OntoRAG: Ontology-Based Knowledge Extraction (#523): New processor kg-extract-ontology that uses ontology objects from config to guide triple extraction. Includes entity contexts and integrates with ontology extractor from workbench.MCP Authentication (#557): Added MCP auth token header support for the simple authentication case.Dynamic Embeddings Model Selection (#556): Embeddings model can now be selected dynamically rather than being fixed. Collection deletion batch error (#559): Fixed batch error during collection deletion by reducing batch size.Fix hard-coded vector size (#555): Vector store now lazy-creates collections with different collections for different dimension lengths.Fix AgentStep schema error (#557): Agent step argument values are now converted to strings to fix schema errors.Remove unnecessary OpenAI parameters (#561): Removed parameters from OpenAI invocation that were causing compatibility issues with OpenAI-compatible services. Python 3.13 Support (#553): Upgraded to Python 3.13, switched from cassandra-driver to scylla-driver (cassandra-driver doesn’t work with Python 3.13).Vector Store Lifecycle Tech Spec (#555): Added technical specification for vector store lifecycle.OntoRAG Tech Spec (#523, #558): Added technical specification for ontology-based knowledge extraction and query. Ontology extraction tests (#560): Added tests for ontology extraction.Dynamic embeddings tests (#556): Added tests for dynamic embeddings model selection.MCP auth and agent step parsing tests (#557): Added tests for MCP authentication and agent step parsing.OpenAI invocation tests (#561): Updated tests for OpenAI parameter changes. Flow Configurable Parameters (#526, #530, #531, #532, #533, #541): Major enhancements to flow parameter system: Flow configurable parameters with dynamic settings LLM dynamic settings using llm-model and llm-rag-model parameters Temperature parameter support for all LLMs Flow creation uses parameter defaults in API and CLI Advanced parameter mode with controlled-by relationships New CLI tools: tg-show-parameter-types Dynamic chunking parameters Structured Data Diagnosis Service (#518, #519): New structured data diagnosis service plumbed into API gateway Added XML, JSON, CSV detection capabilities Type detector with schema selection Enhanced Collection Management (#520, #522, #542, #544): Collection metadata management and deletion capabilities Librarian services integrated with collection manager Collection tracking across all processors Explicit collection creation/deletion (removed implicit creation) Fixed collection management synchronization issues User/Collection Isolation (#509, #510): Neo4j user/collection separation Memgraph user/collection processing Cassandra Performance (#521): Refactored Cassandra knowledge graph for single table Multi-table implementation for performance enhancement Added Cassandra collection table GraphRAG Optimizations (#527): Implemented GraphRAG optimizations with updated testsVector Store Enhancements (#512): Vector stores now create collections on queryBuild System (#515): Parallel container buildsLogging (#528, #543): Reduced excessive request/response logging and log spam Collection Management (#544): Fixed collection management synchronization problemsMetrics (#539, #540): Fixed label names and label issues in metricsWebSocket (#517): Fixed async websocket closure handlingCLI (#529): Fixed CLI typoTests (#534, #535): Fixed failing tests and improved LLM parameter test coverageObject Writer (#544): Fixed object writer management issuesMilvus (#544): Updated Milvus to use ANN correctly Gateway (#514): Return empty embeddings list as empty list through gateway.Parameters : Changed parameters to parameter-types for consistency Structured Data Enhancements (#492, #493, #496, #498, #500): Major improvements to structured data handling: NLP query to GraphQL service for natural language database queries Structured query tool integration with agent framework Enhanced structured query support and object batching Structured data loader CLI with auto mode functionality Object import capabilities with batch processing Collection Management (#503, #511): Extended use of user + collection fields throughout the system Stores automatically create collections on query Tool Groups (#484): Added tool grouping functionality for better organization GraphQL Enhancements (#486, #489): Added GraphQL table query support Removed redundant GraphQL collection parameter Cassandra Configuration Standardization (#483, #488, #490): Made Cassandra options (user, password, host) consistent across all utilities Consolidated Cassandra configuration for better consistency Refactored Cassandra operations to use common helper functions API Improvements (#513): Return empty embeddings list as empty list through gateway Vector Store Fixes (#507): Fixed Milvus vector store integration issuesDocument Processing (#506): Fixed document RAG processing issuesMonitoring (#502): Fixed Prometheus incorrect metric namesAPI Consistency (#481): Fixed trustgraph-base chunks/documents confusion in the APISystem Integration (#494): Resolved various system integration issuesImport/Export (#476): Fixed