PGVectorStore is returning not_implemented with asRetriever function

[talhaFayyazfolio]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

async onModuleInit() {
    const embeddings = new VertexAIEmbeddings({
      model: 'text-embedding-004',
    });

    const config = {
      postgresConnectionOptions: {
        connectionString: process.env.CONNECTION_STRING,
        ssl: {
          rejectUnauthorized: false, // In production, use proper certs
        },
      },
      tableName: 'vault_table_row_embedding',
      columns: {
        idColumnName: 'id', // matches @PrimaryGeneratedColumn
        vectorColumnName: 'embedding', // matches the @Column for embedding
        contentColumnName: 'combinedText', // NOTE: rowData is JSON, better to use `combinedText` as searchable text
        metadataColumnName: 'rowdata', // raw JSON data stored as metadata
      },
      distanceStrategy: 'cosine' as DistanceStrategy,
    };

    this.vectorStore = await PGVectorStore.initialize(embeddings, config);
  }


  async getVectorStoreByVaultTypes(
    type: PRE_DEFINED_TABLES,
    organizationId: string,
  ): Promise<any> {
    return await this.vectorStore.asRetriever({
      verbose: true,
      k: 25,
      searchType: 'similarity',
      filter: {
        vaultTableType: 'Products ',
        organizationId,
      },
    });
  }

Description

Thisis returning not_implemented

System Info

"@langchain/community": "0.3.39",
"langchain": "0.3.20"
These are langchain versions