Refresh get started section

fern/pages/get-started/installation.mdx

@@ -0,0 +1,72 @@
+---
+title: Installation
+slug: /docs/get-started-installation
+
+description: "A guide for installing the Cohere SDK, supported in 4 different languages – Python, TypeScript, Java, and Go."
+image: "../../assets/images/f1cc130-cohere_meta_image.jpg"  
+keywords: "Cohere, Cohere SDK, API v1"
+---
+
+## Platform options
+
+To be able to use Cohere’s models, first choose the platform where you want to access the model from. Cohere's models are available on the following platforms:
+
+| Platform        | Description                                                                 | Setup Guide                                                                 |
+|-----------------|-----------------------------------------------------------------------------|----------------------------------------------------------------------------|
+| Cohere Platform | The fastest way to start using Cohere’s models. Hosted on Cohere infrastructure and available on our public SaaS platform. | [Sign up](https://dashboard.cohere.com/welcome/register) and get an [API key](https://dashboard.cohere.com/api-keys) (trial key available) |
+| Private Deployments | For enterprises looking to deploy the Cohere stack privately on the cloud or on-prem. | [Setup guide](https://docs.cohere.com/docs/single-container-on-private-clouds) |
+| Cloud deployments | Managed services from cloud providers that enable access to Cohere's models. | • [Amazon Bedrock](https://docs.cohere.com/docs/amazon-bedrock#prerequisites)<br/>• [Amazon SageMaker](https://docs.cohere.com/docs/amazon-sagemaker-setup-guide#prerequisites)<br/>• [Azure AI Foundry](https://docs.cohere.com/docs/cohere-on-microsoft-azure#prerequisites)<br/>• [Oracle OCI](https://docs.cohere.com/docs/oracle-cloud-infrastructure-oci) |
+## Model usage
+
+You can then use the models via these options:
+
+- [SDK](https://docs.cohere.com/v1/reference/about#sdks). We support the following SDKs:
+    - [Python](https://github.com/cohere-ai/cohere-python)
+    - [TypeScript](https://github.com/cohere-ai/cohere-typescript)
+    - [Java](https://github.com/cohere-ai/cohere-java)
+    - [Go](https://github.com/cohere-ai/cohere-go)
+- [CLI tool](https://docs.cohere.com/v1/reference/command)
+- [Playground](https://docs.cohere.com/v1/docs/playground-overview)
+
+
+## Installation
+
+To install the Cohere SDK, choose from the following 4 languages:
+
+<Tabs>
+<Tab title="Python">
+
+```bash
+pip install -U cohere
+```
+[Source](https://github.com/cohere-ai/cohere-python)
+</Tab>
+
+<Tab title="TypeScript">
+
+```bash
+npm i -s cohere-ai
+```
+[Source](https://github.com/cohere-ai/cohere-typescript)
+
+</Tab>
+
+<Tab title="Java">
+
+```gradle
+implementation 'com.cohere:cohere-java:1.x.x'
+```
+[Source](https://github.com/cohere-ai/cohere-java)
+
+</Tab>
+
+<Tab title="Go">
+
+```bash
+go get github.com/cohere-ai/cohere-go/v2
+```
+
+[Source](https://github.com/cohere-ai/cohere-go)
+
+</Tab>
+</Tabs>

fern/pages/get-started/playground-overview.mdx

@@ -11,26 +11,22 @@ updatedAt: 'Wed May 29 2024 18:55:51 GMT+0000 (Coordinated Universal Time)'
 ---
 ## What is the Playground?
 
-The [Developer Playground](https://dashboard.cohere.com/playground) is a visual interface for users to try out our APIs and iterate on prompts without writing a single line of code. Use the Playground to test your use cases and when you're ready to start building, simply click `View Code` to add Cohere's functionality to your application.
+The [Cohere Playground](https://dashboard.cohere.com/playground) is a visual interface for users to try out our APIs and iterate on prompts without writing a single line of code. Use the Playground to test your use cases and when you're ready to start building, simply click `CODE` to get the code version that you can add to your application.
 
