supermemory/apps/docs/ingestion/add-memories.mdx

---
title: "Ingesting context to supermemory"
sidebarTitle: "API"
description: "Add text, files, and URLs to Supermemory"
icon: "plus"
---

Send any raw content to Supermemory — conversations, documents, files, URLs. We extract the memories automatically. Pass `customId` to identify content and avoid duplicates, and `taskType: "superrag"` if you just need it searchable, not remembered — that's [5x cheaper](#memory-vs-superrag-ingestion) per token.

## Quick Start

<Tabs>
  <Tab title="TypeScript">
    ```typescript
    import Supermemory from 'supermemory';

    const client = new Supermemory();

    // Add text content
    await client.add({
      content: "Machine learning enables computers to learn from data",
      containerTag: "user_123",
      metadata: { category: "ai" }
    });

    // Add a URL (auto-extracted)
    await client.add({
      content: "https://youtube.com/watch?v=dQw4w9WgXcQ",
      containerTag: "user_123"
    });
    ```
  </Tab>
  <Tab title="Python">
    ```python
    from supermemory import Supermemory

    client = Supermemory()

    # Add text content
    client.add(
        content="Machine learning enables computers to learn from data",
        container_tag="user_123",
        metadata={"category": "ai"}
    )

    # Add a URL (auto-extracted)
    client.add(
        content="https://youtube.com/watch?v=dQw4w9WgXcQ",
        container_tag="user_123"
    )
    ```
  </Tab>
  <Tab title="cURL">
    ```bash
    curl -X POST "https://api.supermemory.ai/v3/documents" \
      -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "content": "Machine learning enables computers to learn from data",
        "containerTag": "user_123",
        "metadata": {"category": "ai"}
      }'
    ```
  </Tab>
</Tabs>

**Response:**
```json
{ "id": "abc123", "status": "queued" }
```

<Warning>
If an irrecoverable processing error occurs, the document is automatically deleted after 2 minutes.
</Warning>

---

## Updating Content

Use `customId` to update existing documents or conversations. When you send content with the same `customId`, Supermemory intelligently processes only what's new.

### Two ways to update:

**Option 1: Send only the new content**
```typescript
// First request
await client.add({
  content: "user: Hi, I'm Sarah.\nassistant: Nice to meet you!",
  customId: "conv_123",
  containerTag: "user_sarah"
});

// Later: send only new messages
await client.add({
  content: "user: What's the weather?\nassistant: It's sunny today.",
  customId: "conv_123",  // Same ID — Supermemory links them
  containerTag: "user_sarah"
});
```

**Option 2: Send the full updated content**
```typescript
// Supermemory detects the diff and only processes new parts
await client.add({
  content: "user: Hi, I'm Sarah.\nassistant: Nice to meet you!\nuser: What's the weather?\nassistant: It's sunny today.",
  customId: "conv_123",
  containerTag: "user_sarah"
});
```

Both work — choose what fits your architecture.

### Replace entire document

To completely replace a document's content (not append), use `memories.update()`:

```typescript
// Replace the entire document content
await client.documents.update("doc_id_123", {
  content: "Completely new content replacing everything",
  metadata: { version: 2 }
});
```

This triggers full reprocessing of the document. If you only update metadata (no content change), the document is updated in place with no reindexing.

### Formatting conversations

Format your conversations however you want. Supermemory handles any string format:

```typescript
// Simple string
content: "user: Hello\nassistant: Hi there!"

// JSON stringify
content: JSON.stringify(messages)

// Template literal
content: messages.map(m => `${m.role}: ${m.content}`).join('\n')

// Any format — just make it a string
content: formatConversation(messages)
```

---

## Upload Files

Upload PDFs, images, and documents directly.

<Tabs>
  <Tab title="TypeScript">
    ```typescript
    import fs from 'fs';

    await client.documents.uploadFile({
      file: fs.createReadStream('document.pdf'),
      containerTag: 'user_123'
    });
    ```
  </Tab>
  <Tab title="Python">
    ```python
    with open('document.pdf', 'rb') as file:
        client.documents.upload_file(
            file=file,
            container_tag='user_123'
        )
    ```
  </Tab>
  <Tab title="cURL">
    ```bash
    curl -X POST "https://api.supermemory.ai/v3/documents/file" \
      -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
      -F "file=@document.pdf" \
      -F "containerTag=user_123"
    ```
  </Tab>
</Tabs>

### Supported File Types

| Type | Formats | Processing |
|------|---------|------------|
| Documents | PDF, DOC, DOCX, TXT, MD | Text extraction, OCR for scans |
| Images | JPG, PNG, GIF, WebP | OCR text extraction |
| Spreadsheets | CSV, Google Sheets | Structured data extraction |
| Videos | YouTube URLs, MP4 | Auto-transcription |

