fixing blockers

Author: Blackmist

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

@@ -77,9 +77,7 @@ Above mentioned Cohere models can be deployed as a service with pay-as-you-go, a
     > 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.
 
 - An [Azure AI project](../how-to/create-projects.md) in Azure AI Studio.
-- 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).
+- 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).
 
 
 ### Create a new deployment
@@ -129,20 +127,21 @@ These models can be consumed using the chat API.
 
 1. Cohere exposes two routes for inference with the Command R and Command R+ models. `v1/chat/completions` adheres to the Azure AI Generative Messages API schema, and `v1/chat` supports Cohere's native API schema.
 
-    For more information on using the APIs, see the [reference](#chat-api-reference-for-cohere-models-deployed-as-a-service) section.
+For more information on using the APIs, see the [reference](#chat-api-reference-for-cohere-models-deployed-as-a-service) section.
 
 ## Chat API reference for Cohere models deployed as a service
 
-## v1/chat/completions 
-### Request
+### v1/chat/completions
+
+#### Request
 ```
     POST /v1/chat/completions HTTP/1.1
     Host: <DEPLOYMENT_URI>
     Authorization: Bearer <TOKEN>
     Content-type: application/json
 ```
 
-### v1/chat/completions request schema
+#### v1/chat/completions request schema
 
 Cohere Command R and Command R+ accept the following parameters for a `v1/chat/completions` response inference call:
 
@@ -162,15 +161,15 @@ Cohere Command R and Command R+ accept the following parameters for a `v1/chat/c
 `response_format` and `tool_choice` aren't yet supported parameters for the Command R and Command R+ models.
 
 
-#### System or user message
+
 A System or User Message supports the following properties:
 
 | Property | Type | Default | Description |
 | --- | --- | --- | --- |
 | `role` | `enum` | Required | `role=system` or `role=user`. |
 |`content` |`string` |Required |Text input for the model to respond to. |
 
-#### Assistant message
+
 An Assistant Message supports the following properties:
 
 | Property | Type | Default | Description |
@@ -179,7 +178,7 @@ An Assistant Message supports the following properties:
 |`content` |`string` |Required |The contents of the assistant message. |
 |`tool_calls` |`array` |None |The tool calls generated by the model, such as function calls. |
 
-#### Tool message
+
 A Tool Message supports the following properties:
 
 | Property | Type | Default | Description |
@@ -189,7 +188,7 @@ A Tool Message supports the following properties:
 |`tool_call_id` |`string` |None |Tool call that this message is responding to. |
 
 
-### v1/chat/completions response schema
+#### v1/chat/completions response schema
 
 The response payload is a dictionary with the following fields:
 
@@ -219,9 +218,9 @@ The `usage` object is a dictionary with the following fields:
 | `total_tokens` | `integer` | Total tokens. |
 
 
-### Examples
+#### Examples
 
-**Request**
+Request:
 
 ```json
     "messages": [
@@ -250,7 +249,7 @@ The `usage` object is a dictionary with the following fields:
     ]
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -276,8 +275,8 @@ The `usage` object is a dictionary with the following fields:
     }
 ```
 
-## v1/chat 
-## Request
+### v1/chat 
+#### Request
 
 ```
     POST /v1/chat HTTP/1.1
@@ -286,7 +285,7 @@ The `usage` object is a dictionary with the following fields:
     Content-type: application/json
 ```
 
-### v1/chat request schema
+#### v1/chat request schema
 
 Cohere Command R and Command R+ accept the following parameters for a `v1/chat` response inference call:
 
@@ -324,7 +323,7 @@ The `documents` object has the following optional fields:
 |`id`   |`string`   |`None` |Can be supplied to identify the document in the citations. This field isn't passed to the model.   |
 |`_excludes`   |`array of strings`   |`None`| Can be optionally supplied to omit some key-value pairs from being shown to the model. The omitted fields still show up in the citation object. The `_excludes` field isn't passed to the model.   |
 
-### v1/chat response schema
+#### v1/chat response schema
 
 Response fields are fully documented on [Cohere's Chat API reference](https://docs.cohere.com/reference/chat). The response object always contains: 
 
