feat(docs): add info for v027 of AI Engine

pages/concepts/ai-engine/ai-engine-personalities.mdx

@@ -25,7 +25,8 @@ The following AI Engine personality types are available for users: **Talkative V
  - Version **v0.23** introduced enhanced session-level memory, tracking credit usage, parallel execution in sync worker, and session termination control within the NextGeneration personality.
  - Version **v0.24** deployed **NextGeneration personality as the default**, and thus replacing **Talkative** personality type. This version focuses on significant stability and scalability improvements, supporting millions of agents. This version also introduced immediate agent registration, enhanced message reliability, UI enhancements, privacy compliance, robust timeout and monitoring systems, infrastructure upgrades, and database and deployment improvements.
  - With version **v0.25** the Talkative personality (previously associated with AI Engine V1) started to refer to AI Engine V2 (previously available under the Next Generation personality). To preserve AI Engine V1, a new **Legacy personality** had been introduced, with a scheduled removal date of September 13, 2024. With this release the following features were introduced: _Functions Metadata_ (location settings can now be assigned to functions), _Permission System_ (users can now share private function groups with others via email), _Dialogue Execution Improvements_, _Permission Sharing in Python SDK_ (added functionality to the Python SDK) and _Next Generation Personality (i.e., This was a new iteration of the Next Generation personality, now called Talkative) supports location filtering on functions with location metadata based on objectives_.
- - Version **v0.26** introduces significant enhancements to the AI Engine; The release includes a Workflows Beta, allowing two workflow creation methods: the first via POST requests to `/v1beta1/engine/workflows/SESSION_ID/` with payloads specifying workflow names and descriptions, where `SESSION_ID` is replaced by a session ID from DeltaV; the second allows posting workflow graphs, primarily for the Agentverse editor. To execute workflows, users append `?workflowId=YOUR-WORKFLOW-ID` to the DeltaV homepage URL. Additionally, starting workflows via API now requires POST requests to `/v1beta1/engine/chat/workflow-session/` with the workflow ID in the payload. Additionally, new **Elasticsearch-based Search APIs** were introduced for querying agents and functions, integrated directly into the Agentverse UI. A global **Agent Event Consumer** was added, processing events like agent creation, startup, and interactions to build an indexed database of agents. Furthermore, the **Function Description API** was implemented, generating detailed function descriptions based on an agent’s model and name within the function creation flow. Other technical improvements include **context validation**, **GPT-4o-mini** for enhanced recommendation accuracy within the NextGeneration personality, and **Prometheus metrics** for in-depth performance monitoring and observability of the system's health.
+ - Version **v0.26** introduced significant enhancements to the AI Engine; The release included a Workflows Beta, allowing two workflow creation methods: the first via POST requests to `/v1beta1/engine/workflows/SESSION_ID/` with payloads specifying workflow names and descriptions, where `SESSION_ID` is replaced by a session ID from DeltaV; the second allows posting workflow graphs, primarily for the Agentverse editor. To execute workflows, users append `?workflowId=YOUR-WORKFLOW-ID` to the DeltaV homepage URL. Additionally, starting workflows via API now requires POST requests to `/v1beta1/engine/chat/workflow-session/` with the workflow ID in the payload. Additionally, new **Elasticsearch-based Search APIs** were introduced for querying agents and functions, integrated directly into the Agentverse UI. A global **Agent Event Consumer** was added, processing events like agent creation, startup, and interactions to build an indexed database of agents. Furthermore, the **Function Description API** was implemented, generating detailed function descriptions based on an agent's model and name within the function creation flow. Other technical improvements include **context validation**, **GPT-4o-mini** for enhanced recommendation accuracy within the NextGeneration personality, and **Prometheus metrics** for in-depth performance monitoring and observability of the system's health.
+ - Version **v0.27** introduces further improvements to the AI Engine. The Workflow Executor v2 now incorporates the latest advancements in Large Language Models (LLMs), allowing for a more refined context builder in workflows. Additionally, the consumption of events from Agentverse has been fully completed, and now enables full support for the explore page search feature. The Search API has also been extended with improved capabilities, particularly by adding relevancy ordering to refine search results. LLM-driven improvements have been implemented allowing for enhanced descriptions of functions through an API endpoint designed for Agentverse. Similarly, function parameter descriptions have been improved using LLMs, with the updated descriptions now available via another API endpoint for Agentverse. Furthermore, the release brings Workflow API enhancements, introducing functionalities to update and delete workflows. Also, several bug fixes have been introduced to improve system performance and ensuring a smoother and more efficient user experience.
 
 ## Exploring the Feature Set of AI Engine Personalities