Build Paths Intermediate
Scaffold a Grok-4 tool-calling agent over an Oracle schema using langchain-oracledb +...
Install
npx skills add oracle-devrel/oracle-ai-developer-hub --skill build-paths-intermediate -g -a claude-code -y- Repository
- oracle-devrel/oracle-ai-developer-hub4.5k
- Category
- Data and ML
- Updated
- 5d ago
- License
- See repository
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Scaffold a Grok-4 tool-calling agent over an Oracle schema using langchain-oracledb + oracle-database-mcp-server + in-DB ONNX embeddings (registered MiniLM model, no external embedding API) + Open WebUI. For users who've built RAG before and want to rebuild it on the production-feeling Oracle stack.
The user picked the intermediate path. They've built RAG and chatbots before. Your job is to introduce them to two new ideas at once: (a) an LLM agent that calls live SQL via oracle-database-mcp-server, and (b) embeddings that happen inside the database via a registered ONNX model. The stack is production-shaped: OCI GenAI Grok 4, in-DB ONNX, Open WebUI. No Ollama, no external embedding API.
Step 0, Read these references first
shared/references/sources.mdshared/references/oracle-26ai-free-docker.mdshared/references/langchain-oracledb.mdshared/references/oci-genai-openai.md← Pattern 1 SigV1 authshared/references/onnx-in-db-embeddings.md← load-bearing for embeddingsshared/references/oracledb-python.mdshared/references/ai-vector-search.mdshared/references/hybrid-search.md(idea 3 specifically)shared/references/exemplars.mdintermediate/project-ideas.mdskills/oracle-aidb-docker-setup/SKILL.mdskills/langchain-oracledb-helper/SKILL.mdskills/oracle-mcp-server-helper/SKILL.md
Step 1, Interview
Run shared/interview.md. For intermediate specifically:
