Skip to content

Commit cea05ec

Browse files
Merge pull request #273175 from shubhirajMsft/patch-8
Add samples deploy-models-cohere-command.md
2 parents ca76872 + bb37350 commit cea05ec

File tree

4 files changed

+52
-12
lines changed

4 files changed

+52
-12
lines changed

articles/ai-studio/how-to/deploy-models-cohere-command.md

Lines changed: 12 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -74,7 +74,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
7474
- An [Azure AI hub resource](../how-to/create-azure-ai-resource.md).
7575

7676
> [!IMPORTANT]
77-
> For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS, EastUS2 or Sweden Central regions.
77+
> For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS2 or Sweden Central region.
7878
7979
- An [Azure AI project](../how-to/create-projects.md) in Azure AI Studio.
8080
- Azure role-based access controls (Azure RBAC) are used to grant access to operations in Azure AI Studio. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, see [Role-based access control in Azure AI Studio](../concepts/rbac-ai-studio.md).
@@ -93,7 +93,7 @@ To create a deployment:
9393

9494
:::image type="content" source="../media/deploy-monitor/cohere-command/command-r-deploy-pay-as-you-go.png" alt-text="A screenshot showing how to deploy a model with the pay-as-you-go option." lightbox="../media/deploy-monitor/cohere-command/command-r-deploy-pay-as-you-go.png":::
9595

96-
1. Select the project in which you want to deploy your model. To deploy the model your project must be in the EastUS, EastUS2 or Sweden Central regions.
96+
1. Select the project in which you want to deploy your model. To deploy the model your project must be in the EastUS2 or Sweden Central region.
9797
1. In the deployment wizard, select the link to **Azure Marketplace Terms** to learn more about the terms of use.
9898
1. You can also select the **Marketplace offer details** tab to learn about pricing for the selected model.
9999
1. If this is your first time deploying the model in the project, you have to subscribe your project for the particular offering. This step requires that your account has the **Azure AI Developer role** permissions on the Resource Group, as listed in the prerequisites. Each project has its own subscription to the particular Azure Marketplace offering of the model, which allows you to control and monitor spending. Select **Subscribe and Deploy**. Currently you can have only one deployment for each model within a project.
@@ -799,6 +799,16 @@ Response:
799799
| OpenAI SDK (experimental) | [openaisdk.ipynb](https://aka.ms/samples/cohere-command/openaisdk) |
800800
| LangChain | [langchain.ipynb](https://aka.ms/samples/cohere/langchain) |
801801
| Cohere SDK | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-python-sdk) |
802+
| LiteLLM SDK | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
803+
804+
##### Retrieval Augmented Generation (RAG) and tool use samples
805+
**Description** | **Sample Type** | **Sample Notebook**
806+
--|--|--
807+
Create a local Facebook AI similarity search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
808+
Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
809+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
810+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
811+
Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
802812

803813
## Cost and quotas
804814

articles/ai-studio/how-to/deploy-models-cohere-embed.md

Lines changed: 14 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -52,7 +52,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
5252
- An [Azure AI hub resource](../how-to/create-azure-ai-resource.md).
5353

5454
> [!IMPORTANT]
55-
> For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS, EastUS2 or Sweden Central regions.
55+
> For Cohere family models, the pay-as-you-go model deployment offering is only available with AI hubs created in EastUS2 or Sweden Central region.
5656
5757
- An [Azure AI project](../how-to/create-projects.md) in Azure AI Studio.
5858
- Azure role-based access controls are used to grant access to operations in Azure AI Studio. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, see [Role-based access control in Azure AI Studio](../concepts/rbac-ai-studio.md).
@@ -71,7 +71,7 @@ To create a deployment:
7171

7272
:::image type="content" source="../media/deploy-monitor/cohere-embed/embed-english-deploy-pay-as-you-go.png" alt-text="A screenshot showing how to deploy a model with the pay-as-you-go option." lightbox="../media/deploy-monitor/cohere-embed/embed-english-deploy-pay-as-you-go.png":::
7373

