Update available models

docs/weaviate/model-providers/_includes/provider.generative.py

@@ -668,7 +668,7 @@ def import_data():
     # highlight-start
     generative_config=Configure.Generative.google(
         project_id="<google-cloud-project-id>",  # Required for Vertex AI
-        model_id="gemini-1.0-pro"
+        model_id="gemini-2.5-flash"
     )
     # highlight-end
     # Additional parameters not shown
@@ -685,7 +685,7 @@ def import_data():
     "DemoCollection",
     # highlight-start
     generative_config=Configure.Generative.google(
-        model_id="gemini-pro"
+        model_id="gemini-2.5-flash"
     )
     # highlight-end
     # Additional parameters not shown

docs/weaviate/model-providers/_includes/provider.generative.ts

@@ -597,7 +597,7 @@ await client.collections.create({
   // highlight-start
   generative: weaviate.configure.generative.google({
     projectId: '<google-cloud-project-id>',  // Required for Vertex AI
-    modelId: 'gemini-1.0-pro'
+    modelId: 'gemini-2.5-flash'
   }),
   // highlight-end
   // Additional parameters not shown
@@ -612,7 +612,7 @@ await client.collections.create({
   name: 'DemoCollection',
   // highlight-start
   generative: weaviate.configure.generative.google({
-    modelId: 'gemini-pro',
+    modelId: 'gemini-2.5-flash',
   }),
   // highlight-end
   // Additional parameters not shown

docs/weaviate/model-providers/_includes/provider.vectorizer.py

@@ -277,7 +277,7 @@
         name="title_vector",
         source_properties=["title"],
         # (Optional) To manually set the model ID
-        model="text-embedding-004"
+        model="gemini-embedding-001"
     ),
     # highlight-end
     # Additional parameters not shown
@@ -317,7 +317,7 @@
         name="title_vector",
         source_properties=["title"],
         # Further options
-        model_id="text-embedding-004",
+        model_id="gemini-embedding-001",
     ),
     # highlight-end
     # Additional parameters not shown

docs/weaviate/model-providers/google/embeddings-multimodal.md

@@ -19,7 +19,7 @@ import TSCode from '!!raw-loader!../_includes/provider.vectorizer.ts';
 Weaviate's integration with [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs allows you to access their models' capabilities directly from Weaviate.
 
 :::note Gemini API not available
-Multimodal embeddings are currently not available to Google Gemini API users.
+Multimodal embeddings are currently only available to Google Vertex AI users.
 :::
 
 [Configure a Weaviate vector index](#configure-the-vectorizer) to use a Google embedding model, and Weaviate will generate embeddings for various operations using the specified model and your Google API key. This feature is called the *vectorizer*.
@@ -138,7 +138,7 @@ import ApiKeyNote from '../_includes/google-api-key-note.md';
 
 </Tabs>
 
-You can [specify](#vectorizer-parameters) one of the [available models](#available-models) for the vectorizer to use. Currently, `multimodalembedding@001` is the only available model.
+You can [specify](#vectorizer-parameters) one of the [available models](#available-models) for the vectorizer to use.
 
 <!-- The default model (`textembedding-gecko@001` for Vertex AI, `embedding-001` for Gemini API) is used if no model is specified. -->
 

docs/weaviate/model-providers/google/embeddings.md

@@ -35,7 +35,7 @@ At [import time](#data-import), Weaviate generates text object embeddings and sa
 :::
 
 :::info Gemini API availability
-At the time of writing (November 2023), Gemini API is not available in all regions. See [this page](https://ai.google.dev/gemini-api/docs/available-regions) for the latest information.
+Gemini API is not available in all regions. See [this page](https://ai.google.dev/gemini-api/docs/available-regions) for the latest information.
 :::
 
 ## Requirements
@@ -230,7 +230,7 @@ import VectorizationBehavior from '/_includes/vectorization.behavior.mdx';
 The following examples show how to configure Google-specific options.
 