@@ -339,7 +338,7 @@ Response fields are fully documented on [Cohere's Chat API reference](https://do
 
 <br/>
 
-### Documents
+#### Documents
 If `documents` are specified in the request, there are two other fields in the response:
 
 |Key       |Type   |Description   |
@@ -356,7 +355,7 @@ If `documents` are specified in the request, there are two other fields in the r
 |`text`   |`string`   |The text of the citation. For example, a generation of `Hello, world!` with a citation of `world` would have a text value of `world`.   |
 |`document_ids`   |`array of strings`   |Identifiers of documents cited by this section of the generated reply.   |
 
-### Tools
+#### Tools
 If `tools` are specified and invoked by the model, there's another field in the response:
 
 |Key       |Type   |Description   |
@@ -370,7 +369,7 @@ If `tools` are specified and invoked by the model, there's another field in the
 |`name`  |`string`   |Name of the tool to call.   |
 |`parameters`   |`object`   |The name and value of the parameters to use when invoking a tool. |
 
-### Search_queries_only
+#### Search_queries_only
 If `search_queries_only=TRUE` is specified in the request, there are two other fields in the response:
 
 |Key       |Type   |Description   |
@@ -385,12 +384,12 @@ If `search_queries_only=TRUE` is specified in the request, there are two other f
 |`text`  |`string`   |The text of the search query.   |
 |`generation_id`   |`string`   |Unique identifier for the generated search query. Useful for submitting feedback. |
 
-### Examples
+#### Examples
 
-### Chat - Completions
+##### Chat - Completions
 The following example is a sample request call to get chat completions from the Cohere Command model. Use when generating a chat completion.
 
-**Request**
+Request:
 
 ```json
     {
@@ -402,7 +401,7 @@ The following example is a sample request call to get chat completions from the
     }
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -428,11 +427,11 @@ The following example is a sample request call to get chat completions from the
     }
 ```
 
-### Chat - Grounded generation and RAG capabilities
+##### Chat - Grounded generation and RAG capabilities
 
 Command R and Command R+ are trained for RAG via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. We introduce that prompt template via the `documents` parameter. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings. The values can be text or semi-structured.
 
-**Request**
+Request:
 
 ```json
     {
@@ -450,7 +449,7 @@ Command R and Command R+ are trained for RAG via a mixture of supervised fine-tu
     }
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -506,11 +505,11 @@ Command R and Command R+ are trained for RAG via a mixture of supervised fine-tu
     }
 ```
 
-### Chat - Tool Use
+##### Chat - Tool Use
 
 If invoking tools or generating a response based on tool results, use the following parameters. 
 
-**Request**
+Request:
 
 ```json
     {
@@ -569,7 +568,7 @@ If invoking tools or generating a response based on tool results, use the follow
     }
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -634,7 +633,7 @@ If invoking tools or generating a response based on tool results, use the follow
 
 Once you run your function and received tool outputs, you can pass them back to the model to generate a response for the user.
 
-**Request**
+Request:
 
 ```json
     {
@@ -693,7 +692,7 @@ Once you run your function and received tool outputs, you can pass them back to
     }
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -756,11 +755,11 @@ Once you run your function and received tool outputs, you can pass them back to
     }
 ```
 
-### Chat - Search queries
+##### Chat - Search queries
 If you're building a RAG agent, you can also use Cohere's Chat API to get search queries from Command. Specify `search_queries_only=TRUE` in your request.
 
 
-**Request**
+Request:
 
 ```json
     {
@@ -769,7 +768,7 @@ If you're building a RAG agent, you can also use Cohere's Chat API to get search
     }
 ```
 
-**Response**
+Response:
 
 ```json
     {
@@ -791,7 +790,7 @@ If you're building a RAG agent, you can also use Cohere's Chat API to get search
     }
 ```
 
-#### More inference examples
+##### More inference examples
 
 | **Sample Type**       | **Sample Notebook**                             |
 |----------------|----------------------------------------|