Document Azure OpenAI Models support (#683)

spiceai · Dec 16, 2024 · eb3eaed · eb3eaed
1 parent 588b281
commit eb3eaed
Show file tree

Hide file tree

Showing 9 changed files with 83 additions and 9 deletions.
diff --git a/spiceaidocs/docs/components/embeddings/azure.md b/spiceaidocs/docs/components/embeddings/azure.md
@@ -0,0 +1,34 @@
+---
+title: 'Azure OpenAI Embedding Models'
+sidebar_label: 'Azure OpenAI'
+sidebar_position: 2
+---
+
+To use an embedding model hosted on Azure OpenAI, specify the `azure` path in the `from` field and the following parameters from the [Azure OpenAI Model Deployment](https://ai.azure.com/resource/deployments) page:
+
+| Param                   | Description                                                                 | Default                     |
+| ----------------------- | --------------------------------------------------------------------------- | --------------------------- |
+| `azure_api_key`         | The Azure OpenAI API key from the models deployment page.                   | -                           |
+| `azure_api_version`     | The API version used for the Azure OpenAI service.                          | -                           |
+| `azure_deployment_name` | The name of the model deployment.                                           | Model name                  |
+| `endpoint`              | The Azure OpenAI resource endpoint, e.g., `https://resource-name.openai.azure.com`. | -                           |
+| `azure_entra_token`     | The Azure Entra token for authentication.                                   | -                           |
+
+Only one of `azure_api_key` or `azure_entra_token` can be provided for model configuration.
+
+Example:
+
+```yaml
+embeddings:
+  - name: embeddings-model
+    from: azure:text-embedding-3-small
+    params:
+      endpoint: ${ secrets:SPICE_AZURE_AI_ENDPOINT }
+      azure_deployment_name: text-embedding-3-small
+      azure_api_version: 2023-05-15
+      azure_api_key: ${ secrets:SPICE_AZURE_API_KEY }
+```
+
+Refer to the [Azure OpenAI Service models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) for more details on available models and configurations.
+
+Follow [Quickstart: Using Azure OpenAI models](https://github.com/spiceai/quickstarts/tree/trunk/azure_openai) to try Azure OpenAI models for vector-based search and chat functionalities with structured (taxi trips) and unstructured (GitHub files) data.
diff --git a/spiceaidocs/docs/components/embeddings/huggingface.md b/spiceaidocs/docs/components/embeddings/huggingface.md
@@ -1,7 +1,7 @@
 ---
 title: 'HuggingFace Text Embedding Models'
 sidebar_label: 'HuggingFace'
-sidebar_position: 2
+sidebar_position: 3
 ---
 
 To use an embedding model from HuggingFace with Spice, specify the `huggingface` path in the `from` field of your configuration. The model and its related files will be automatically downloaded, loaded, and served locally by Spice.

diff --git a/spiceaidocs/docs/components/models/anthropic.md b/spiceaidocs/docs/components/models/anthropic.md
@@ -2,12 +2,12 @@
 title: 'Anthropic Models'
 description: 'Instructions for using language models hosted on Anthropic with Spice.'
 sidebar_label: 'Anthropic'
-sidebar_position: 5
+sidebar_position: 3
 ---
 
 To use a language model hosted on Anthropic, specify `anthropic` in the `from` field.
 
-To use a specific model, include its model ID in the `from` field (see example below). If not specified, the default model is `"claude-3-5-sonnet-latest"`.
+To use a specific model, include its model ID in the `from` field (see example below). If not specified, the default model is `claude-3-5-sonnet-latest`.
 
 The following parameters are specific to Anthropic models:
 