 **Google AI Studio (Gemini API) parameters:**
-- `modelId` (Optional): e.g. `text-embedding-004`, `gemini-embedding-001`
+- `modelId` (Optional): e.g. `gemini-embedding-001`
 
 **Vertex AI parameters:**
 - `projectId` (Required): Your Google Cloud project ID, e.g. `cloud-large-language-models`
@@ -395,9 +395,7 @@ The query below returns the `n` best scoring objects from the database, set by `
 ### Available models
 
 **Google AI Studio (Gemini API):**
-- `text-embedding-004` (recommended)
 - `gemini-embedding-001` (default)
-    - `embedding-001` (deprecated name for `gemini-embedding-001`)
 
 **Vertex AI:**
 - `gemini-embedding-001` (default, added in 1.30.11, 1.31.5 and onwards)
@@ -409,6 +407,8 @@ The query below returns the `n` best scoring objects from the database, set by `
 
 The following models have been deprecated by Google and are no longer supported. They may not function as expected.
 
+- `text-embedding-004`
+- `embedding-001`
 - `textembedding-gecko@001`
 - `textembedding-gecko@002`
 - `textembedding-gecko@003`

docs/weaviate/model-providers/google/generative.md

@@ -26,7 +26,7 @@ More specifically, Weaviate will perform a search, retrieve the most relevant ob
 ![RAG integration illustration](../_includes/integration_google_rag.png)
 
 :::info Gemini API availability
-At the time of writing (November 2023), Gemini API is not available in all regions. See [this page](https://ai.google.dev/gemini-api/docs/available-regions) for the latest information.
+Gemini API is not available in all regions. See [this page](https://ai.google.dev/gemini-api/docs/available-regions) for the latest information.
 :::
 
 ## Requirements
@@ -321,22 +321,42 @@ You can also supply images as a part of the input when performing retrieval augm
 ### Available models
 
 Vertex AI:
-- `chat-bison` (default)
-- `chat-bison-32k` (from Weaviate `v1.24.9`)
-- `chat-bison@002` (from Weaviate `v1.24.9`)
-- `chat-bison-32k@002` (from Weaviate `v1.24.9`)
-- `chat-bison@001` (from Weaviate `v1.24.9`)
-- `gemini-1.5-pro-preview-0514` (from Weaviate `v1.25.1`)
-- `gemini-1.5-pro-preview-0409` (from Weaviate `v1.25.1`)
-- `gemini-1.5-flash-preview-0514` (from Weaviate `v1.25.1`)
-- `gemini-1.0-pro-002` (from Weaviate `v1.25.1`)
-- `gemini-1.0-pro-001` (from Weaviate `v1.25.1`)
-- `gemini-1.0-pro` (from Weaviate `v1.25.1`)
+- `gemini-2.5-pro`
+- `gemini-2.5-flash`
+- `gemini-2.0-flash`
+- `gemini-1.5-pro`
+- `gemini-1.5-flash`
 
 Gemini API:
-- `chat-bison-001` (default)
+- `gemini-2.5-flash`
+- `gemini-2.5-pro`
+- `gemini-2.0-flash`
+- `gemini-1.5-pro`
+- `gemini-1.5-flash`
+
+<details>
+  <summary>Deprecated models</summary>
+
+The following models have been deprecated by Google. They may not function as expected.
+
+**Vertex AI:**
+- `chat-bison`
+- `chat-bison-32k`
+- `chat-bison@002`
+- `chat-bison-32k@002`
+- `chat-bison@001`
+- `gemini-1.0-pro-002`
+- `gemini-1.0-pro-001`
+- `gemini-1.0-pro`
+- `gemini-1.5-pro-preview-0514`
+- `gemini-1.5-pro-preview-0409`
+- `gemini-1.5-flash-preview-0514`
+
+**Gemini API:**
+- `chat-bison-001`
 - `gemini-pro`
-<!-- - `gemini-pro-vision` (from Weaviate `v1.24.2`) -->
+
+</details>
 
 ## Further resources