content updates

fern/docs.yml

@@ -123,25 +123,36 @@ navigation:
           - page: Rerank
             path: pages/models/rerank-2.mdx
       - section: Text Generation
-        skip-slug: true
         contents:
           - page: Using the Chat API
             path: pages/text-generation/chat-api.mdx
           - page: Streaming Responses
             path: pages/text-generation/streaming.mdx
+          - page: Structured Generations (JSON)
+            path: pages/text-generation/structured-outputs-json.mdx
           - page: Predictable Outputs
             path: pages/text-generation/predictable-outputs.mdx
           - page: Advanced Generation Parameters
             path: pages/text-generation/advanced-generation-hyperparameters.mdx
           - page: Retrieval Augmented Generation (RAG)
             path: pages/text-generation/retrieval-augmented-generation-rag.mdx
+          - section: RAG Connectors
+            contents:
+              - page: Overview of RAG Connectors
+                path: pages/text-generation/connectors/overview-1.mdx
+              - page: Creating and Deploying a Connector
+                path: pages/text-generation/connectors/creating-and-deploying-a-connector.mdx
+              - page: Managing your Connector
+                path: pages/text-generation/connectors/managing-your-connector.mdx
+              - page: Connector Authentication
+                path: pages/text-generation/connectors/connector-authentication.mdx
+              - page: Connector FAQs
+                path: pages/text-generation/connectors/connector-faqs.mdx
           - section: Tool Use
             path: pages/text-generation/tools.mdx
-            skip-slug: true
             contents:
               - section: Multi-step Tool Use (Agents)
                 path: pages/text-generation/tools/multi-step-tool-use.mdx
-                skip-slug: true
                 contents:
                   - page: Implementing a Multi-Step Agent with Langchain
                     path: pages/text-generation/tools/multi-step-tool-use/implementing-a-multi-step-agent-with-langchain.mdx
@@ -179,23 +190,11 @@ navigation:
                     path: pages/text-generation/prompt-engineering/prompt-library/faster-web-search.mdx
                   - page: Multilingual interpreter
                     path: pages/text-generation/prompt-engineering/prompt-library/multilingual-interpreter.mdx
-          - section: RAG Connectors
-            contents:
-              - page: Overview
-                path: pages/text-generation/connectors/overview-1.mdx
-              - page: Creating and Deploying a Connector
-                path: pages/text-generation/connectors/creating-and-deploying-a-connector.mdx
-              - page: Managing your Connector
-                path: pages/text-generation/connectors/managing-your-connector.mdx
-              - page: Connector Authentication
-                path: pages/text-generation/connectors/connector-authentication.mdx
-              - page: Connector FAQs
-                path: pages/text-generation/connectors/connector-faqs.mdx
           - page: Migrating from the Generate API to the Chat API
             path: pages/text-generation/migrating-from-cogenerate-to-cochat.mdx
       - section: Text Embeddings (Vectors, Search, Retrieval)
         contents:
-          - page: Embeddings
+          - page: Introduction to Embeddings at Cohere
             path: pages/text-embeddings/embeddings.mdx
           - page: Batch Embedding Jobs
             path: pages/text-embeddings/embed-jobs-api.mdx
@@ -205,6 +204,8 @@ navigation:
                 path: pages/text-embeddings/reranking/overview.mdx
               - page: Rerank Best Practices
                 path: pages/text-embeddings/reranking/reranking-best-practices.mdx
+          - page: Text Classification
+            path: pages/text-embeddings/text-classification-1.mdx
       - section: Fine-Tuning
         contents:
           - page: Introduction
@@ -229,7 +230,7 @@ navigation:
             contents:
               - page: Preparing the Classify Fine-tuning data
                 path: pages/fine-tuning/classify-fine-tuning/classify-preparing-the-data.mdx
-              - page: Starting the Classify Fine-Tuning
+              - page: Trains and deploys a fine-tuned model
                 path: pages/fine-tuning/classify-fine-tuning/classify-starting-the-training.mdx
               - page: Understanding the Classify Fine-tuning Results
                 path: pages/fine-tuning/classify-fine-tuning/classify-understanding-the-results.mdx
@@ -269,22 +270,22 @@ navigation:
                 path: pages/integrations/integrations/redis-and-cohere.mdx
               - page: Haystack and Cohere
                 path: pages/integrations/integrations/haystack-and-cohere.mdx
+              - page: Pinecone and Cohere
+                path: pages/integrations/integrations/pinecone-and-cohere.mdx
+              - page: Weaviate and Cohere
+                path: pages/integrations/integrations/weaviate-and-cohere.mdx
               - page: Open Search and Cohere
                 path: pages/integrations/integrations/opensearch-and-cohere.mdx
               - page: Vespa and Cohere
                 path: pages/integrations/integrations/vespa-and-cohere.mdx
-              - page: Chroma and Cohere
-                path: pages/integrations/integrations/chroma-and-cohere.mdx
               - page: Qdrant and Cohere
                 path: pages/integrations/integrations/qdrant-and-cohere.mdx
-              - page: Weaviate and Cohere
-                path: pages/integrations/integrations/weaviate-and-cohere.mdx
-              - page: Pinecone and Cohere
-                path: pages/integrations/integrations/pinecone-and-cohere.mdx
               - page: Milvus and Cohere
                 path: pages/integrations/integrations/milvus-and-cohere.mdx
               - page: Zilliz and Cohere
                 path: pages/integrations/integrations/zilliz-and-cohere.mdx
+              - page: Chroma and Cohere
+                path: pages/integrations/integrations/chroma-and-cohere.mdx
           - section: LangChain
             path: pages/integrations/cohere-and-langchain.mdx
             contents:
@@ -334,9 +335,8 @@ navigation:
                 path: pages/responsible-use/responsible-use/generation-benchmarks.mdx
               - page: Representation Benchmarks
                 path: pages/responsible-use/responsible-use/representation-benchmarks.mdx
-          - page: Security
-            # LINK ELSEWHERE
-            path: pages/responsible-use/security.mdx
+          - link: Security
+            href: https://cohere.ai/security
           - page: Environmental Impact
             path: pages/responsible-use/environmental-impact.mdx
       - section: Cohere for AI
@@ -587,9 +587,6 @@ navigation:
       - page: Sending Feedback
         hidden: true
         path: pages/text-generation/feedback.mdx
-      - page: Structured Generations (JSON)
-        hidden: true
-        path: pages/text-generation/structured-outputs-json.mdx
       - page: Book an appointment
         hidden: true
         path: pages/text-generation/prompt-engineering/prompt-library/book-an-appointment.mdx