 ## Using the Playground
 
 ### Chat
 
-The Chat API provides a natural language response to a prompt.  You can use the Chat Playground to generate text, answer a question or create content.  There is a default preamble, which you can change in the playground. The preamble and the messages are sent to the model to generate a response. 
+The [Chat endpoint](/reference/chat)  provides a natural language response to a prompt.  You can use the Chat Playground to generate text, answer a question or create content.  There is a default preamble, which you can change in the playground. The preamble and the messages are sent to the model to generate a response.
 
 - To write inputs that produce the best results for your use case, read our [Prompt Engineering](/docs/prompt-engineering) guide.
 - Try tinkering with different [temperature](/docs/temperature)  to get different outputs.
-- You can also toggle raw prompting on the playground.  If raw prompting is turned off, the user's input will be sent to the playground without any preprocessing.
 
 <img src='../../assets/images/67f4530-Playground_-_Chat.png' />
 
-
-
-
 ### Embed
 
-Using [Embed](/reference/embed) in the Playground enables users to assign numerical representations to strings and visualize comparative meaning on a 2-dimensional plane. Phrases similar in meaning should ideally be closer together on this visualization. Add a couple of your own phrases and see if the Playground visualization feels accurate to you.
+The [Embed endpoint](/reference/embed) enables users to assign numerical representations to strings and visualize comparative meaning on a 2-dimensional plane. Phrases similar in meaning should ideally be closer together on this visualization. Add a couple of your own phrases and see if the Playground visualization feels accurate to you.
 
 <img src='../../assets/images/4e876d8-Playground_-_Embed.png' />
 
@@ -39,7 +35,7 @@ Cohere [embeddings](/docs/embeddings) can be used to train a semantic classifier
 
 ### Classify
 
-The Cohere [Classify](/reference/classify) endpoint enables users to create a classifier from a few labeled examples.
+The [Classify endpoint](/reference/classify) enables users to create a classifier from a few labeled examples.
 
