> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memsync.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# File Integration

> Upload and process documents to extract memories

Upload documents to automatically extract and store memories from their content.

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST 'https://api.memchat.io/integrations/files' \
    -H 'X-API-Key: YOUR_API_KEY' \
    -F 'file=@document.pdf' \
    -F 'category=learning' \
    -F 'extract_mode=comprehensive'
  ```

  ```python Python theme={null}
  import requests

  url = "https://api.memchat.io/integrations/files"
  headers = {
      "X-API-Key": "YOUR_API_KEY"
  }

  files = {
      'file': open('document.pdf', 'rb')
  }

  data = {
      'category': 'learning',
      'extract_mode': 'comprehensive'
  }

  response = requests.post(url, headers=headers, files=files, data=data)
  result = response.json()
  ```

  ```javascript JavaScript theme={null}
  const formData = new FormData();
  formData.append('file', fileInput.files[0]);
  formData.append('category', 'learning');
  formData.append('extract_mode', 'comprehensive');

  const response = await fetch('https://api.memchat.io/integrations/files', {
    method: 'POST',
    headers: {
      'X-API-Key': 'YOUR_API_KEY',
    },
    body: formData,
  });

  const result = await response.json();
  ```
</RequestExample>

## Request Parameters

<ParamField body="file" type="file" required>
  Document file to process. Supported formats: PDF, DOCX, TXT, MD, HTML
</ParamField>

<ParamField body="category" type="string">
  Default category for extracted memories. One of: `identity`, `career`, `interests`, `relationships`, `health`, `finance`, `learning`, `travel`, `productivity`, `private`
</ParamField>

<ParamField body="extract_mode" type="string" default="smart">
  Extraction strategy. Options: `comprehensive`, `smart`, `highlights`, `summary`
</ParamField>

<ParamField body="chunk_size" type="number" default="1000">
  Maximum size of text chunks for processing (characters)
</ParamField>

<ParamField body="overlap" type="number" default="200">
  Overlap between chunks to maintain context
</ParamField>

<ParamField body="auto_categorize" type="boolean" default="true">
  Whether to automatically categorize extracted memories
</ParamField>

<ParamField body="metadata" type="object">
  Additional metadata for the document

  <Expandable title="Metadata Properties">
    <ParamField body="title" type="string">
      Document title
    </ParamField>

    <ParamField body="author" type="string">
      Document author
    </ParamField>

    <ParamField body="source" type="string">
      Source or origin of the document
    </ParamField>

    <ParamField body="tags" type="array">
      Custom tags for the document
    </ParamField>

    <ParamField body="date_created" type="string">
      When the document was created
    </ParamField>
  </Expandable>
</ParamField>

## Response

<ResponseField name="integration_id" type="string">
  Unique identifier for the file integration
</ResponseField>

<ResponseField name="filename" type="string">
  Name of the uploaded file
</ResponseField>

<ResponseField name="file_size" type="number">
  Size of the uploaded file in bytes
</ResponseField>

<ResponseField name="status" type="string">
  Processing status: `uploaded`, `processing`, `completed`, `error`
</ResponseField>

<ResponseField name="extraction_stats" type="object">
  Statistics about the extraction process

  <Expandable title="Extraction Statistics">
    <ResponseField name="total_pages" type="number">
      Number of pages in the document
    </ResponseField>

    <ResponseField name="text_length" type="number">
      Total characters extracted
    </ResponseField>

    <ResponseField name="chunks_created" type="number">
      Number of text chunks created
    </ResponseField>

    <ResponseField name="memories_extracted" type="number">
      Number of memories extracted
    </ResponseField>

    <ResponseField name="categories_detected" type="array">
      Categories detected in the content
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="memories" type="array">
  List of extracted memories (if processing is complete)

  <Expandable title="Memory Properties">
    <ResponseField name="memory_id" type="string">
      Unique identifier for the extracted memory
    </ResponseField>

    <ResponseField name="content" type="string">
      Extracted text content
    </ResponseField>

    <ResponseField name="category" type="string">
      Assigned category
    </ResponseField>

    <ResponseField name="importance" type="number">
      Calculated importance score
    </ResponseField>

    <ResponseField name="page_number" type="number">
      Source page number in document
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="created_at" type="string">
  ISO 8601 timestamp when upload was initiated
</ResponseField>

<ResponseField name="completed_at" type="string">
  ISO 8601 timestamp when processing completed
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "integration_id": "file_int_456def",
    "filename": "research_paper.pdf",
    "file_size": 2458697,
    "status": "completed",
    "extraction_stats": {
      "total_pages": 15,
      "text_length": 45678,
      "chunks_created": 23,
      "memories_extracted": 12,
      "categories_detected": ["learning", "career", "interests"]
    },
    "memories": [
      {
        "memory_id": "mem_789ghi",
        "content": "The study demonstrates that machine learning algorithms can improve medical diagnosis accuracy by 23% when trained on diverse datasets.",
        "category": "learning",
        "importance": 0.87,
        "page_number": 3
      }
    ],
    "created_at": "2024-01-15T16:30:00Z",
    "completed_at": "2024-01-15T16:32:15Z"
  }
  ```
</ResponseExample>

## Extraction Modes

<Accordion title="Comprehensive">
  Extracts memories from all significant text passages, creating detailed memories for each section.
</Accordion>

<Accordion title="Smart">
  Uses AI to identify the most important passages and concepts, creating focused memories.
</Accordion>

<Accordion title="Highlights">
  Extracts only key insights, findings, and actionable information.
</Accordion>

<Accordion title="Summary">
  Creates a single comprehensive memory summarizing the entire document.
</Accordion>

## Supported File Types

<Accordion title="PDF">
  * Text extraction from standard PDFs
  * OCR for scanned documents
  * Preserves page structure and formatting
</Accordion>

<Accordion title="Word Documents (DOCX)">
  * Full text extraction
  * Maintains document structure
  * Extracts embedded content
</Accordion>

<Accordion title="Text Files (TXT, MD)">
  * Direct text processing
  * Markdown formatting recognition
  * Fast processing
</Accordion>

<Accordion title="Web Pages (HTML)">
  * Content extraction from HTML
  * Removes navigation and ads
  * Focuses on main content
</Accordion>

## Error Responses

<ResponseField name="400" type="object">
  Invalid file or parameters

  ```json theme={null}
  {
    "error": "Unsupported file type",
    "code": "INVALID_FILE_TYPE",
    "supported_types": ["pdf", "docx", "txt", "md", "html"]
  }
  ```
</ResponseField>

<ResponseField name="413" type="object">
  File too large

  ```json theme={null}
  {
    "error": "File size exceeds limit",
    "code": "FILE_TOO_LARGE",
    "max_size_mb": 50,
    "file_size_mb": 75
  }
  ```
</ResponseField>