fern/openapi/cohere.yaml

@@ -9251,7 +9251,7 @@ components:
           description: |
             [BETA] A JSON schema object that the output will adhere to. There are some restrictions we have on the schema, refer to [our guide](/docs/structured-outputs-json#schema-constraints) for more information.
             Example (required name and age object):
-            ```json
+            ```json JSON
             {
               "type": "object",
               "properties": {

fern/pages/-ARCHIVE-/old-tutorials/semantic-search.mdx

@@ -36,7 +36,7 @@ You can find the code in the <a target="_blank" href="https://github.com/cohere-
 
 ### 1. Download the Dependencies
 
-```python
+```python PYTHON
 # Install Cohere for embeddings, Umap to reduce embeddings to 2 dimensions, 
 # Altair for visualization, Annoy for approximate nearest neighbor search
 pip install cohere umap-learn altair annoy datasets tqdm

fern/pages/cohere-api/about.mdx

@@ -27,7 +27,7 @@ We support SDKs in 4 different languages. Please see the following installation
 python -m pip install cohere --upgrade
 ```
 
-```python
+```python 
 import cohere
 
 co = cohere.Client("<<apiKey>>")
@@ -103,7 +103,7 @@ public class ChatPost {
 go get github.com/cohere-ai/cohere-go/v2
 ```
 
-```go
+```go 
 package main
 
 import (

fern/pages/cohere-api/errors.mdx

@@ -25,3 +25,32 @@ With a non-2xx response code, the response will be an error object in the follow
 ```
 
 Here are code examples for how error handling might look in our SDKs:
+
+<CodeBlocks>
+```python PYTHON
+ try:
+  response = co.generate(
+      model='invalid-model',
+      prompt='sample prompt')
+  except cohere.CohereError as e:
+      print(e.message)
+      print(e.http_status)
+      print(e.headers)
+```
+```javascript JAVASCRIPT
+(async () => {
+  const response = await cohere.generate({model: 'invalid-model'});
+
+  if (response.statusCode !== 200) {
+      console.log(response.body.message);
+  }
+})();
+```
+```go GO
+_, err := co.Generate(generateOptions)
+if err != nil {
+  fmt.Println(err)
+  return
+}
+```
+</CodeBlocks>

fern/pages/cookbooks/agent-api-calls.mdx

@@ -40,14 +40,14 @@ With this approach, we bring together the best of two worlds: the ability of LLM
 
 # Step 1: Setup [#sec_step1]
 
-```python
+```python PYTHON
 # Uncomment if you need to install the following packages
 # !pip install cohere
 # !pip install python-dotenv
 # !pip install pandas
 ```
 
-```python
+```python PYTHON
 import os
 import json
 import re
@@ -60,7 +60,7 @@ from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_core.tools import tool
 ```
 
-```python
+```python PYTHON
 # load the cohere api key
 os.environ["COHERE_API_KEY"] = getpass.getpass()
 ```
@@ -70,7 +70,7 @@ os.environ["COHERE_API_KEY"] = getpass.getpass()
 Here we create a tool which implements the deterministic function to extract alphanumeric strings
 from the user's query and match them to the right parameter.
 
