Docs: change the google embedding model name (#11179)

Co-authored-by: anakin87 <stefanofiorucci@gmail.com>

Author: bilgeyucel

docs-website/docs/pipeline-components/embedders/googlegenaidocumentembedder.mdx

@@ -17,7 +17,7 @@ The vectors computed by this component are necessary to perform embedding retrie
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `documents`: A list of documents to be embedded |
 | **Output variables** | `documents`: A list of documents (enriched with embeddings)  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
 | **Package name** | `google-genai-haystack` |
 
@@ -27,10 +27,9 @@ The vectors computed by this component are necessary to perform embedding retrie
 
 `GoogleGenAIDocumentEmbedder` enriches the metadata of documents with an embedding of their content. To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
 
-The component supports the following Google AI models:
+The component supports [Google AI Embedding models](https://ai.google.dev/gemini-api/docs/embeddings#model-versions).
 
-- `text-embedding-004` (default)
-- `text-embedding-004-v2`
+`gemini-embedding-001` is the default model.
 
 To start using this integration with Haystack, install it with:
 

docs-website/docs/pipeline-components/embedders/googlegenaimultimodaldocumentembedder.mdx

@@ -17,7 +17,7 @@ It uses Google AI multimodal embedding models with the ability to embed text, im
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `documents`:  A list of documents, with a meta field containing an image file path |
 | **Output variables** | `documents`: A list of documents (enriched with embeddings)  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
 | **Package name** | `google-genai-haystack` |
 
@@ -31,7 +31,7 @@ The embedder efficiently loads the files, computes the embeddings using a Google
 
 `GoogleGenAIMultimodalDocumentEmbedder` is commonly used in indexing pipelines. At retrieval time, you need to use the same model with a `GoogleGenAITextEmbedder` to embed the query, before using an Embedding Retriever.
 
-This component is compatible with Gemini multimodal models: `gemini-embedding-2-preview` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
+This component is compatible with Gemini multimodal models: `gemini-embedding-2` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
 
 To embed a textual document, you should use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx).
 To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
@@ -125,7 +125,7 @@ print(result["documents"][0].embedding)
 
 ### Setting embedding dimensions
 
-Models like `gemini-embedding-2-preview` have a default embedding dimension of 3072, but, thanks to
+Models like `gemini-embedding-2` have a default embedding dimension of 3072, but, thanks to
 Matryoshka Representation Learning, it's possible to reduce embedding size while keeping similar performance.
 
 Check the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings#control-embedding-size) for more information.

docs-website/docs/pipeline-components/embedders/googlegenaitextembedder.mdx

@@ -17,7 +17,7 @@ This component transforms a string into a vector that captures its semantics usi
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `text`: A string |
 | **Output variables** | `embedding`: A list of float numbers  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
 | **Package name** | `google-genai-haystack` |
 
@@ -27,10 +27,9 @@ This component transforms a string into a vector that captures its semantics usi
 
 `GoogleGenAITextEmbedder` embeds a simple string (such as a query) into a vector. For embedding lists of documents, use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx), which enriches the document with the computed embedding, also known as vector.
 
-The component supports the following Google AI models:
+The component supports [Google AI Embedding models](https://ai.google.dev/gemini-api/docs/embeddings#model-versions).
 
-- `text-embedding-004` (default)
-- `text-embedding-004-v2`
+`gemini-embedding-001` is the default model.
 
 To start using this integration with Haystack, install it with:
 
@@ -107,7 +106,7 @@ text_embedder = GoogleGenAITextEmbedder()
 
