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

# Introduction

> Visual Search — upload videos and images, index them automatically, and search them at scale.

Visual Search is a Video Management System (VMS) built for AI applications. You upload content, it indexes automatically, and you search it — using natural language, a query image, or an exact transcript phrase.

## How It Works

<Steps>
  <Step title="Upload">
    Send videos or images to the API. Each is indexed automatically and stored in the appropriate library.
  </Step>

  <Step title="Auto-Index">
    Every upload is processed through two pipelines in parallel:

    * **Embedding** — visual frames and audio are encoded into semantic vectors, enabling natural-language and image search
    * **Caption & transcription** — the platform generates descriptions and transcribes spoken audio, enabling text-level search

    Status transitions from `UNPARSE` (processing) to `PARSE` (searchable).
  </Step>

  <Step title="Search">
    Query your indexed content by natural language, image, or transcript keyword. Results are ranked by relevance.
  </Step>
</Steps>

## Three Libraries

Visual Search has three distinct libraries. **Understanding which library holds what content is essential** — uploads go to different libraries, and each library has its own search endpoints.

| Library                   | What it holds                              | How to populate                                                                                                         | Who can search    |
| ------------------------- | ------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------- | ----------------- |
| **Private Video Library** | Videos you upload                          | [Upload Video](/visual-search/upload-video-from-file), [Upload from Social Media](/visual-search/upload-from-post-urls) | Your account only |
| **Private Image Library** | Images you upload                          | [Upload Image](/visual-search/upload-image-from-file)                                                                   | Your account only |
| **Public Video Library**  | Public TikTok / YouTube / Instagram videos | Pre-indexed by Memories.ai — no upload needed                                                                           | All API users     |

**Private Video Library and Private Image Library are separate.** Uploading a video does not add it to your image library, and uploading an image does not add it to your video library. They have different upload endpoints, different search endpoints, and return different result formats.

## Search Modalities

Once indexed, content is searchable in two fundamental ways:

| Modality       | How it works                                                                                            | Best for                                              |
| -------------- | ------------------------------------------------------------------------------------------------------- | ----------------------------------------------------- |
| **Semantic**   | Embedding vectors — finds content that *means* the same as your query, even if exact words don't appear | Natural language queries or query images              |
| **Transcript** | Exact LIKE matching against stored audio transcripts                                                    | Known phrases or spoken keywords (video library only) |

## Next Steps

<CardGroup cols={2}>
  <Card title="Get Your API Key" icon="key" href="/visual-search/create-your-key">
    Generate a key to authenticate all API requests.
  </Card>

  <Card title="Upload Content" icon="upload" href="/visual-search/upload-overview">
    Upload videos and images — how the indexing pipeline works and which library each upload lands in.
  </Card>

  <Card title="Search" icon="magnifying-glass" href="/visual-search/search-overview">
    Explore all search endpoints across all three libraries.
  </Card>
</CardGroup>