**Limits:** 50MB max file size

---

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `content` | string | **Required.** Any raw content — text, conversations, URLs, HTML |
| `customId` | string | **Recommended.** Your ID for the content (conversation ID, doc ID). Enables updates and deduplication |
| `containerTag` | string | Group by user/project. Required for user profiles |
| `metadata` | object | Key-value pairs for filtering (strings, numbers, booleans) |
| `filterByMetadata` | object | Filter which existing memories are used as context during ingestion. See [Filtered Writes](#filtered-writes) |
| `entityContext` | string | Context for memory extraction on this container tag. Max 1500 chars. See [Customization](/concepts/customization#entity-context) |
| `dreaming` | `"dynamic" \| "instant"` | Processing mode. Default `"dynamic"`. `"instant"` processes each document on its own and bills one extra operation. See [Processing Modes](#processing-modes) |
| `taskType` | `"memory" \| "superrag"` | Pipeline to run. Default `"memory"`. `"superrag"` skips fact extraction and profile updates, doing only chunk/embed/index — at 5x cheaper per token. See [SuperRAG ingestion](/concepts/super-rag#ingesting-as-pure-superrag-tasktype-superrag) |

<AccordionGroup>
  <Accordion title="Parameter Details & Examples">
    **Content Types:**
    ```typescript
    // Any text — conversations, notes, documents
    { content: "Meeting notes from today's standup" }
    { content: JSON.stringify(messages) }

    // URLs (auto-detected and extracted)
    { content: "https://example.com/article" }
    { content: "https://youtube.com/watch?v=abc123" }

    // Markdown, HTML, or any format
    { content: "# Project Docs\n\n## Features\n- Real-time sync" }
    ```

    **Container Tags:**
    ```typescript
    // By user
    { containerTag: "user_123" }

    // By project
    { containerTag: "project_alpha" }

    // Hierarchical
    { containerTag: "org_456_team_backend" }
    ```

    **Custom IDs (Recommended):**
    ```typescript
    // Use IDs from your system
    { customId: "conv_abc123" }        // Conversation ID
    { customId: "doc_456" }            // Document ID
    { customId: "thread_789" }         // Thread ID
    { customId: "meeting_2024_01_15" } // Meeting ID

    // Updates: same customId = same document
    // Supermemory only processes new/changed content
    await client.add({
      content: "Updated content...",
      customId: "doc_456"  // Links to existing document
    });
    ```

    **Metadata:**
    ```typescript
    {
      metadata: {
        source: "slack",
        author: "john",
        priority: 1,
        reviewed: true
      }
    }
    ```
    - No nested objects or arrays
    - Values: string, number, or boolean only

    **Entity Context:**
    ```typescript
    // Guide memory extraction for this container tag
    {
      containerTag: "session_abc123",
      entityContext: `Design exploration conversation between john@acme.com and Brand.ai assistant.
        Focus on John's design preferences and brand requirements.`
    }
    ```
    - Max 1500 characters
    - Persists on the container tag
    - Combines with org-level filter prompts
  </Accordion>
</AccordionGroup>

---

## Processing Modes

### Dreaming: dynamic vs instant

The `dreaming` parameter controls how Supermemory turns a document into memories.

- `"dynamic"` (default) — groups related documents together so memories form from coherent, logical units rather than one isolated entry at a time.
- `"instant"` — processes each document on its own right away, and bills one extra operation per document.

```json
{
  "content": "...",
  "dreaming": "instant"
}
```

### Memory vs SuperRAG ingestion

The `taskType` parameter controls whether that content also feeds the memory pipeline.

- `"memory"` (default) — chunks/embeds for search **and** extracts facts, updates the user's profile, and links into the graph.
- `"superrag"` — chunks/embeds for search only. No fact extraction, no profile updates. Priced at **5x cheaper per token** than `"memory"`.

```json
{
  "content": "...",
  "taskType": "superrag"
}
```

Use `"superrag"` for reference material you want searchable but that shouldn't shape what Supermemory knows about a user. Full explanation: [SuperRAG → Ingesting as pure SuperRAG](/concepts/super-rag#ingesting-as-pure-superrag-tasktype-superrag).

---

## Filtered Writes

By default, when you add content, Supermemory uses **all** existing memories in the space as context for generating new memories. With **filtered writes**, you can scope this context to only memories from documents matching specific metadata.

This is useful when you have many documents in a space but want new memories to build on top of a specific subset — for example, only memories from a particular source, category, or user.

