cohere-ai · fern-support · Aug 12, 2024 · Aug 11, 2024 · Aug 12, 2024 · Aug 12, 2024
@@ -354,6 +354,16 @@ button[class^="Sidebar-link-buttonWrapper"] {
   flex-direction: column;
 }
 
+.fern-header .fern-button-text {
+  font-family: 'CohereText',Segoe UI,Roboto,Oxygen,Ubuntu,Cantarell,Open Sans,Helvetica Neue,sans-serif !important;
+  -webkit-font-smoothing: unset !important;
+}
+
+.fern-sidebar-content .fern-button-text {
+  font-family: 'CohereText',Segoe UI,Roboto,Oxygen,Ubuntu,Cantarell,Open Sans,Helvetica Neue,sans-serif !important;
+  -webkit-font-smoothing: unset !important;
+}
+
 #content {
   padding: 0 32px;
 }
@@ -459,3 +469,11 @@ button[class^="Sidebar-link-buttonWrapper"] {
   float: right !important;
   margin-left: .75rem !important;
 }
+
+.light-bg {
+  background-color: #E8E6DE !important;
+  border-color: #e0e0e0 !important;
+  border-radius: .5rem !important;
+  border-width: 1px !important;
+  padding: 15px !important;
+}
@@ -241,7 +241,7 @@ By passing `return_prompt=True` in any message, you can see which preamble is be
 
 Here's a Python script to make this clearer:
 
-```python python
+```python PYTHON
 import cohere
 
 co = cohere.Client('Your API key')

@@ -7,12 +7,12 @@ createdAt: "Thu May 23 2024 16:53:24 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:53:54 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/2d0a48f-chroma-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/2d0a48f-chroma-logo.png" width="200px" height="auto" class="light-bg" />
 
 Chroma is an open-source vector search engine that's quick to install and start building with using Python or Javascript.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://trychroma.com"
   target="_self"
 >

@@ -11,7 +11,7 @@ createdAt: "Sun Apr 07 2024 20:15:08 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 30 2024 15:56:35 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/17b17dc-elastic-search-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/17b17dc-elastic-search-logo.png" width="200px" height="auto" class="light-bg" />
 
 [Elasticsearch](https://www.elastic.co/search-labs/blog/elasticsearch-cohere-embeddings-support) has all the tools developers need to build next generation search experiences with generative AI, and it supports native integration with [Cohere](https://www.elastic.co/search-labs/blog/elasticsearch-cohere-embeddings-support) through their [inference API](https://www.elastic.co/guide/en/elasticsearch/reference/master/semantic-search-inference.html).
 
@@ -34,7 +34,7 @@ This guide uses a dataset of Wikipedia articles to set up a pipeline for semanti
 To see the full code sample, refer to this [notebook](https://github.com/cohere-ai/notebooks/blob/main/notebooks/Cohere_Elastic_Guide.ipynb).
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://www.elastic.co/search-labs/integrations/cohere"
   target="_self"
 >

@@ -11,7 +11,7 @@ createdAt: "Tue Feb 27 2024 20:06:57 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 17:07:17 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/d82df2c-haystack-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/d82df2c-haystack-logo.png" width="200px" height="auto" class="light-bg" />
 
 [Haystack](https://github.com/deepset-ai/haystack) is an open source LLM framework in Python by [deepset](https://www.deepset.ai/) for building customizable, production-ready LLM applications. You can use Cohere's `/embed`, `/generate`, `/chat`, and `/rerank` models with Haystack.
 

@@ -7,14 +7,14 @@ createdAt: "Thu May 23 2024 16:59:08 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:59:13 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/92a8592-milvus-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/92a8592-milvus-logo.png" width="200px" height="auto" class="light-bg" />
 
 [Milvus](https://milvus.io/) is a highly flexible, reliable, and blazing-fast cloud-native, open-source vector database. It powers embedding similarity search and AI applications and strives to make vector databases accessible to every organization. Milvus is a graduated-stage project of the LF AI & Data Foundation.
 
 The following [guide](https://milvus.io/docs/integrate_with_cohere.md) walks through how to integrate [Cohere embeddings](/docs/embeddings) with Milvus.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://milvus.io/docs/integrate_with_cohere.md"
   target="_self"
 >

@@ -11,14 +11,14 @@ createdAt: "Thu May 23 2024 16:41:27 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 17:06:29 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/f9726ea-mongo-db-logo.svg" width="200px" height="auto" />
+<img src="../../../assets/images/f9726ea-mongo-db-logo.svg" width="200px" height="auto" class="light-bg" />
 
 MongoDB Atlas Vector Search is a fully managed vector search platform from MongoDB. It can be used with Cohere's Embed and Rerank models to easily build semantic search or retrieval-augmented generation (RAG) systems with your data from MongoDB.
 
