> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt > Use this file to discover all available pages before exploring further. # Gemini Format - Embeddings > - Compatible with all Gemini native format embedding APIs - Converts text into high-dimensional vector representations - Supports multiple task types: retrieval, classification, clustering, semantic similarity, etc. - Supports custom output dimensionality (dimensionality reduction) ## OpenAPI ````yaml openapi/en/gemini-format-embeddings.json POST /v1beta/models/{model}:embedContent openapi: 3.1.0 info: title: Gemini Format - Embeddings version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1beta/models/{model}:embedContent: post: tags: - Text Series > Gemini Format summary: Gemini Format - Embeddings description: > - Compatible with all Gemini native format embedding APIs - Converts text into high-dimensional vector representations - Supports multiple task types: retrieval, classification, clustering, semantic similarity, etc. - Supports custom output dimensionality (dimensionality reduction) operationId: gemini-format-embed-content parameters: - name: model in: path required: true schema: type: string example: gemini-embedding-2-preview description: Embedding model name, e.g. gemini-embedding-2-preview requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/EmbedContentRequest' examples: simple: summary: Single text embedding description: The most basic single text embedding request value: content: parts: - text: What is deep learning? with-task-type: summary: Specify task type and output dimensions description: >- Use taskType and outputDimensionality to control embedding behavior value: content: parts: - text: How do Transformer models handle long sequences? taskType: RETRIEVAL_QUERY outputDimensionality: 768 retrieval-document: summary: Document retrieval embedding description: Document embedding for retrieval, with title parameter value: content: parts: - text: >- Deep learning is a subfield of machine learning that learns complex patterns and representations from data through multi-layer neural networks. It has achieved breakthroughs in areas such as image recognition, natural language processing, and speech recognition. taskType: RETRIEVAL_DOCUMENT title: Overview of Deep Learning responses: '200': $ref: '#/components/responses/EmbedContentSuccess' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: EmbedContentRequest: type: object required: - content properties: content: type: object description: The content to embed required: - parts properties: parts: type: array description: >- List of content parts. `gemini-embedding-2-preview` supports multimodal input (image/audio/video/PDF); older models support text only items: type: object properties: text: type: string description: Text content to embed inlineData: type: object description: >- Inline binary data (base64 encoded). Only supported by `gemini-embedding-2-preview`. Supports images (up to 6), audio (up to 80s), video (up to 120s), PDF (up to 6 pages). required: - mimeType - data properties: mimeType: type: string description: IANA standard MIME type examples: - image/png - image/jpeg - audio/mp3 - audio/wav - video/mp4 - video/quicktime - application/pdf data: type: string description: Base64 encoded binary data taskType: type: string description: >- Embedding task type, which affects the optimization direction of the embedding vector. **Note**: `gemini-embedding-2-preview` does not support this field; that model uses a prompt prefix approach to specify task types (e.g. `task: search result | query: {content}`) enum: - RETRIEVAL_QUERY - RETRIEVAL_DOCUMENT - SEMANTIC_SIMILARITY - CLASSIFICATION - CLUSTERING - QUESTION_ANSWERING - FACT_VERIFICATION - CODE_RETRIEVAL_QUERY title: type: string description: Document title, only effective when taskType is RETRIEVAL_DOCUMENT outputDimensionality: type: integer description: >- Output vector dimensionality, used for dimensionality reduction. Default 3072 EmbedContentResponse: type: object properties: embedding: type: object description: Embedding result properties: values: type: array description: Embedding vector values items: type: number example: - 0.0123 - -0.0456 - 0.0789 - 0.0234 - -0.0567 ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: Invalid API Key type: type: string example: authentication_error ErrorResponse403: type: object properties: error: type: object properties: message: type: string example: Access denied type: type: string example: permission_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: Rate limit exceeded type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: Internal server error type: type: string example: server_error responses: EmbedContentSuccess: description: Embedding response content: application/json: schema: $ref: '#/components/schemas/EmbedContentResponse' BadRequest: description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse403' TooManyRequests: description: Too many requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## All endpoints require Bearer Token authentication ## Add the following to your request headers: `Authorization: Bearer YOUR_API_KEY` ````