<Note>
The metadata itself is still written to the document, but the memories will only be built on top of what's already there matching the filter.
</Note>

<Tabs>
  <Tab title="TypeScript">
    ```typescript
    await client.add({
      content: "New research findings on transformer architectures...",
      containerTag: "user_123",
      metadata: { category: "ml", source: "arxiv" },
      filterByMetadata: { category: "ml" }
    });
    ```
  </Tab>
  <Tab title="Python">
    ```python
    client.add(
        content="New research findings on transformer architectures...",
        container_tag="user_123",
        metadata={"category": "ml", "source": "arxiv"},
        filter_by_metadata={"category": "ml"}
    )
    ```
  </Tab>
  <Tab title="cURL">
    ```bash
    curl -X POST "https://api.supermemory.ai/v3/documents" \
      -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "content": "New research findings on transformer architectures...",
        "containerTag": "user_123",
        "metadata": {"category": "ml", "source": "arxiv"},
        "filterByMetadata": {"category": "ml"}
      }'
    ```
  </Tab>
</Tabs>

### How it works

When `filterByMetadata` is provided:
- **Profile memories** (static context) are filtered to only those from documents matching the metadata
- **Similar memories** used as context during ingestion are filtered the same way
- The new document's own metadata is written normally — the filter only affects which **existing** memories are used as context

### `filterByMetadata` parameter

| Key | Type | Description |
|-----|------|-------------|
| `filterByMetadata` | `Record<string, string \| number \| boolean \| string[]>` | Key-value pairs to filter existing memories by their source document metadata |

- **Scalar values** (string, number, boolean) match exactly
- **Array values** match if **any** value in the array matches (OR logic)
- **Multiple keys** are combined with AND logic

```typescript
// Match documents where category is "ml" AND source is either "arxiv" or "pubmed"
await client.add({
  content: "...",
  containerTag: "user_123",
  filterByMetadata: {
    category: "ml",
    source: ["arxiv", "pubmed"]
  }
});
```

---

## Processing Pipeline

When you add content, Supermemory:

1. **Validates** your request
2. **Stores** the document and queues for processing
3. **Extracts** content (OCR, transcription, web scraping)
4. **Chunks** into searchable memories
5. **Embeds** for vector search
6. **Indexes** for retrieval

Track progress with `GET /v3/documents/{id}`:
```typescript
const doc = await client.documents.get("abc123");
console.log(doc.status); // "queued" | "processing" | "done"
```

<AccordionGroup>
  <Accordion title="Batch Upload">
    Process multiple documents with rate limiting:

    ```typescript
    async function batchUpload(documents: Array<{id: string, content: string}>) {
      const results = [];

      for (const doc of documents) {
        try {
          const result = await client.add({
            content: doc.content,
            customId: doc.id,
            containerTag: "batch_import"
          });
          results.push({ id: doc.id, success: true, docId: result.id });
        } catch (error) {
          results.push({ id: doc.id, success: false, error });
        }

        // Rate limit: 1 second between requests
        await new Promise(r => setTimeout(r, 1000));
      }

      return results;
    }
    ```

    **Tips:**
    - Batch size: 3-5 documents at once
    - Delay: 1-2 seconds between requests
    - Use `customId` to track and deduplicate
  </Accordion>

  <Accordion title="Error Handling">
    | Status | Error | Cause |
    |--------|-------|-------|
    | 400 | BadRequestError | Missing required fields, invalid parameters |
    | 401 | AuthenticationError | Invalid or missing API key |
    | 403 | PermissionDeniedError | Insufficient permissions |
    | 429 | RateLimitError | Too many requests or quota exceeded |
    | 500 | InternalServerError | Processing failure |

    ```typescript
    import { BadRequestError, RateLimitError } from 'supermemory';

    try {
      await client.add({ content: "..." });
    } catch (error) {
      if (error instanceof RateLimitError) {
        // Wait and retry
        await new Promise(r => setTimeout(r, 60000));
      } else if (error instanceof BadRequestError) {
        // Fix request parameters
        console.error("Invalid request:", error.message);
      }
    }
    ```
  </Accordion>

  <Accordion title="Delete Content">
    **Single delete:**
    ```typescript
    await client.documents.delete("doc_id_123");
    ```

    **Bulk delete by IDs:**
    ```typescript
    await client.documents.deleteBulk({
      ids: ["doc_1", "doc_2", "doc_3"]
    });
    ```

    **Bulk delete by container tag:**
    ```typescript
    // Delete all content for a user
    await client.documents.deleteBulk({
      containerTags: ["user_123"]
    });
    ```

    Deletes are permanent — no recovery.
  </Accordion>
</AccordionGroup>

---

## Next Steps

- [How to backfill historical data](/ingestion/batch-ingest-historical-data) — Import dated content with the batch API
- [Search Memories](/recall/search) — Query your content
- [User Profiles](/recall/user-profiles) — Get user context
- [Organizing & Filtering](/concepts/filtering) — Container tags and metadata