Multi-agent retrieval-augmented generation system with 9 reasoning strategies, powered by Oracle AI Database and local Ollama LLMs. A complete RAG pipeline from document ingestion to intelligent query synthesis.
Oracle AI Vector Search integration for LangChain. Provides OracleVS, OracleEmbeddings, OracleTextSplitter.
core databasePython driver for Oracle Database. Thick/thin client for connection pooling and session management.
database9 reasoning strategies library: CoT, ToT, ReAct, MCTS, R1, Beam Search, Self-Consistency, PRM, Meta-Reasoning.
coreLocal LLM inference server. Default model: gemma3:270m. No cloud dependency.
corePDF document processing with structure extraction. Handles tables, headers, and metadata.
ingestionWeb content extraction. Cleans HTML to readable text with metadata preservation.
ingestionCode repository ingestion. Processes Git repos into document chunks for RAG indexing.
ingestionHigh-performance API framework. Serves OpenAI-compatible endpoints and A2A protocol.
interfaceInteractive web UI with tabbed interface for querying, uploading documents, and monitoring.
interfaceFull-featured chat UI. Connects via OpenAI-compatible API exposing 18 reasoning models.
interfaceFallback vector store when Oracle DB is unavailable. Same interface abstraction.
fallbackFallback embedding model. Used when OracleEmbeddings is not configured.
fallbackSix Oracle Database tables provide full observability across every layer of the system. Every operation is tracked with timestamps, durations, and contextual metadata.
Three custom Open WebUI functions bridge the chat interface with Oracle AI Database. Together they enable transparent RAG augmentation across every conversation.