skills.rest
oracle-devrel
oracle-devrelOFFICIAL
Explore all skills by this author →
WebsiteGitHub

build-paths-advanced

Scaffold Oracle AI DB agent projects with DB-only state and verify.py checks.

4.3k|807|Updated Jan 16, 2024
Search Tags:#rag#agent#mcp#open webui#oracle ai database#in-db embeddings#db-as-only-store
One-click install
npx skills add https://github.com/oracle-devrel/oracle-ai-developer-hub --skill build-paths-advanced
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: build-paths-advanced
Source: https://github.com/oracle-devrel/oracle-ai-developer-hub/tree/main/build-paths/advanced
Command: npx skills add https://github.com/oracle-devrel/oracle-ai-developer-hub --skill build-paths-advanced

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It scaffolds an advanced, production-feeling agent project where Oracle AI Database is the only durable state store, so you can demo and iterate on agentic workflows without sidecar databases or hidden state.

Core Features & Use Cases

  • Oracle DB as the only state store: Enforces a forbidden-imports constraint and routes all durable memory and retrieval through Oracle components (OracleVS, in-DB ONNX embeddings, and OAMP where applicable).
  • Skill-library composition: Orchestrates three reusable building blocks—Oracle DB docker setup, LangChain Oracle vector wiring, and an MCP server that exposes SQL/schema tools—then layers in only the application logic.
  • Three advanced demo projects: Scaffolds (1) a hybrid NL2SQL + document RAG analyst with OAMP-backed durable per-user memory, (2) a self-improving research agent that logs tool runs and retrieves prior executions via OracleVS plus OAMP conversation context, or (3) a conversational schema designer with DDL confirmation gating and JSON Duality view generation (with read_write MCP).
  • Verification + executed notebook payoff: Includes a verify.py checklist (DB/memory/MCP smoke tests and state-store invariants) and requires a clean, executed notebook for shareable demos.

Quick Start

Run the scaffold with a non-empty empty target directory, choose one of the three advanced project ideas (or provide a pitch mapped to them), confirm OCI GenAI usage, and generate the project with an executable notebook and verification script.

Frequently Asked Questions about build-paths-advanced

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an AI agent using Oracle Database as the only state store?▼

You can build an Oracle DB-as-only-store agent by routing all durable memory, retrieval, and tooling through in-DB ONNX embeddings and OracleVS, enforcing a forbidden-imports constraint to eliminate sidecar databases.

What is an NL2SQL plus RAG analyst and how does it work with Oracle AI Database?▼

A hybrid NL2SQL plus document RAG analyst is an agent pattern combining natural language to SQL with document retrieval, backed by Oracle AI Database for durable per-user memory via OAMP and in-DB ONNX embeddings.

Can I use Open WebUI and MCP servers with Oracle AI Database for agent memory?▼

Yes, you can use an Oracle MCP server helper to expose SQL and schema tools, integrating with Open WebUI while Oracle AI Database handles all durable memory and conversation context via OAMP and OracleVS.

Do I need OCI GenAI and ONNX embeddings to run an Oracle DB-as-only-store agent?▼

Yes, Oracle DB-as-only-store agents require OCI GenAI via an OpenAI-compatible endpoint and in-DB ONNX embeddings with a fixed dimension of 384 to operate entirely within Oracle components.

How do I create a conversational schema designer with confirmation-gated DDL in Oracle?▼

Create a conversational schema designer by using a read_write MCP server to generate JSON Duality views and enforce confirmation-gated DDL, ensuring all schema changes route securely through Oracle Database.

What are the limitations of using Oracle AI Database as the only state store for agents?▼

The DB-as-only-store invariant forbids external imports for state, limiting you to Oracle components like OracleVS and OAMP, and requires a verify.py checklist to ensure memory and MCP smoke tests pass.

Related Skills

Explore More Software Engineering Skills→
oracle-devreloracle-devrel
4.3k

build-paths-beginner

Scaffold a RAG chatbot with OracleVS embeddings and a Grok-4 chat UI.

Official
Advanced
Just-itJust-it
33

kernel-verifier

Automate kernel verification by running verify.py and benchmark.py for Ascend/NPU.

Community
Advanced
oracle-devreloracle-devrel
4.3k

build-paths-intermediate

Scaffold a Grok-4 tool-calling agent over an Oracle schema with MCP and ONNX embeddings.

Official
Advanced
cxnaivecxnaive

pinecone-research

Store and retrieve conversation context using Pinecone vector databases.

Community
Intermediate