-```python
+```python PYTHON
 @tool
 def regex_extractor(user_query: str) -> dict:
     """Function which, given the query from the user, returns a dictionary parameter:value."""
@@ -94,7 +94,7 @@ regex_extractor.args_schema = extract_code_v1productssearch
 tools=[regex_extractor]
 ```
 
-```python
+```python PYTHON
 # Let's define the preamble for the Agent.
 # The preamble includes info about:
 # - the tool the Agent has access to
@@ -122,7 +122,7 @@ Search products sport | Search products dress and jumpsuit | [{'taxonomies': ['S
 """
 ```
 
-```python
+```python PYTHON
 # Define the prompt
 prompt = ChatPromptTemplate.from_template("{input}")
 # Define the agent
@@ -140,7 +140,7 @@ agent_executor = AgentExecutor(agent=agent,
                     )
 ```
 
-```python
+```python PYTHON
 # finally, let's write a function to convert the Agents output to a json
 def convert_to_json(string: str) -> json:
     return json.loads(
@@ -155,7 +155,7 @@ def convert_to_json(string: str) -> json:
 
 Let's now test the Agent we just defined!
 
-```python
+```python PYTHON
 query_1 = "Look for urn:75f2b737-06dd-4399-9206-a6c11b65138e, GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE"
 response_1 = agent_executor.invoke(
             {
@@ -172,7 +172,7 @@ I will use the regex_extractor tool to extract the codes from the user query.
 {'tool_name': 'regex_extractor', 'parameters': {'user_query': 'Look for urn:75f2b737-06dd-4399-9206-a6c11b65138e, GLCMS004AGTCAMIS; 0000234GLCMS0100ANORAKCAA, GLCHL000CGUCHALE'}}
 {'nmgs': ['0000234GLCMS0100ANORAKCAA'], 'objref': ['GLCMS004AGTCAMIS', 'GLCHL000CGUCHALE'], 'urn': ['urn:75f2b737-06dd-4399-9206-a6c11b65138e']}Relevant Documents: 0
 Cited Documents: 0
-Answer: ```json
+Answer: ```json JSON
 [
     {
         "urn": ["urn:75f2b737-06dd-4399-9206-a6c11b65138e"],
@@ -181,7 +181,7 @@ Answer: ```json
     }
 ]
 ```
-Grounded answer: ```json
+Grounded answer: ```json JSON
   [
     {
         "urn": [<co: 0>"urn:75f2b737-06dd-4399-9206-a6c11b65138e</co: 0>"],
@@ -197,7 +197,7 @@ Grounded answer: ```json
 In the reasoning chain above, we can see that the Agent uses the tool we provided it to extract the strings in the query.
 The output of the tool is then used to generate the request.
 
-```python
+```python PYTHON
 # let's have a look at the final output
 convert_to_json(response_1['output'])
 ```
@@ -210,7 +210,7 @@ convert_to_json(response_1['output'])
 
 As mentioned above, the Agent can use the tool when specific alphanumeric patterns have to be extracted from the query; however, it can also generate the output based on its semantic understanding of the query. For example:
 
-```python
+```python PYTHON
 query_2 = "I need tennis products"
 
 response_2 = agent_executor.invoke(
@@ -228,7 +228,7 @@ I will use the regex_extractor tool to extract the relevant information from the
 {'tool_name': 'regex_extractor', 'parameters': {'user_query': 'I need tennis products'}}
 {}Relevant Documents: None
 Cited Documents: None
-Answer: ```json
+Answer: ```json JSON
 [
     {
         "taxonomies": [
@@ -237,7 +237,7 @@ Answer: ```json
     }
 ]
 ```
-Grounded answer: ```json
+Grounded answer: ```json JSON
   [
   {
   "taxonomies": [
@@ -252,7 +252,7 @@ Grounded answer: ```json
 
 The Agent runs the tool to check if any target string was in the query, then it generated the request body based on its understanding.
 
-```python
+```python PYTHON
 convert_to_json(response_2['output'])
 ```
 
@@ -262,7 +262,7 @@ convert_to_json(response_2['output'])
 
 Finally, the two paths to generation - deterministic and semantic - can be applied in parallel by the Agent, as shown below:
 
-```python
+```python PYTHON
 query_3 = "Look for GLBRL0000GACHALE, nmg 0000234GLCZD0000GUREDTOAA and car products"
 
 response_3 = agent_executor.invoke(
@@ -280,7 +280,7 @@ I will use the regex_extractor tool to extract the codes from the user query. Th
 {'tool_name': 'regex_extractor', 'parameters': {'user_query': 'Look for GLBRL0000GACHALE, nmg 0000234GLCZD0000GUREDTOAA and car products'}}
 {'nmgs': ['0000234GLCZD0000GUREDTOAA'], 'objref': ['GLBRL0000GACHALE']}Relevant Documents: 0
 Cited Documents: 0
-Answer: ```json
+Answer: ```json JSON
 [
     {
         "objref": ["GLBRL0000GACHALE"],
@@ -291,7 +291,7 @@ Answer: ```json
     }
 ]
 ```
-Grounded answer: ```json
+Grounded answer: ```json JSON
   [
     {
         "objref": [<co: 0>"GLBRL0000GACHALE</co: 0>"],
@@ -306,7 +306,7 @@ Grounded answer: ```json
 > Finished chain.
 ````
 
-```python
+```python PYTHON
 convert_to_json(response_3['output'])
 ```