => {
       });
     });
   });
+
+  describe("upsertExamplesMultipart", () => {
+    it("should upsert examples with attachments via multipart endpoint", async () => {
+      const datasetName = `__test_upsert_examples_multipart${uuidv4().slice(0, 4)}`;
+      // NEED TO FIX THIS AFTER ENDPOINT MAKES IT TO PROD
+      const client = new Client({ 
+        apiUrl: "https://dev.api.smith.langchain.com", 
+        apiKey: "HARDCODE FOR TESTING" 
+      });
+
+      // Clean up existing dataset if it exists
+      if (await client.hasDataset({ datasetName })) {
+        await client.deleteDataset({ datasetName });
+      }
+
+      // Create actual dataset
+      const dataset = await client.createDataset(
+        datasetName, {
+          description: "Test dataset for multipart example upload",
+          dataType: "kv"
+        }
+      );
+
+      const pathname = path.join(
+        path.dirname(fileURLToPath(import.meta.url)),
+        "test_data",
+        "parrot-icon.png"
+      );
+      // Create test examples
+      const exampleId = uuidv4();
+      const example1: ExampleUpsertWithAttachments = {
+        id: exampleId,
+        dataset_id: dataset.id,
+        inputs: { text: "hello world" },
+        // check that passing no outputs works fine
+        attachments: {
+          test_file: ["image/png", fs.readFileSync(pathname)],
+        },
+      };
+
+      const example2: ExampleUpsertWithAttachments = {
+        dataset_id: dataset.id,
+        inputs: { text: "foo bar" },
+        outputs: { response: "baz" },
+        attachments: {
+          my_file: ["image/png", fs.readFileSync(pathname)],
+        },
+      };
+
+      // Test creating examples
+      const createdExamples = await client.upsertExamplesMultipart({
+        upserts: [
+        example1,
+        example2,
+      ]});
+
+      expect(createdExamples.count).toBe(2);
+
+      const createdExample1 = await client.readExample(
+        createdExamples.example_ids[0]
+      );
+      expect(createdExample1.inputs["text"]).toBe("hello world");
+
+      const createdExample2 = await client.readExample(
+        createdExamples.example_ids[1]
+      );
+      expect(createdExample2.inputs["text"]).toBe("foo bar");
+      expect(createdExample2.outputs?.["response"]).toBe("baz");
+
+      // Test examples were sent to correct dataset
+      const allExamplesInDataset = [];
+      for await (const example of client.listExamples({
+        datasetId: dataset.id,
+      })) {
+        allExamplesInDataset.push(example);
+      }
+      expect(allExamplesInDataset.length).toBe(2);
+
+      // Test updating example
+      const example1Update: ExampleUpsertWithAttachments = {
+        id: exampleId,
+        dataset_id: dataset.id,
+        inputs: { text: "bar baz" },
+        outputs: { response: "foo" },
+        attachments: {
+          my_file: ["image/png", fs.readFileSync(pathname)],
+        },
+      };
+
+      const updatedExamples = await client.upsertExamplesMultipart({
+        upserts: [
+        example1Update,
+      ]});
+      expect(updatedExamples.count).toBe(1);
+      expect(updatedExamples.example_ids[0]).toBe(exampleId);
+
+      const updatedExample = await client.readExample(updatedExamples.example_ids[0]);
+      expect(updatedExample.inputs["text"]).toBe("bar baz");
+      expect(updatedExample.outputs?.["response"]).toBe("foo");
+
+      // Test invalid example fails
+      const example3: ExampleUpsertWithAttachments = {
+        dataset_id: uuidv4(), // not a real dataset
+        inputs: { text: "foo bar" },
+        outputs: { response: "baz" },
+        attachments: {
+          my_file: ["image/png", fs.readFileSync(pathname)],
+        },
+      };
+
+      const errorResponse = await client.upsertExamplesMultipart({ upserts: [example3] });
+      expect(errorResponse).toHaveProperty("error");
+
+      // Clean up
+      await client.deleteDataset({ datasetName });
+    });
+  });
 });