diff --git a/docs/rag.md b/docs/rag.md
index fb60fd7ee2..e8fc8c7b86 100644
--- a/docs/rag.md
+++ b/docs/rag.md
@@ -303,10 +303,39 @@ export const ragFlow = defineFlow(
 
 It's also possible to create your own retriever. This is useful if your
 documents are managed in a document store that is not supported in Genkit (eg:
-MySQL, Google Drive, etc.). The Genkit SDK provides a flexible `defineRetriever`
-method that lets you provide custom code for fetching documents. You can also
-define custom retrievers that build on top of existing retrievers in Genkit and
-apply advanced RAG techniques (such as reranking or prompt extensions) on top.
+MySQL, Google Drive, etc.). The Genkit SDK provides flexible methods that let
+you provide custom code for fetching documents. You can also define custom
+retrievers that build on top of existing retrievers in Genkit and apply advanced
+RAG techniques (such as reranking or prompt extensions) on top.
+
+### Simple Retrievers
+
+Simple retrievers let you easily convert existing code into retrievers:
+
+```javascript
+import {
+  defineSimpleRetriever,
+  retrieve
+} from '@genkit-ai/ai/retriever';
+import { searchEmails } from './db';
+import { z } from 'zod';
+
+defineSimpleRetriever({
+  name: 'myDatabase',
+  configSchema: z.object({
+    limit: z.number().optional()
+  }).optional(),
+  // we'll extract "message" from the returned email item
+  content: 'message',
+  // and several keys to use as metadata
+  metadata: ['from', 'to', 'subject'],
+} async (query, config) => {
+  const result = await searchEmails(query.text(), {limit: config.limit});
+  return result.data.emails;
+});
+```
+
+### Custom Retrievers
 
 ```javascript
 import {
diff --git a/js/ai/src/retriever.ts b/js/ai/src/retriever.ts
index 1ea4d9a4e8..e3c6a89240 100644
--- a/js/ai/src/retriever.ts
+++ b/js/ai/src/retriever.ts
@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-import { Action, defineAction } from '@genkit-ai/core';
+import { Action, GenkitError, defineAction } from '@genkit-ai/core';
 import { lookupAction } from '@genkit-ai/core/registry';
 import * as z from 'zod';
 import { Document, DocumentData, DocumentDataSchema } from './document.js';
@@ -294,3 +294,106 @@ export function indexerRef<
 ): IndexerReference<CustomOptionsSchema> {
   return { ...options };
 }
+
+function itemToDocument<R>(
+  item: any,
+  options: SimpleRetrieverOptions
+): Document {
+  if (!item)
+    throw new GenkitError({
+      status: 'INVALID_ARGUMENT',
+      message: `Items returned from simple retriever must be non-null.`,
+    });
+  if (typeof item === 'string') return Document.fromText(item);
+  if (typeof options.content === 'function') {
+    const transformed = options.content(item);
+    return typeof transformed === 'string'
+      ? Document.fromText(transformed)
+      : new Document({ content: transformed });
+  }
+  if (typeof options.content === 'string' && typeof item === 'object')
+    return Document.fromText(item[options.content]);
+  throw new GenkitError({
+    status: 'INVALID_ARGUMENT',
+    message: `Cannot convert item to document without content option. Item: ${JSON.stringify(item)}`,
+  });
+}
+
+function itemToMetadata(
+  item: any,
+  options: SimpleRetrieverOptions
+): Document['metadata'] {
+  if (typeof item === 'string') return undefined;
+  if (Array.isArray(options.metadata) && typeof item === 'object') {
+    const out: Record<string, any> = {};
+    options.metadata.forEach((key) => (out[key] = item[key]));
+  }
+  if (typeof options.metadata === 'function') return options.metadata(item);
+  if (!options.metadata && typeof item === 'object') {
+    const out = { ...item };
+    if (typeof options.content === 'string') delete out[options.content];
+    return out;
+  }
+  throw new GenkitError({
+    status: 'INVALID_ARGUMENT',
+    message: `Unable to extract metadata from item with supplied options. Item: ${JSON.stringify(item)}`,
+  });
+}
+
+export interface SimpleRetrieverOptions<
+  C extends z.ZodTypeAny = z.ZodTypeAny,
+  R = any,
+> {
+  /** The name of the retriever you're creating. */
+  name: string;
+  /** A Zod schema containing any configuration info available beyond the query. */
+  configSchema?: C;
+  /**
+   * Specifies how to extract content from the returned items.
+   *
+   * - If a string, specifies the key of the returned item to extract as content.
+   * - If a function, allows you to extract content as text or a document part.
+   **/
+  content?: string | ((item: R) => Document['content'] | string);
+  /**
+   * Specifies how to extract metadata from the returned items.
+   *
+   * - If an array of strings, specifies list of keys to extract from returned objects.
+   * - If a function, allows you to use custom behavior to extract metadata from returned items.
+   */
+  metadata?: string[] | ((item: R) => Document['metadata']);
+}
+
+/**
+ * defineSimpleRetriever makes it easy to map existing data into documents that
+ * can be used for prompt augmentation.
+ *
+ * @param options Configuration options for the retriever.
+ * @param handler A function that queries a datastore and returns items from which to extract documents.
+ * @returns A Genkit retriever.
+ */
+export function defineSimpleRetriever<
+  C extends z.ZodTypeAny = z.ZodTypeAny,
+  R = any,
+>(
+  options: SimpleRetrieverOptions<C, R>,
+  handler: (query: Document, config: z.infer<C>) => Promise<R[]>
+) {
+  return defineRetriever(
+    {
+      name: options.name,
+      configSchema: options.configSchema,
+    },
+    async (query, config) => {
+      const result = await handler(query, config);
+      return {
+        documents: result.map((item) => {
+          const doc = itemToDocument(item, options);
+          if (typeof item !== 'string')
+            doc.metadata = itemToMetadata(item, options);
+          return doc;
+        }),
+      };
+    }
+  );
+}