graceful shutdown for import/export operationsKnowledge Loading (#472): Use collection field from request when loading knowledge core MCP Tool Arguments Support (#462): Added support for Model Context Protocol (MCP) tool arguments, including agent support and additional testsAnthropic Support for VertexAI (#458): Added Anthropic model support for Google Vertex AI platformKnowledge Load Utility CLI (#456): New command-line utility for loading knowledge into the systemStructured Data MVP (#452): Initial implementation of structured data handling with: New schemas and architecture principles Object extractor functionality Cassandra object storage support Knowledge Extraction via Agent Framework (#439): Implemented KG extraction agent (kg-extract-agent) Using ReAct framework (agent-manager-react) Refactored ReAct manager to use traditional ReAct messages Agent Tool Coverage (#460): Increased ReAct tool coverage with multi-step tool invocation and reasoning testsSchema Structure Refactor (#451): Major refactoring of schema structure for better organizationLogging Strategy (#444): Implemented comprehensive logging strategy, converting all print() statements to proper logging invocationsBuild System Modernization (#440): Migrated from setup.py to pyproject.toml for modern package infrastructure Agent Tool Resilience (#461): Fixed incorrect tool initialization in agent service Made Action parsing more resilient by handling quotation marks Missing Anthropic Import (#459): Fixed missing import for Anthropic functionalityToken Chunker API (#454, #455): Fixed broken API invocation in token chunkerLibrarian Collection Validation (#453): Added validation for librarian collectionsMistral OCR (#448, #450): Fixed Mistral OCR to use current API Corrected Mistral OCR identifier to standard pdf-decoder Logging Startup Issues (#445, #446, #447): Resolved multiple logging startup problems Build Dependencies (#441, #442): Added missing build dependenciesTemplate Addition (#463): Added new template supportPython Dependencies : Updated Python dependencies to version 1.2 PDF Decoder Tests : Added comprehensive tests for PDF decoder functionalityMCP Arguments Tests : Added test coverage for MCP tool argumentsMulti-step Reasoning Tests : New tests for multi-step tool invocation scenarios MCP (Model Context Protocol) Support : Added MCP server and client support (#419, #425, #426, #427, #428)React Integration : Added React call MCP functionality (#428) Documentation updates for API/CLI changes in v1.0 (#420, #421) Enhanced README with messaging improvements and link fixes Flow API & Management : Complete flow configuration and management system (#345, #346, #356, #357, #358)Knowledge Management : Knowledge service, library management, and core CLI tools (#367, #368, #369, #372)Enhanced Gateway : Reverse gateway functionality and improved API gateway (#416, #356)Performance Improvements : Multi-threading support for consumers and LLMs (#408, #409) vLLM Support : Added vLLM integration (untested) (#410)HuggingFace TGI : Added HuggingFace Text Generation Inference support (#396)Google AI Updates : Enhanced Google AI integration (#394) Fixed command line arguments handling (#417) Fixed library translators (#415) Fixed missing script issues (#418) Improved token rate measurement utility (#412) Enhanced translator classes (#414) Miscellaneous fixes (#413) Knowledge Service : Full knowledge management system with CLI toolsLibrary Management : Document submission and library CLI functionalityEntity Contexts : Import/export capabilities for entity contextsConfiguration Persistence : Enhanced config management and reload mechanisms Container Updates : Upgraded to Python 3.12 (#386)OCR Improvements : Ported OCR code to new API architectureApache 2 License : Updated licensing (#373) Fixed LLM launch bugs (#377, #378) Fixed queue initialization issues (#381, #382) Fixed chunking not being enabled (#364) Fixed OpenAI base URL handling Configuration Service : Dynamic configuration management (#332, #334, #335)Prompt Management : Dynamic prompt loading and CLI commands (#338)Agent Management : Enhanced agent configuration system Removed template directory (moved to separate repository) (#336) Enhanced configuration initialization (#335) Added config reload handler mechanism (#334) Librarian Service : Document processing and management (#304, #305, #307, #310, #311)Mistral AI Support : Complete Mistral API integration including OCR (#313, #326)LM Studio Integration : Added LM Studio LLM hosting support (#323, #328)PDF OCR : Separate PDF OCR package with Tesseract support (#324)Cassandra Integration : Added Cassandra auth with SSL support (#318) Azure AKS : Azure Kubernetes Service integration (#317, #319)AWS Bedrock : Inference profiles support (#314)FastEmbed : Enabled FastEmbed component (#316) Pulsar API Key : Added API key support (#308)Async/Sync Fixes : Resolved async/sync loading issues (#315)GraphRAG & DocRAG : Enhanced parameters and path hops (#312) Fixed broken setup.py (#320) Fixed async send typos (#322) Fixed container build issues (#325) Fixed missing OpenAI symbol and base URL specification (#330) Fixed Bedrock integration issues (#331)