 print(text_embedder.run(text_to_embed))
 ## {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
-## 'meta': {'model': 'text-embedding-004',
+## 'meta': {'model': 'gemini-embedding-001',
 ## 'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}
 ```
 

docs-website/versioned_docs/version-2.25/pipeline-components/embedders/googlegenaimultimodaldocumentembedder.mdx

@@ -30,7 +30,7 @@ The embedder efficiently loads the files, computes the embeddings using a Google
 
 `GoogleGenAIMultimodalDocumentEmbedder` is commonly used in indexing pipelines. At retrieval time, you need to use the same model with a `GoogleGenAITextEmbedder` to embed the query, before using an Embedding Retriever.
 
-This component is compatible with Gemini multimodal models: `gemini-embedding-2-preview` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
+This component is compatible with Gemini multimodal models: `gemini-embedding-2` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
 
 To embed a textual document, you should use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx).
 To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
@@ -124,7 +124,7 @@ print(result["documents"][0].embedding)
 
 ### Setting embedding dimensions
 
-Models like `gemini-embedding-2-preview` have a default embedding dimension of 3072, but, thanks to
+Models like `gemini-embedding-2` have a default embedding dimension of 3072, but, thanks to
 Matryoshka Representation Learning, it's possible to reduce embedding size while keeping similar performance.
 
 Check the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings#control-embedding-size) for more information.

docs-website/versioned_docs/version-2.26/pipeline-components/embedders/googlegenaimultimodaldocumentembedder.mdx

@@ -30,7 +30,7 @@ The embedder efficiently loads the files, computes the embeddings using a Google
 
 `GoogleGenAIMultimodalDocumentEmbedder` is commonly used in indexing pipelines. At retrieval time, you need to use the same model with a `GoogleGenAITextEmbedder` to embed the query, before using an Embedding Retriever.
 
-This component is compatible with Gemini multimodal models: `gemini-embedding-2-preview` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
+This component is compatible with Gemini multimodal models: `gemini-embedding-2` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
 
 To embed a textual document, you should use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx).
 To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
@@ -124,7 +124,7 @@ print(result["documents"][0].embedding)
 
 ### Setting embedding dimensions
 
-Models like `gemini-embedding-2-preview` have a default embedding dimension of 3072, but, thanks to
+Models like `gemini-embedding-2` have a default embedding dimension of 3072, but, thanks to
 Matryoshka Representation Learning, it's possible to reduce embedding size while keeping similar performance.
 
 Check the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings#control-embedding-size) for more information.

docs-website/versioned_docs/version-2.27/pipeline-components/embedders/googlegenaimultimodaldocumentembedder.mdx

@@ -30,7 +30,7 @@ The embedder efficiently loads the files, computes the embeddings using a Google
 
 `GoogleGenAIMultimodalDocumentEmbedder` is commonly used in indexing pipelines. At retrieval time, you need to use the same model with a `GoogleGenAITextEmbedder` to embed the query, before using an Embedding Retriever.
 
-This component is compatible with Gemini multimodal models: `gemini-embedding-2-preview` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
+This component is compatible with Gemini multimodal models: `gemini-embedding-2` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
 
 To embed a textual document, you should use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx).
 To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
@@ -124,7 +124,7 @@ print(result["documents"][0].embedding)
 
 ### Setting embedding dimensions
 
-Models like `gemini-embedding-2-preview` have a default embedding dimension of 3072, but, thanks to
+Models like `gemini-embedding-2` have a default embedding dimension of 3072, but, thanks to
 Matryoshka Representation Learning, it's possible to reduce embedding size while keeping similar performance.
 
 Check the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings#control-embedding-size) for more information.

docs-website/versioned_docs/version-2.28/pipeline-components/embedders/googlegenaidocumentembedder.mdx

@@ -17,19 +17,19 @@ The vectors computed by this component are necessary to perform embedding retrie
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `documents`: A list of documents to be embedded |
 | **Output variables** | `documents`: A list of documents (enriched with embeddings)  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
+| **Package name** | `google-genai-haystack` |
 
 </div>
 
 ## Overview
 
 `GoogleGenAIDocumentEmbedder` enriches the metadata of documents with an embedding of their content. To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
 
-The component supports the following Google AI models:
+The component supports [Google AI Embedding models](https://ai.google.dev/gemini-api/docs/embeddings#model-versions).
 
-- `text-embedding-004` (default)
-- `text-embedding-004-v2`
+`gemini-embedding-001` is the default model.
 
 To start using this integration with Haystack, install it with:
 

docs-website/versioned_docs/version-2.28/pipeline-components/embedders/googlegenaimultimodaldocumentembedder.mdx

@@ -17,8 +17,9 @@ It uses Google AI multimodal embedding models with the ability to embed text, im
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `documents`:  A list of documents, with a meta field containing an image file path |
 | **Output variables** | `documents`: A list of documents (enriched with embeddings)  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
+| **Package name** | `google-genai-haystack` |
 
 </div>
 
@@ -30,7 +31,7 @@ The embedder efficiently loads the files, computes the embeddings using a Google
 
 `GoogleGenAIMultimodalDocumentEmbedder` is commonly used in indexing pipelines. At retrieval time, you need to use the same model with a `GoogleGenAITextEmbedder` to embed the query, before using an Embedding Retriever.
 
-This component is compatible with Gemini multimodal models: `gemini-embedding-2-preview` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
+This component is compatible with Gemini multimodal models: `gemini-embedding-2` and later. For a complete list of supported models, see the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings).
 
 To embed a textual document, you should use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx).
 To embed a string, you should use the [`GoogleGenAITextEmbedder`](googlegenaitextembedder.mdx).
@@ -124,7 +125,7 @@ print(result["documents"][0].embedding)
 
 ### Setting embedding dimensions
 
-Models like `gemini-embedding-2-preview` have a default embedding dimension of 3072, but, thanks to
+Models like `gemini-embedding-2` have a default embedding dimension of 3072, but, thanks to
 Matryoshka Representation Learning, it's possible to reduce embedding size while keeping similar performance.
 
 Check the [Google AI documentation](https://ai.google.dev/gemini-api/docs/embeddings#control-embedding-size) for more information.

docs-website/versioned_docs/version-2.28/pipeline-components/embedders/googlegenaitextembedder.mdx

@@ -17,19 +17,19 @@ This component transforms a string into a vector that captures its semantics usi
 | **Mandatory init variables** | `api_key`: The Google API key. Can be set with `GOOGLE_API_KEY` or `GEMINI_API_KEY` env var. |
 | **Mandatory run variables** | `text`: A string |
 | **Output variables** | `embedding`: A list of float numbers  <br /> <br />`meta`: A dictionary of metadata |
-| **API reference** | [Google AI](/reference/integrations-google-genai) |
+| **API reference** | [Google GenAI](/reference/integrations-google-genai) |
 | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_genai |
+| **Package name** | `google-genai-haystack` |
 
 </div>
 
 ## Overview
 
 `GoogleGenAITextEmbedder` embeds a simple string (such as a query) into a vector. For embedding lists of documents, use the [`GoogleGenAIDocumentEmbedder`](googlegenaidocumentembedder.mdx), which enriches the document with the computed embedding, also known as vector.
 
-The component supports the following Google AI models:
+The component supports [Google AI Embedding models](https://ai.google.dev/gemini-api/docs/embeddings#model-versions).
 
-- `text-embedding-004` (default)
-- `text-embedding-004-v2`
+`gemini-embedding-001` is the default model.
 
 To start using this integration with Haystack, install it with:
 
@@ -106,7 +106,7 @@ text_embedder = GoogleGenAITextEmbedder()
 
 print(text_embedder.run(text_to_embed))
 ## {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
-## 'meta': {'model': 'text-embedding-004',
+## 'meta': {'model': 'gemini-embedding-001',
 ## 'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}
 ```