 <img src='../../assets/images/8af00ab-Playground_-_Classify.png' />
 

fern/pages/get-started/quickstart/rag-quickstart.mdx

@@ -0,0 +1,209 @@
+---
+title: Retrieval Augmented Generation (RAG)
+slug: /docs/rag-quickstart
+
+description: "A quickstart guide for performing retrieval augmented generation (RAG) with Cohere's Command models (v1 API)."
+image: "../../../assets/images/f1cc130-cohere_meta_image.jpg"  
+keywords: "Cohere, RAG, retrieval augmented generation, chatbot, command models"
+---
+
+Retrieval Augmented Generation (RAG) enables an LLM to ground its responses on external documents, thus improving the accuracy of its responses and minimizing hallucinations.
+
+The Chat endpoint comes with built-in RAG capabilities such as document grounding and citation generation.  
+
+This quickstart guide shows you how to perform RAG with the Chat endpoint.
+
+<Steps>
+### Setup
+First, install the Cohere Python SDK with the following command.
+
+```bash
+pip install -U cohere
+```
+
+Next, import the library and create a client.
+
+<Tabs>
+<Tab title="Cohere Platform">
+
+```python PYTHON
+import cohere
+
+co = cohere.Client("COHERE_API_KEY") # Get your free API key here: https://dashboard.cohere.com/api-keys
+```
+
+</Tab>
+<Tab title="Private Deployment">
+
+```python PYTHON
+import cohere
+
+co = cohere.Client(
+    api_key="", # Leave this blank
+    base_url="<YOUR_DEPLOYMENT_URL>"
+)
+```
+
+</Tab>
+
+<Tab title="Bedrock">
+
+```python PYTHON
+import cohere
+
+co = cohere.BedrockClient(
+    aws_region="AWS_REGION",
+    aws_access_key="AWS_ACCESS_KEY_ID",
+    aws_secret_key="AWS_SECRET_ACCESS_KEY",
+    aws_session_token="AWS_SESSION_TOKEN",
+)
+
+# Get the model name: https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html
+```
+</Tab>
+
+<Tab title="SageMaker">
+
+```python PYTHON
+import cohere
+
+co = cohere.SagemakerClient(
+    aws_region="AWS_REGION",
+    aws_access_key="AWS_ACCESS_KEY_ID",
+    aws_secret_key="AWS_SECRET_ACCESS_KEY",
+    aws_session_token="AWS_SESSION_TOKEN",
+)
+```
+</Tab>
+
+<Tab title="Azure AI">
+
+```python PYTHON
+import cohere
+
+co = cohere.Client(
+    api_key="AZURE_API_KEY",
+    base_url="AZURE_ENDPOINT",
+)
+```
+</Tab>
+
+</Tabs>
+
+### Documents
+
+First, define the documents that will passed as the context for RAG. These documents are typically retrieved from sources such as vector databases via semantic search, or any system that can retrieve unstructured data given a user query.
+
+Each document can take any number of fields e.g. `title`, `url`, `text`, etc.
+
+```python PYTHON
+documents = [
+    {
+        "text": "Reimbursing Travel Expenses: Easily manage your travel expenses by submitting them through our finance tool. Approvals are prompt and straightforward."
+    },
+    {
+        "text": "Health and Wellness Benefits: We care about your well-being and offer gym memberships, on-site yoga classes, and comprehensive health insurance."
+    },
+]
+```
+### Response Generation
+
+Next, call the Chat API by passing the documents in the `documents` parameter. This tells the model to run in RAG-mode and use these documents as the context in its response.
+
+<Tabs>
+<Tab title="Cohere Platform">
+```python PYTHON
+message = "Are there fitness-related benefits?"
+
+response = co.chat(
+    model="command-r-plus-08-2024",
+    message=message,
+    documents=documents
+)
+
+print(response.text)
+```
+</Tab>
+
+<Tab title="Private Deployment">
+```python PYTHON
+message = "Are there fitness-related benefits?"
+
+response = co.chat(
+    model="command-r-plus-08-2024",
+    message=message,
+    documents=documents
+)
+
+print(response.text)
+```
+</Tab>
+
+<Tab title="Bedrock">
+```python PYTHON
+message = "Are there fitness-related benefits?"
+
+response = co.chat(
+    model="YOUR_MODEL_NAME",
+    message=message,
+    documents=documents
+)
+
+print(response.text)
+```
+</Tab>
+
+<Tab title="SageMaker">
+```python PYTHON
+message = "Are there fitness-related benefits?"
+
+response = co.chat(
+    model="YOUR_ENDPOINT_NAME",
+    message=message,
+    documents=documents
+)
+
+print(response.text)
+```
+</Tab>
+
+<Tab title="Azure AI">
+```python PYTHON
+message = "Are there fitness-related benefits?"
+
+response = co.chat(
+    message=message,
+    documents=documents
+)
+
+print(response.text)
+```
+</Tab>
+</Tabs>
+
+```mdx wordWrap
+Yes, we offer gym memberships, on-site yoga classes, and comprehensive health insurance.
+
+```
+
+### Citation Generation
+
+The response object contains a `citations` field, which contains specific text spans from the documents on which the response is grounded.
+
+```python PYTHON
+if response.citations:
+    for citation in response.citations:
+        print(citation, "\n")
+```
+
+```mdx wordWrap
+start=14 end=88 text='gym memberships, on-site yoga classes, and comprehensive health insurance.' document_ids=['doc_1'] 
+
+```
+
+</Steps>
+
+## Further Resources
+- [Chat endpoint API reference](https://docs.cohere.com/v1/reference/chat)
+- [Documentation on RAG](https://docs.cohere.com/v1/docs/retrieval-augmented-generation-rag)
+- [LLM University module on RAG](https://cohere.com/llmu#rag)