diff --git a/spiceaidocs/docs/components/models/azure.md b/spiceaidocs/docs/components/models/azure.md
@@ -0,0 +1,35 @@
+---
+title: 'Azure OpenAI Models'
+description: 'Instructions for using Azure OpenAI models'
+sidebar_label: 'Azure OpenAI'
+sidebar_position: 2
+---
+
+To use a language model hosted on Azure OpenAI, specify the `azure` path in the `from` field and the following parameters from the [Azure OpenAI Model Deployment](https://ai.azure.com/resource/deployments) page:
+
+| Param                   | Description                                                                 | Default                     |
+| ----------------------- | --------------------------------------------------------------------------- | --------------------------- |
+| `azure_api_key`         | The Azure OpenAI API key from the models deployment page.                   | -                           |
+| `azure_api_version`     | The API version used for the Azure OpenAI service.                          | -                           |
+| `azure_deployment_name` | The name of the model deployment.                                           | Model name                  |
+| `endpoint`              | The Azure OpenAI resource endpoint, e.g., `https://resource-name.openai.azure.com`. | -                           |
+| `azure_entra_token`     | The Azure Entra token for authentication.                                   | -                           |
+
+Only one of `azure_api_key` or `azure_entra_token` can be provided for model configuration.
+
+Example:
+
+```yaml
+models:
+  - from: azure:gpt-4o-mini
+    name: gpt-4o-mini
+    params:
+      endpoint: ${ secrets:SPICE_AZURE_AI_ENDPOINT }
+      azure_api_version: 2024-08-01-preview
+      azure_deployment_name: gpt-4o-mini
+      azure_api_key: ${ secrets:SPICE_AZURE_API_KEY }
+```
+
+Refer to the [Azure OpenAI Service models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) for more details on available models and configurations.
+
+Follow [Quickstart: Using Azure OpenAI models](https://github.com/spiceai/quickstarts/tree/trunk/azure_openai) to try Azure OpenAI models for vector-based search and chat functionalities with structured (taxi trips) and unstructured (GitHub files) data.
diff --git a/spiceaidocs/docs/components/models/filesystem.md b/spiceaidocs/docs/components/models/filesystem.md
@@ -2,7 +2,7 @@
 title: 'Filesystem'
 description: 'Instructions for using models hosted on a filesystem with Spice.'
 sidebar_label: 'Filesystem'
-sidebar_position: 3
+sidebar_position: 5
 ---
 
 To use a model hosted on a filesystem, specify the path to the model file in the `from` field.

diff --git a/spiceaidocs/docs/components/models/huggingface.md b/spiceaidocs/docs/components/models/huggingface.md
@@ -2,7 +2,7 @@
 title: 'HuggingFace'
 description: 'Instructions for using machine learning models hosted on HuggingFace with Spice.'
 sidebar_label: 'HuggingFace'
-sidebar_position: 1
+sidebar_position: 4
 ---
 
 To use a model hosted on HuggingFace, specify the `huggingface.co` path in the `from` field along with the files to include.

diff --git a/spiceaidocs/docs/components/models/index.md b/spiceaidocs/docs/components/models/index.md
@@ -13,6 +13,7 @@ Spice supports various model providers for traditional machine learning (ML) mod
 | `huggingface` | Models hosted on [HuggingFace](https://huggingface.co)                                          | ONNX         | GGUF, GGML, SafeTensor |
 | `spice.ai`    | Models hosted on the [Spice Cloud Platform](https://docs.spice.ai/building-blocks/spice-models) | ONNX         | -                      |
 | `openai`      | OpenAI (or compatible) LLM endpoint                                                             | -            | Remote HTTP endpoint   |
+| `azure`       | Azure OpenAI                                                                                    | -            | Remote HTTP endpoint   |
 | `anthropic`   | Models hosted on [Anthropic](https://www.anthropic.com)                                         | -            | Remote HTTP endpoint   |
 | `grok`        | Coming soon                                                                                     | -            | Remote HTTP endpoint   |
 

diff --git a/spiceaidocs/docs/components/models/openai.md b/spiceaidocs/docs/components/models/openai.md
@@ -2,12 +2,12 @@
 title: 'OpenAI (or Compatible) Language Models'
 description: 'Instructions for using language models hosted on OpenAI or compatible services with Spice.'
 sidebar_label: 'OpenAI'
-sidebar_position: 4
+sidebar_position: 1
 ---
 
 To use a language model hosted on OpenAI (or compatible), specify the `openai` path in the `from` field.
 
-For a specific model, include it as the model ID in the `from` field (see example below). The default model is `"gpt-3.5-turbo"`.
+For a specific model, include it as the model ID in the `from` field (see example below). The default model is `gpt-3.5-turbo`.
 
 These parameters are specific to OpenAI models:
 
@@ -23,7 +23,7 @@ Example:
 ```yaml
 models:
   - from: openai:gpt-4o
-    name: local_fs_model
+    name: openai_model
     params:
       openai_api_key: ${ secrets:SPICE_OPENAI_API_KEY }
 ```
@@ -32,6 +32,10 @@ models:
 
 Spice supports several OpenAI compatible providers. Specify the appropriate endpoint in the params section.
 
+### Azure OpenAI
+
+Follow [Azure AI Models](./azure) instructions.
+
 ### Groq
 
 Groq provides OpenAI compatible endpoints. Use the following configuration:

diff --git a/spiceaidocs/docs/components/models/spiceai.md b/spiceaidocs/docs/components/models/spiceai.md
@@ -2,7 +2,7 @@
 title: 'Spice Cloud Platform'
 description: 'Instructions for using models hosted on the Spice Cloud Platform with Spice.'
 sidebar_label: 'Spice Cloud Platform'
-sidebar_position: 2
+sidebar_position: 5
 ---
 
 To use a model hosted on the [Spice Cloud Platform](https://docs.spice.ai/building-blocks/spice-models), specify the `spice.ai` path in the `from` field.