First round of fixes based on user feedback (#290)

* A batch of changes. * Changing some rerank language. * More titles. * Updating queries. --------- Signed-off-by: trentfowlercohere <[email protected]> Co-authored-by: Trent Fowler <[email protected]>
cohere-ai · Dec 12, 2024 · 4d1a9d5 · 4d1a9d5
1 parent d8dff78
commit 4d1a9d5
Show file tree

Hide file tree

Showing 7 changed files with 12 additions and 12 deletions.
diff --git a/fern/pages/models/cohere-embed.mdx b/fern/pages/models/cohere-embed.mdx
@@ -1,5 +1,5 @@
 ---
-title: Embed Model
+title: Cohere's Embed Models (Details and Application)
 slug: docs/cohere-embed
 hidden: false
 description: >-

diff --git a/fern/pages/models/models.mdx b/fern/pages/models/models.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Models Overview"
+title: An Overview of Cohere's Models
 slug: "docs/models"
 
 hidden: false

diff --git a/fern/pages/models/rerank-2.mdx b/fern/pages/models/rerank-2.mdx
@@ -1,5 +1,5 @@
 ---
-title: "Rerank Model"
+title: Cohere's Rerank Model (Details and Application)
 slug: "docs/rerank-2"
 
 hidden: false

diff --git a/fern/pages/text-embeddings/reranking/reranking-best-practices.mdx b/fern/pages/text-embeddings/reranking/reranking-best-practices.mdx
@@ -41,7 +41,7 @@ If `Number of documents * max_chunks_per_doc` exceeds `10,000`, the endpoint wil
 
 ## Queries
 
-Our `rerank-v3.5` and `rerankv-3.0` models are trained with a context length of 4096 tokens. The model takes into account both the input from the query and document. If your query is larger than 2048 tokens, it will be truncated to the first 2048 tokens.
+Our `rerank-v3.5` and `rerank-v3.0` models are trained with a context length of 4096 tokens. The model takes both the _query_ and the _document_ into account when calculating against this limit, and the query can account for up to half of the full context length. If your query is larger than 2048 tokens, in other words, it will be truncated to the first 2048 tokens (leaving the other 2048 for the document(s)).
 
 ## Semi-Structured Data Support
 

diff --git a/fern/pages/text-generation/prompt-engineering/prompt-truncation.mdx b/fern/pages/text-generation/prompt-engineering/prompt-truncation.mdx
@@ -10,8 +10,8 @@ keywords: "prompt engineering, generative AI prompts"
 createdAt: "Thu Feb 29 2024 18:14:26 GMT+0000 (Coordinated Universal Time)"
 updatedAt: "Thu May 23 2024 20:21:50 GMT+0000 (Coordinated Universal Time)"
 ---
-LLMs come with limitations; specifically, they can only handle so much text as input. This means that you will often need to figure out which document sections and chat history elements to keep, and which ones to omit.
+LLMs come with limitations; specifically, they can only handle so much text as input. This means that you will often need to figure out which part of a document or chat history to keep, and which ones to omit.
 
-To make this easier, the Chat API comes with a helpful `prompt_truncation` parameter. When `prompt_truncation` is set to `AUTO`, the API will automatically break up the documents into smaller chunks, rerank the chunks and drop the minimum required number of the least relevant documents in order to stay within the model's context length limit.
+To make this easier, the Chat API comes with a helpful `prompt_truncation` parameter. When `prompt_truncation` is set to `AUTO`, the API will automatically break up the documents into smaller chunks, rerank those chunks according to how relevant they are, and then start dropping the least relevant documents until the text fits within the model's context length limit.
 
 **Note:** The last few messages in the chat history will never be truncated or dropped. The RAG API will throw a 400 `Too Many Tokens` error if it can't fit those messages along with a single document under the context limit.
diff --git a/fern/v1.yml b/fern/v1.yml
@@ -41,7 +41,7 @@ navigation:
             path: pages/get-started/contribute.mdx
       - section: Models
         contents:
-          - page: Models Overview
+          - page: An Overview of Cohere's Models
             path: pages/models/models.mdx
           - section: Command
             contents:
@@ -51,9 +51,9 @@ navigation:
                 path: pages/models/the-command-family-of-models/command-r.mdx
               - page: Command and Command Light
                 path: pages/models/the-command-family-of-models/command-beta.mdx
-          - page: Embed
+          - page: Cohere's Embed Models (Details and Application)
             path: pages/models/cohere-embed.mdx
-          - page: Rerank
+          - page: Cohere's Rerank Model (Details and Application)
             path: pages/models/rerank-2.mdx
           - page: Aya
             path: pages/models/aya.mdx

diff --git a/fern/v2.yml b/fern/v2.yml
@@ -41,7 +41,7 @@ navigation:
             path: pages/get-started/contribute.mdx
       - section: Models
         contents:
-          - page: Models Overview
+          - page: An Overview of Cohere's Models
             path: pages/models/models.mdx
           - section: Command
             contents:
@@ -51,9 +51,9 @@ navigation:
                 path: pages/v2/models/the-command-family-of-models/command-r.mdx
               - page: Command and Command Light
                 path: pages/v2/models/the-command-family-of-models/command-beta.mdx
-          - page: Embed
+          - page: Cohere's Embed Models (Details and Application)
             path: pages/models/cohere-embed.mdx
-          - page: Rerank
+          - page: Cohere's Rerank Model (Details and Application)
             path: pages/models/rerank-2.mdx
           - page: Aya
             path: pages/models/aya.mdx