diff --git a/docs/weaviate/model-providers/cohere/embeddings-multimodal.md b/docs/weaviate/model-providers/cohere/embeddings-multimodal.md index aaeffa4c..e7126e2d 100644 --- a/docs/weaviate/model-providers/cohere/embeddings-multimodal.md +++ b/docs/weaviate/model-providers/cohere/embeddings-multimodal.md @@ -295,7 +295,7 @@ The query below returns the `n` most similar objects to the input image from the ### Available models - `embed-v4.0` -- `embed-multilingual-v3.0` (Default) +- `embed-multilingual-v3.0` (server default) - `embed-multilingual-light-v3.0` - `embed-english-v3.0` - `embed-english-light-v3.0` diff --git a/docs/weaviate/model-providers/cohere/embeddings.md b/docs/weaviate/model-providers/cohere/embeddings.md index 3250e0b7..6464cb67 100644 --- a/docs/weaviate/model-providers/cohere/embeddings.md +++ b/docs/weaviate/model-providers/cohere/embeddings.md @@ -356,7 +356,7 @@ The query below returns the `n` best scoring objects from the database, set by ` ### Available models - `embed-v4.0` -- `embed-multilingual-v3.0` (Default) +- `embed-multilingual-v3.0` (server default) - `embed-multilingual-light-v3.0` - `embed-multilingual-v2.0` (previously `embed-multilingual-22-12`) - `embed-english-v3.0` @@ -379,7 +379,7 @@ The following models are available, but deprecated: ### Other integrations -- [Cohere multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [Cohere multimodal embedding models + Weaviate](./embeddings-multimodal.md) - [Cohere generative models + Weaviate](./generative.md) - [Cohere reranker models + Weaviate](./reranker.md) diff --git a/docs/weaviate/model-providers/cohere/generative.md b/docs/weaviate/model-providers/cohere/generative.md index 6bc94c00..15ba4486 100644 --- a/docs/weaviate/model-providers/cohere/generative.md +++ b/docs/weaviate/model-providers/cohere/generative.md @@ -288,7 +288,7 @@ The following models are commonly used: ### Other integrations - [Cohere text embedding models + Weaviate](./embeddings.md). -- [Cohere multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [Cohere multimodal embedding models + Weaviate](./embeddings-multimodal.md). - [Cohere reranker models + Weaviate](./reranker.md). ### Code examples diff --git a/docs/weaviate/model-providers/cohere/reranker.md b/docs/weaviate/model-providers/cohere/reranker.md index e04e7c03..5f3565b5 100644 --- a/docs/weaviate/model-providers/cohere/reranker.md +++ b/docs/weaviate/model-providers/cohere/reranker.md @@ -180,7 +180,7 @@ Any search in Weaviate can be combined with a reranker to perform reranking oper ### Available models -- `rerank-v3.5` (default) +- `rerank-v3.5` (server default) - `rerank-english-v3.0` - `rerank-multilingual-v3.0` - `rerank-english-v2.0` @@ -199,7 +199,7 @@ For further details on model parameters, see the [Cohere API documentation](http ### Other integrations - [Cohere text embedding models + Weaviate](./embeddings.md). -- [Cohere multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [Cohere multimodal embedding models + Weaviate](./embeddings-multimodal.md). - [Cohere generative models + Weaviate](./generative.md). ### Code examples diff --git a/docs/weaviate/model-providers/databricks/embeddings.md b/docs/weaviate/model-providers/databricks/embeddings.md index 6207c204..7060f1b4 100644 --- a/docs/weaviate/model-providers/databricks/embeddings.md +++ b/docs/weaviate/model-providers/databricks/embeddings.md @@ -50,7 +50,7 @@ This integration is enabled by default on Weaviate Cloud (WCD) instances. You must provide a valid Databricks Personal Access Token (PAT) to Weaviate for this integration. Refer to the [Databricks documentation](https://docs.databricks.com/en/dev-tools/auth/pat.html) for instructions on generating your PAT in your workspace. -Provide the Dataricks token to Weaviate using one of the following methods: +Provide the Databricks token to Weaviate using one of the following methods: - Set the `DATABRICKS_TOKEN` environment variable that is available to Weaviate. - Provide the token at runtime, as shown in the examples below. @@ -125,13 +125,13 @@ This will configure Weaviate to use the vectorizer served through the endpoint y ### Vectorizer parameters - `endpoint`: The URL of the embedding model hosted on Databricks. -- `instruction`:An optional instruction to pass to the embedding model. +- `instruction`: An optional instruction to pass to the embedding model. For further details on model parameters, see the [Databricks