Add comprehensive AWS Bedrock embedders guide

[tbuatois]

Pull Request

Related issue

No issue. This PR adds missing documentation for AWS Bedrock embedding models integration with Meilisearch.

What does this PR do?

This PR adds a comprehensive guide for using AWS Bedrock embedding models with Meilisearch, including:

• New Bedrock embedders guide (guides/embedders/bedrock.mdx) covering:
  • Amazon Titan Text Embeddings (V1 and V2)
  • Amazon Nova 2 Multimodal Embeddings with proper API schema
  • Cohere Embed models (English and Multilingual)
• Proper API key setup instructions with emphasis on regional requirements

The guide provides developers with complete, working examples to integrate Meilisearch with AWS Bedrock's embedding models for semantic search capabilities.

PR checklist

Please check if your PR fulfills the following requirements:

• Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)?
• Have you read the contributing guidelines?
• Have you made sure that the title is accurate and descriptive of the changes?

[curquiza]

@tbuatois I think "```" is missing, and because it's the delimiter of GitHub suggestion, I cannot add it myself

[Kerollmops]

And what's the difference between what I have, which is working perfectly with our Flickr demo? I would rather use mine as I know it works.

"bedrock": {
  "source": "rest",
  "apiKey": "ABSKQXXXXXX...",
  "dimensions": 1024,
  "binaryQuantized": true,
  "url": "https://bedrock-runtime.eu-west-3.amazonaws.com/model/amazon.titan-embed-image-v1/invoke",
  "indexingFragments": {
    "image": {
      "value": {
        "inputImage": "{{doc.base64}}",
        "embeddingConfig": {
          "outputEmbeddingLength": 1024
        }
      }
    }
  },
  "searchFragments": {
    "text": {
      "value": {
        "inputText": "{{q}}",
        "embeddingConfig": {
          "outputEmbeddingLength": 1024
        }
      }
    }
  },
  "request": "{{fragment}}",
  "response": {
    "embedding": "{{embedding}}"
  },
  "headers": {}
}

[curquiza]

@Kerollmops I need your technical review on it! Muchas gracias!

[Kerollmops]

I prefer @qdequele to review the process for creating an API Key, but otherwise I think it's good. We still need to update the different settings config to the one I linked, though.

[Kerollmops]

And what's the difference between what I have, which is working perfectly with our Flickr demo? I would rather use mine as I know it works.

"bedrock": {
  "source": "rest",
  "apiKey": "ABSKQXXXXXX...",
  "dimensions": 1024,
  "binaryQuantized": true,
  "url": "https://bedrock-runtime.eu-west-3.amazonaws.com/model/amazon.titan-embed-image-v1/invoke",
  "indexingFragments": {
    "image": {
      "value": {
        "inputImage": "{{doc.base64}}",
        "embeddingConfig": {
          "outputEmbeddingLength": 1024
        }
      }
    }
  },
  "searchFragments": {
    "text": {
      "value": {
        "inputText": "{{q}}",
        "embeddingConfig": {
          "outputEmbeddingLength": 1024
        }
      }
    }
  },
  "request": "{{fragment}}",
  "response": {
    "embedding": "{{embedding}}"
  },
  "headers": {}
}