mem0ai/mem0 · error · Error

Provided Langchain 'instance' in the 'model' field does not

Error message

Provided Langchain 'instance' in the 'model' field does not appear to be a valid Langchain Embeddings instance (missing embedQuery or embedDocuments method).

What it means

Thrown by the LangchainEmbedder constructor when config.model IS an object but lacks functioning embedQuery or embedDocuments methods — the duck-type check for a real LangChain Embeddings instance. This catches near-misses: a plain options object, a partially built instance, a mock, or an object from an incompatible @langchain/core major version whose method surface changed.

Source

Thrown at mem0-ts/src/oss/src/embeddings/langchain.ts:21

import { EmbeddingConfig } from "../types";

export class LangchainEmbedder implements Embedder {
  private embedderInstance: Embeddings;
  private batchSize?: number; // Some LC embedders have batch size

  constructor(config: EmbeddingConfig) {
    // Check if config.model is provided and is an object (the instance)
    if (!config.model || typeof config.model !== "object") {
      throw new Error(
        "Langchain embedder provider requires an initialized Langchain Embeddings instance passed via the 'model' field in the embedder config.",
      );
    }
    // Basic check for embedding methods
    if (
      typeof (config.model as any).embedQuery !== "function" ||
      typeof (config.model as any).embedDocuments !== "function"
    ) {
      throw new Error(
        "Provided Langchain 'instance' in the 'model' field does not appear to be a valid Langchain Embeddings instance (missing embedQuery or embedDocuments method).",
      );
    }
    this.embedderInstance = config.model as Embeddings;
    // Store batch size if the instance has it (optional)
    this.batchSize = (this.embedderInstance as any).batchSize;
  }

  async embed(text: string): Promise<number[]> {
    try {
      // Use embedQuery for single text embedding
      return await this.embedderInstance.embedQuery(text);
    } catch (error) {
      console.error("Error embedding text with Langchain Embedder:", error);
      throw error;
    }
  }

View on GitHub (pinned to 001c235229)

Solutions

1. Extend @langchain/core/embeddings Embeddings (or use a built-in like OpenAIEmbeddings) so both methods exist as real functions
2. If wrapping, forward both methods: embedQuery = (t) => this.inner.embedQuery(t); embedDocuments = (d) => this.inner.embedDocuments(d);
3. Construct the instance in the same process that builds Memory — never serialize it through IPC/JSON

Example fix

// before
class MyEmbedder { async embed(text: string) { /* ... */ } }
embedder: { provider: 'langchain', config: { model: new MyEmbedder() } }

// after
import { Embeddings } from '@langchain/core/embeddings';
class MyEmbedder extends Embeddings {
  async embedQuery(text: string) { /* ... */ return [0.1]; }
  async embedDocuments(docs: string[]) { /* ... */ return docs.map(() => [0.1]); }
}
embedder: { provider: 'langchain', config: { model: new MyEmbedder() } }

if (typeof (instance as any).embedQuery !== 'function' || typeof (instance as any).embedDocuments !== 'function') {
  throw new Error('Object is not a LangChain Embeddings instance: implement both embedQuery and embedDocuments');
}

const isLangchainEmbeddings = (m: unknown): m is Embeddings =>
  !!m && typeof m === 'object' &&
  typeof (m as Embeddings).embedQuery === 'function' &&
  typeof (m as Embeddings).embedDocuments === 'function';

if (!isLangchainEmbeddings(config.model)) throw new Error('invalid embedder instance');

When it happens

Trigger: Passing { model: { model: 'text-embedding-3-small' } } (config nested one level too deep); passing a custom wrapper that implements embed() but not embedQuery/embedDocuments; passing an object whose methods were stripped by structuredClone/serialization across worker boundaries.

Common situations: Wrapping an embedder in a custom class that does not extend LangChain's Embeddings base; version drift between @langchain/core in the host app and in dependencies; sending config through IPC/JSON so functions are lost.

Related errors

• Langchain embedder provider requires an initialized Langchai
• Unknown embedder provider: ${providerId}
• apiKey is required for Mem0Memory
• sessionId is required for Mem0Memory
• Invalid memory action: ${memoryAction}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/9c0670c2d5484f9a. Report an issue: GitHub.