documentation](https://docs.databricks.com/en/machine-learning/foundation-models/api-reference.html#embedding-request). ## Header parameters -You can provide the API key as well as some optional parameters at runtime through additional headers in the request. The following headers are available: +You can provide the token as well as some optional parameters at runtime through additional headers in the request. The following headers are available: - `X-Databricks-Token`: The Databricks API token. - `X-Databricks-Endpoint`: The endpoint to use for the Databricks model. diff --git a/docs/weaviate/model-providers/databricks/generative.md b/docs/weaviate/model-providers/databricks/generative.md index 8f9a5278..22c953e6 100644 --- a/docs/weaviate/model-providers/databricks/generative.md +++ b/docs/weaviate/model-providers/databricks/generative.md @@ -48,10 +48,10 @@ This integration is enabled by default on Weaviate Cloud (WCD) instances. You must provide a valid Databricks Personal Access Token (PAT) to Weaviate for this integration. Refer to the [Databricks documentation](https://docs.databricks.com/en/dev-tools/auth/pat.html) for instructions on generating your PAT in your workspace. -Provide the Dataricks token to Weaviate using one of the following methods: +Provide the Databricks token to Weaviate using one of the following methods: - Set the `DATABRICKS_TOKEN` environment variable that is available to Weaviate. -- Provide the API key at runtime, as shown in the examples below. +- Provide the token at runtime, as shown in the examples below. @@ -156,7 +156,7 @@ Aside from setting the default model provider when creating the collection, you ## Header parameters -You can provide the API key as well as some optional parameters at runtime through additional headers in the request. The following headers are available: +You can provide the token as well as some optional parameters at runtime through additional headers in the request. The following headers are available: - `X-Databricks-Token`: The Databricks API token. - `X-Databricks-Endpoint`: The endpoint to use for the Databricks model. diff --git a/docs/weaviate/model-providers/google/index.md b/docs/weaviate/model-providers/google/index.md index 5e11e7c9..7b0d72ff 100644 --- a/docs/weaviate/model-providers/google/index.md +++ b/docs/weaviate/model-providers/google/index.md @@ -22,6 +22,7 @@ Google's embedding models transform text data into vector embeddings, capturing [Weaviate integrates with Google's embedding models](./embeddings.md) to enable seamless vectorization of data. This integration allows users to perform semantic and hybrid search operations without the need for additional preprocessing or data transformation steps. [Google embedding integration page](./embeddings.md) + [Google multimodal embedding integration page](./embeddings-multimodal.md) ### Generative AI models for RAG @@ -42,11 +43,11 @@ In turn, they simplify the process of building AI-driven applications to speed u ## Credentials -You must provide a valid Googles API credentials to Weaviate for these integrations. +You must provide valid Google API credentials to Weaviate for these integrations. ### Vertex AI -##### Automatic token generation +#### Automatic token generation import UseGoogleAuthInstructions from './_includes/use_google_auth_instructions.mdx'; @@ -54,7 +55,7 @@ import UseGoogleAuthInstructions from './_includes/use_google_auth_instructions. ## Get started -Weaviate integrates with both [Google Gemini API](https://aistudio.google.com/app/apikey/?utm_source=weaviate&utm_medium=referral&utm_campaign=partnerships&utm_content=) or [Google Vertex AI](https://cloud.google.com/vertex-ai). +Weaviate integrates with both the [Google Gemini API](https://aistudio.google.com/app/apikey/?utm_source=weaviate&utm_medium=referral&utm_campaign=partnerships&utm_content=) and [Google Vertex AI](https://cloud.google.com/vertex-ai). Go to the relevant integration page to learn how to configure Weaviate with the Google models and start using them in your applications. diff --git a/docs/weaviate/model-providers/kubeai/index.md b/docs/weaviate/model-providers/kubeai/index.md index 8f820019..e1d50080 100644 --- a/docs/weaviate/model-providers/kubeai/index.md +++ b/docs/weaviate/model-providers/kubeai/index.md @@ -7,7 +7,7 @@ image: og/docs/integrations/provider_integrations_kubeai.jpg -[KubeAI](https://github.com/substratusai/kubeai) provides offers a wide range of models for natural language processing and generation through OpenAI-style