74-
1. Select the project in which you want to deploy your model. To deploy the model, your project must be in the EastUS, EastUS2 or Sweden Central regions.
74+
1. Select the project in which you want to deploy your model. To deploy the model, your project must be in the EastUS2 or Sweden Central region.
7575
1. In the deployment wizard, select the link to **Azure Marketplace Terms** to learn more about the terms of use.
7676
1. You can also select the **Marketplace offer details** tab to learn about pricing for the selected model.
7777
1. If it is your first time deploying the model in the project, you have to subscribe your project for the particular offering. This step requires that your account has the **Azure AI Developer role** permissions on the Resource Group, as listed in the prerequisites. Each project has its own subscription to the particular Azure Marketplace offering of the model, which allows you to control and monitor spending. Select **Subscribe and Deploy**. Currently you can have only one deployment for each model within a project.
@@ -119,15 +119,15 @@ These models can be consumed using the embed API.
119119
Content-type: application/json
120120
```
121121

122-
#### v1/emebeddings request schema
122+
#### v1/embeddings request schema
123123

124124
Cohere Embed v3 - English and Embed v3 - Multilingual accept the following parameters for a `v1/embeddings` API call:
125125

126126
| Property | Type | Default | Description |
127127
| --- | --- | --- | --- |
128128
|`input` |`array of strings` |Required |An array of strings for the model to embed. Maximum number of texts per call is 96. We recommend reducing the length of each text to be under 512 tokens for optimal quality. |
129129

130-
#### v1/emebeddings response schema
130+
#### v1/embeddings response schema
131131

132132
The response payload is a dictionary with the following fields:
133133

@@ -330,6 +330,16 @@ Response:
330330
| OpenAI SDK (experimental) | [openaisdk.ipynb](https://aka.ms/samples/cohere-embed/openaisdk) |
331331
| LangChain | [langchain.ipynb](https://aka.ms/samples/cohere-embed/langchain) |
332332
| Cohere SDK | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-embed/cohere-python-sdk) |
333+
| LiteLLM SDK | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
334+
335+
##### Retrieval Augmented Generation (RAG) and tool-use samples
336+
**Description** | **Sample Type** | **Sample Notebook**
337+
--|--|--
338+
Create a local Facebook AI Similarity Search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
339+
Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
340+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
341+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
342+
Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
333343

334344
## Cost and quotas
335345

articles/machine-learning/how-to-deploy-models-cohere-command.md

Lines changed: 12 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -73,7 +73,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
7373
- An Azure Machine Learning workspace. If you don't have these, use the steps in the [Quickstart: Create workspace resources](quickstart-create-resources.md) article to create them.
7474

7575
> [!IMPORTANT]
76-
> Pay-as-you-go model deployment offering is only available in workspaces created in EastUS, EastUS2 or Sweden Central regions.
76+
> Pay-as-you-go model deployment offering is only available in workspaces created in EastUS2 or Sweden Central region.
7777
7878
- Azure role-based access controls (Azure RBAC) are used to grant access to operations. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the Resource Group.
7979

@@ -84,7 +84,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
8484
To create a deployment:
8585

8686
1. Go to [Azure Machine Learning studio](https://ml.azure.com/home).
87-
1. Select the workspace in which you want to deploy your models. To use the pay-as-you-go model deployment offering, your workspace must belong to the EastUS, EastUS2 or Sweden Central region.
87+
1. Select the workspace in which you want to deploy your models. To use the pay-as-you-go model deployment offering, your workspace must belong to the EastUS2 or Sweden Central region.
8888
1. Choose the model you want to deploy from the [model catalog](https://ml.azure.com/model/catalog).
8989

9090
Alternatively, you can initiate deployment by going to your workspace and selecting **Endpoints** > **Serverless endpoints** > **Create**.
@@ -795,6 +795,16 @@ Response:
795795
| OpenAI SDK (experimental) | [openaisdk.ipynb](https://aka.ms/samples/cohere-command/openaisdk) |
796796
| LangChain | [langchain.ipynb](https://aka.ms/samples/cohere/langchain) |
797797
| Cohere SDK | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-python-sdk) |
798+
| LiteLLM SDK | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
799+
800+
##### Retrieval Augmented Generation (RAG) and tool use samples
801+
**Description** | **Sample Type** | **Sample Notebook**
802+
--|--|--
803+
Create a local Facebook AI Similarity Search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
804+
Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
805+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
806+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
807+
Command R+ tool/function calling using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
798808

799809
## Cost and quotas
800810

articles/machine-learning/how-to-deploy-models-cohere-embed.md

Lines changed: 14 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
5353
- An Azure Machine Learning workspace. If you don't have these, use the steps in the [Quickstart: Create workspace resources](quickstart-create-resources.md) article to create them.
5454

5555
> [!IMPORTANT]
56-
> Pay-as-you-go model deployment offering is only available in workspaces created in EastUS, EastUS2 or Sweden Central regions.
56+
> Pay-as-you-go model deployment offering is only available in workspaces created in EastUS2 or Sweden Central region.
5757
5858
- Azure role-based access controls (Azure RBAC) are used to grant access to operations. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the Resource Group.
5959

@@ -64,7 +64,7 @@ The previously mentioned Cohere models can be deployed as a service with pay-as-
6464
To create a deployment:
6565

6666
1. Go to [Azure Machine Learning studio](https://ml.azure.com/home).
67-
1. Select the workspace in which you want to deploy your models. To use the pay-as-you-go model deployment offering, your workspace must belong to the EastUS, EastUS2 or Sweden Central region.
67+
1. Select the workspace in which you want to deploy your models. To use the pay-as-you-go model deployment offering, your workspace must belong to the EastUS2 or Sweden Central region.
6868
1. Choose the model you want to deploy from the [model catalog](https://ml.azure.com/model/catalog).
6969

7070
Alternatively, you can initiate deployment by going to your workspace and selecting **Endpoints** > **Serverless endpoints** > **Create**.
@@ -118,15 +118,15 @@ For more information on using the APIs, see the [reference](#embed-api-reference
118118
Content-type: application/json
119119
```
120120

