- Improvements to CrewAI specialists and Specialists in general
- Addition of reusable components to check or get answers to questions from the full Human Message - HumanAnswerServices
- Re-introduction of EveAIAsset
- Make translation services resistent for situation with and without current_event defined.
- Ensure first question is asked in eveai_chat_client
- Start of version 1.4.0 of TRAICIE_SELECTION_SPECIALIST
- Ensure Traicie Role Definition Specialist complies to latest technical requirements
- Ensure that empty historical messages do not cause a crash in eveai_client
- take into account empty customisation options
- make was not processed in the system dynamic attribute tenant_make
- ensure only relevant makes are shown when creating magic links
- refresh partner info when editing or adding Partner Services$
- Form values shown correct in MessageHistory of Chat client
- Improements to CSS
- Move css en js to assets directory
- Introduce better Personal Contact Form & Professional Contact Form
- Start working on actual Selection Specialist
- Add active field to Specialist model
- Improve Specialists view
- Propagate make for Role Definition Specialist to Selection Specialist (make is defined at the role level)
- Ensure a make with a given name can only be defined once
- Introduce new vanilla-jsoneditor iso older jsoneditor (for viewing a.o. ChatSessions)
- Introduce use of npm to install required javascript libraries
- update Material-kit-pro
- Introduce new top bar to show session defaults, remove old navbar buttons
- Correct Task & Tools editor
- Creation of Traicie Vancancy Definition specialist
- Allow to invoke non-interaction specialists from withing Evie's mgmt interface (eveai_app)
- Improvements to crewai specialized classes
- Introduction to json editor for showing specialists arguments and results in a better way
- Introduction of more complex pagination (adding extra arguments) by adding a global 'get_pagination_html'
- Allow follow-up of ChatSession / Specialist execution
- Improvement in logging of Specialists (but needs to be finished)
- Correct entitlement processing
- Remove get_template functionality from ModelVariables, define it directly with LLM model definition in configuration file.
- Adding Prometheus metrics to the business events
- Ensure asynchronous behaviour of crewai specialists.
- Adapt Business events to working in mixed synchronous / asynchronous contexts
- Extend business events with specialist information
- Started adding a grafana dashboard (TBC)
- Move embedding model settings from tenant to catalog
- BUG: error processing configuration for chunking patterns in HTML_PROCESSOR
- Removed eveai_chat from docker-files and nginx configuration, as it is now obsolete
- BUG: error in Library Operations when creating a new default RAG library
- BUG: Added public type in migration scripts
- Removed SocketIO from all code and requirements.txt
- eveai_chat becomes deprecated and should be replaced with SSE
- Adaptation of STANDARD_RAG specialist
- Base class definition allowing to realise specialists with crewai framework
- Implementation of SPIN_SPECIALIST
- Implementation of test app for testing specialists (test_specialist_client). Also serves as an example for future SSE-based client
- Improvements to startup scripts to better handle and scale multiple connections
- Small improvements to the interaction forms and views
- Caching implementation improved and augmented with additional caches
- Created a base mail template
- Adapt and improve document API to usage of catalogs and processors
- Adapt eveai_sync to new authentication mechanism and usage of catalogs and processors
- Introduction of dynamic Processors
- Introduction of caching system
- Introduction of a better template manager
- Adaptation of ModelVariables to support dynamic Processors / Retrievers / Specialists
- Start adaptation of chat client
- Introduction of retrievers
- Ensuring processing information is collected from Catalog iso Tenant
- Introduction of a generic Form class to enable dynamic fields based on a configuration
- Realisation of Retriever functionality to support dynamic fields
- Allow filtering on Tenant Types & searching for parts of Tenant names
- Implement health checks
- Start Prometheus monitoring (needs to be finalized)
- Refine audio_processor and srt_processor to reduce duplicate code and support for larger files
- Introduce repopack to reason in LLMs about the code