API endpoints. Weaviate seamlessly integrates with KubeAI's APIs, allowing users to leverage any KubeAI models directly from the Weaviate Database. +[KubeAI](https://github.com/substratusai/kubeai) offers a wide range of models for natural language processing and generation through OpenAI-style API endpoints. Weaviate seamlessly integrates with KubeAI's APIs, allowing users to leverage any KubeAI models directly from the Weaviate Database. These integrations empower developers to build sophisticated AI-driven applications with ease. diff --git a/docs/weaviate/model-providers/nvidia/embeddings.md b/docs/weaviate/model-providers/nvidia/embeddings.md index 82ef5664..377ecdaf 100644 --- a/docs/weaviate/model-providers/nvidia/embeddings.md +++ b/docs/weaviate/model-providers/nvidia/embeddings.md @@ -342,7 +342,7 @@ The default model is `nvidia/nv-embed-v1`. ### Other integrations -- [NVIDIA multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [NVIDIA multimodal embedding models + Weaviate](./embeddings-multimodal.md) - [NVIDIA generative models + Weaviate](./generative.md) - [NVIDIA reranker models + Weaviate](./reranker.md) diff --git a/docs/weaviate/model-providers/nvidia/generative.md b/docs/weaviate/model-providers/nvidia/generative.md index 6e49a16c..59473b3f 100644 --- a/docs/weaviate/model-providers/nvidia/generative.md +++ b/docs/weaviate/model-providers/nvidia/generative.md @@ -260,7 +260,7 @@ The default model is `nvidia/llama-3.1-nemotron-51b-instruct`. ### Other integrations - [NVIDIA text embedding models + Weaviate](./embeddings.md). -- [NVIDIA multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [NVIDIA multimodal embedding models + Weaviate](./embeddings-multimodal.md). - [NVIDIA reranker models + Weaviate](./reranker.md). ### Code examples diff --git a/docs/weaviate/model-providers/nvidia/reranker.md b/docs/weaviate/model-providers/nvidia/reranker.md index 57a29e85..497b6dfa 100644 --- a/docs/weaviate/model-providers/nvidia/reranker.md +++ b/docs/weaviate/model-providers/nvidia/reranker.md @@ -177,7 +177,7 @@ The default model is `nvidia/rerank-qa-mistral-4b`. ### Other integrations - [NVIDIA text embedding models + Weaviate](./embeddings.md). -- [NVIDIA multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [NVIDIA multimodal embedding models + Weaviate](./embeddings-multimodal.md). - [NVIDIA generative models + Weaviate](./generative.md). ### Code examples diff --git a/docs/weaviate/model-providers/transformers/embeddings-custom-image.md b/docs/weaviate/model-providers/transformers/embeddings-custom-image.md index 7c2be7f1..424eaa18 100644 --- a/docs/weaviate/model-providers/transformers/embeddings-custom-image.md +++ b/docs/weaviate/model-providers/transformers/embeddings-custom-image.md @@ -70,7 +70,7 @@ To build an image with a local, custom model, create a new `Dockerfile` similar Save the `Dockerfile` as `my-inference-image.Dockerfile`. (You can name it anything you like.)
-This will creates a custom image for a model stored in a local folder `my-model` on your machine. +This will create a custom image for a model stored in a local folder `my-model` on your machine.
```yaml diff --git a/docs/weaviate/model-providers/transformers/embeddings-multimodal-custom-image.md b/docs/weaviate/model-providers/transformers/embeddings-multimodal-custom-image.md index 0773b08b..e2e6ec49 100644 --- a/docs/weaviate/model-providers/transformers/embeddings-multimodal-custom-image.md +++ b/docs/weaviate/model-providers/transformers/embeddings-multimodal-custom-image.md @@ -61,16 +61,16 @@ RUN CLIP_MODEL_NAME=clip-ViT-B-32 TEXT_MODEL_NAME=clip-ViT-B-32 ./download.py -You can also build a custom image with any model that is compatible with the Transformer library's `SentenceTransformers` and `ClIPModel` classes. To ensure that text embeddings will output compatible vectors to image embeddings, you must only use models that have been specifically trained for use with CLIP models. (Note that a CLIP model is in reality two models: one for text and one for images.) +You can also build a custom image with models compatible with the `SentenceTransformer` class from the Sentence Transformers library and the `CLIPModel` class from the Transformers library. To ensure that text embeddings will output compatible vectors to image embeddings, you must only use models that have been specifically trained for use with CLIP models. (Note that a CLIP model is in reality two models: one for text and one for images.)