121-
#### v1/emebeddings request schema
121+
#### v1/embeddings request schema
122122

123123
Cohere Embed v3 - English and Embed v3 - Multilingual accept the following parameters for a `v1/embeddings` API call:
124124

125125
| Property | Type | Default | Description |
126126
| --- | --- | --- | --- |
127127
|`input` |`array of strings` |Required |An array of strings for the model to embed. Maximum number of texts per call is 96. We recommend reducing the length of each text to be under 512 tokens for optimal quality. |
128128

129-
#### v1/emebeddings response schema
129+
#### v1/embeddings response schema
130130

131131
The response payload is a dictionary with the following fields:
132132

@@ -329,6 +329,16 @@ Response:
329329
| OpenAI SDK (experimental) | [openaisdk.ipynb](https://aka.ms/samples/cohere-embed/openaisdk) |
330330
| LangChain | [langchain.ipynb](https://aka.ms/samples/cohere-embed/langchain) |
331331
| Cohere SDK | [cohere-sdk.ipynb](https://aka.ms/samples/cohere-embed/cohere-python-sdk) |
332+
| LiteLLM SDK | [litellm.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/litellm.ipynb) |
333+
334+
##### Retrieval Augmented Generation (RAG) and tool use samples
335+
**Description** | **Sample Type** | **Sample Notebook**
336+
--|--|--
337+
Create a local Facebook AI Similarity Search (FAISS) vector index, using Cohere embeddings - Langchain|`langchain`, `langchain_cohere`|[cohere_faiss_langchain_embed.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere_faiss_langchain_embed.ipynb)
338+
Use Cohere Command R/R+ to answer questions from data in local FAISS vector index - Langchain|`langchain`, `langchain_cohere`|[command_faiss_langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_faiss_langchain.ipynb)
339+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Langchain|`langchain`, `langchain_cohere`|[cohere-aisearch-langchain-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-langchain-rag.ipynb)
340+
Use Cohere Command R/R+ to answer questions from data in AI search vector index - Cohere SDK| `cohere`, `azure_search_documents`|[cohere-aisearch-rag.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/cohere-aisearch-rag.ipynb)
341+
Command R+ tool/function calling, using LangChain|`cohere`, `langchain`, `langchain_cohere`|[command_tools-langchain.ipynb](https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/cohere/command_tools-langchain.ipynb)
332342

333343
## Cost and quotas
334344

0 commit comments

Comments
 (0)