 The following guide walks through how to integrate Cohere models with MongoDB Atlas Vector Search.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://www.mongodb.com/developer/products/atlas/how-use-cohere-embeddings-rerank-modules-mongodb-atlas/"
   target="_self"
 >

@@ -10,7 +10,7 @@ keywords: "OpenSearch, Cohere"
 createdAt: "Fri Feb 02 2024 15:17:19 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 17:09:12 GMT+0000 (Coordinated Universal Time)"
 ---
-<img src='../../../assets/images/d6bc303-open-search-logo.svg' width="200px" height="auto" />
+<img src='../../../assets/images/d6bc303-open-search-logo.svg' width="200px" height="auto" class="light-bg" />
 
 
 [OpenSearch](https://opensearch.org/platform/search/vector-database.html) is an open-source, distributed search and analytics engine platform that allows users to search, analyze, and visualize large volumes of data in real time. When it comes to text search, OpenSearch is well-known for powering keyword-based (also called lexical) search methods. OpenSearch supports Vector Search and integrates with Cohere through [3rd-Party ML Connectors](https://opensearch.org/docs/latest/ml-commons-plugin/remote-models/connectors/) as well as Amazon Bedrock
@@ -7,12 +7,12 @@ createdAt: "Thu May 23 2024 16:56:18 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:57:06 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/4a1ad91-pinecone-logo.svg" width="200px" height="auto" />
+<img src="../../../assets/images/4a1ad91-pinecone-logo.svg" width="200px" height="auto" class="light-bg" />
 
 The [Pinecone](https://www.pinecone.io/) vector database makes it easy to build high-performance vector search applications. Use Cohere to generate language embeddings, then store them in Pinecone and use them for Semantic Search.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://docs.pinecone.io/docs/cohere"
   target="_self"
 >

@@ -7,14 +7,14 @@ createdAt: "Thu May 23 2024 16:54:52 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:55:09 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/7c00c49-qdrant-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/7c00c49-qdrant-logo.png" width="200px" height="auto" class="light-bg" />
 
 [Qdrant](https://qdrant.tech/) is an open-source vector similarity search engine and vector database. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications.
 
 Qdrant is written in Rust, which makes it fast and reliable even under high load.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://qdrant.tech/documentation/embeddings/cohere/"
   target="_self"
 >

@@ -11,7 +11,7 @@ createdAt: "Mon Feb 26 2024 22:22:44 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 17:06:49 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/5ae9bbd-redis-logo.png" width="200px" height="auto" />
+<img src="../../../assets/images/5ae9bbd-redis-logo.png" width="200px" height="auto" class="light-bg" />
 
 [RedisVL](https://www.redisvl.com/) provides a powerful, dedicated Python client library for using Redis as a Vector Database. This walks through how to integrate [Cohere embeddings](/docs/embeddings) with Redis using a dataset of Wikipedia articles to set up a pipeline for semantic search. It will cover:
 
@@ -23,7 +23,7 @@ updatedAt: "Thu May 23 2024 17:06:49 GMT+0000 (Coordinated Universal Time)"
 To see the full code sample, refer to this [notebook](https://github.com/cohere-ai/notebooks/blob/main/notebooks/Cohere_Redis_Guide.ipynb).
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://www.redisvl.com/user_guide/vectorizers_04.html#cohere"
   target="_self"
 >

@@ -7,12 +7,12 @@ createdAt: "Thu May 23 2024 16:52:12 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:52:39 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/912a0a4-vespa-logo.svg" width="200px" height="auto" />
+<img src="../../../assets/images/912a0a4-vespa-logo.svg" width="200px" height="auto" class="light-bg" />
 
 [Vespa](https://vespa.ai/) is a fully featured search engine and vector database. It supports vector search (ANN), lexical search, and search in structured data, all in the same query. Integrated machine-learned model inference allows you to apply AI to make sense of your data in real time.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://blog.vespa.ai/scaling-large-vector-datasets-with-cohere-binary-embeddings-and-vespa/"
   target="_self"
 >

@@ -7,14 +7,14 @@ createdAt: "Thu May 23 2024 16:55:16 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 16:56:09 GMT+0000 (Coordinated Universal Time)"
 ---
 
-<img src="../../../assets/images/970c76b-weaviate-logo.svg" width="200px" height="auto" />
+<img src="../../../assets/images/970c76b-weaviate-logo.svg" width="200px" height="auto" class="light-bg" />
 
 [Weaviate](https://weaviate.io/) is an open source vector search engine that stores both objects and vectors, allowing for combining vector search with structured filtering.
 
 The `text2vec-cohere` module allows you to use [Cohere embeddings](/docs/embeddings) directly in the Weaviate vector search engine as a vectorization module.
 
 <a
-  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral text-white border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
+  className="rounded-4xl group flex h-fit items-center justify-center whitespace-nowrap transition ease-in-out py-3 px-6 disabled:cursor-not-allowed bg-primary-neutral border border-primary-neutral hover:bg-primary-light hover:text-primary-dark hover:border-primary-light active:bg-primary-neutral active:text-white active:border-primary-neutral disabled:bg-gray-80 disabled:text-gray-30 disabled:border-gray-80 focus:outline-none focus:ring-offset-2 focus:ring focus:ring-black w-100-to-75-to-50 mt-6"
   href="https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-cohere"
   target="_self"
 >