-To build an image with a local, custom model, create a new `Dockerfile` similar to the following, replacing `./my-test-model` and `./my-clip-model` with the path to your model folder. +To build an image with a local, custom model, create a new `Dockerfile` similar to the following, replacing `./my-text-model` and `./my-clip-model` with the paths to your model folders.
Save the `Dockerfile` as `my-inference-image.Dockerfile`. (You can name it anything you like.)
-This will creates a custom image for a model stored in a local folder `my-model` on your machine. +This will create a custom image for the models stored in the local folders `my-text-model` and `my-clip-model` on your machine.
```yaml diff --git a/docs/weaviate/model-providers/transformers/embeddings-multimodal.md b/docs/weaviate/model-providers/transformers/embeddings-multimodal.md index cc14c4eb..5c1640c3 100644 --- a/docs/weaviate/model-providers/transformers/embeddings-multimodal.md +++ b/docs/weaviate/model-providers/transformers/embeddings-multimodal.md @@ -156,8 +156,8 @@ As this integration runs a local container with the CLIP model, no additional cr -:::note Chose a container image to select a model -To chose a model, select the [container image](#configure-the-integration) that hosts it. +:::note Choose a container image to select a model +To choose a model, select the [container image](#configure-the-integration) that hosts it. ::: import VectorizationBehavior from '/_includes/vectorization.behavior.mdx'; diff --git a/docs/weaviate/model-providers/transformers/embeddings.md b/docs/weaviate/model-providers/transformers/embeddings.md index 28ebd31a..a0fd1ebf 100644 --- a/docs/weaviate/model-providers/transformers/embeddings.md +++ b/docs/weaviate/model-providers/transformers/embeddings.md @@ -159,8 +159,8 @@ As this integration runs a local container with the Transformers model, no addit -:::note Chose a container image to select a model -To chose a model, select the [container image](#configure-the-integration) that hosts it. +:::note Choose a container image to select a model +To choose a model, select the [container image](#configure-the-integration) that hosts it. ::: import VectorizationBehavior from '/_includes/vectorization.behavior.mdx'; diff --git a/docs/weaviate/model-providers/transformers/reranker.md b/docs/weaviate/model-providers/transformers/reranker.md index cff1fba8..b47029ee 100644 --- a/docs/weaviate/model-providers/transformers/reranker.md +++ b/docs/weaviate/model-providers/transformers/reranker.md @@ -160,8 +160,8 @@ Configure a Weaviate collection to use a Transformer reranker model as follows: -:::note Chose a container image to select a model -To chose a model, select the [container image](#configure-the-integration) that hosts it. +:::note Choose a container image to select a model +To choose a model, select the [container image](#configure-the-integration) that hosts it. ::: ## Reranking query diff --git a/docs/weaviate/model-providers/voyageai/embeddings.md b/docs/weaviate/model-providers/voyageai/embeddings.md index 7e727bef..d45101c6 100644 --- a/docs/weaviate/model-providers/voyageai/embeddings.md +++ b/docs/weaviate/model-providers/voyageai/embeddings.md @@ -387,7 +387,7 @@ The `voyage-context-3` model uses Voyage AI's [contextual embeddings API](https: ### Other integrations -- [Voyage AI multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [Voyage AI multimodal embedding models + Weaviate](./embeddings-multimodal.md). - [Voyage AI reranker models + Weaviate](./reranker.md). ### Code examples diff --git a/docs/weaviate/model-providers/voyageai/reranker.md b/docs/weaviate/model-providers/voyageai/reranker.md index 452eee94..d85b75e5 100644 --- a/docs/weaviate/model-providers/voyageai/reranker.md +++ b/docs/weaviate/model-providers/voyageai/reranker.md @@ -184,7 +184,7 @@ Any search in Weaviate can be combined with a reranker to perform reranking oper ### Other integrations - [Voyage AI embedding models + Weaviate](./embeddings.md). -- [Voyage AI multimodal embedding embeddings models + Weaviate](./embeddings-multimodal.md) +- [Voyage AI multimodal embedding models + Weaviate](./embeddings-multimodal.md). ### Code examples