exasol-agent-skills

Exasol database interaction via exapump CLI and Exasol SQL. Covers SQL queries, schema inspection, table design, query profiling, analytics, and Exasol-specific SQL behavior outside exasol-import and exasol-export.

Catalog and routing guide for Exasol tools, extensions, connectors, integrations, and architecture patterns. Use when users ask how to extend, customize, deploy, load, explore, enrich, surface, scale, automate, govern, migrate, or integrate Exasol, including Exasol Labs tools, AI/ML, UDFs, lakehouse, SAP, Databricks, agentic workflows, or product/version status.

Top-level router for Exasol work. Use for any Exasol database, exapump, SQL, BucketFS, extension, integration, UDF, Script Language Container, or Exasol Personal setup task, then route to the narrowest specialized Exasol skill.

Build, install, validate, and debug custom Exasol virtual schema adapters. Covers source-specific JDBC dialect implementation with virtual-schema-common-jdbc, custom document-file adapter code boundaries, JAR packaging, BucketFS deployment, adapter script setup, EXPLAIN VIRTUAL validation, and adapter-side remote debugging workflows.

Use Exasol document-file virtual schemas for federated read-only access to object and file storage. Covers document-file adapter family selection, CREATE VIRTUAL SCHEMA usage, refresh workflows, and query-side troubleshooting.

Use Exasol JDBC-based virtual schemas for federated read-only access to external databases. Covers database-source adapter selection, CREATE VIRTUAL SCHEMA, EXPLAIN VIRTUAL, metadata refresh, and query-side troubleshooting.

Use Exasol Cloud Storage Extension workflows for moving structured object-storage files through extension UDFs. Covers setup prerequisites, fixed UDF entrypoints, supported import/export formats, connection-object credential patterns, and routing away from native IMPORT or EXPORT when the extension path is the right fit.

Use Exasol IMPORT SQL plus exapump local file upload workflows for moving data into Exasol. Covers CSV, FBV, Parquet, connection objects, cloud credential patterns, reject handling, and staging-based import workflows.

Use Exasol EXPORT SQL plus exapump local file export workflows for moving data out of Exasol. Covers native CSV/FBV export, local CSV/Parquet exports with exapump, connection objects, reject limits, and export credential patterns.

Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY + SET scripts + BucketFS), per-entity federated training with partial_fit and ctx.reset(), batch inference, map-reduce ensemble training, distributed ensemble and SON algorithm for frequent itemset mining, Lua execute script orchestration for iterative algorithms (k-means, SGD, Apriori), parallel hyperparameter search, per-entity forecasting, anomaly detection, model lifecycle in BucketFS (pickle/joblib/ONNX versioning), GPU acceleration via CUDA SLCs (PyTorch/TensorFlow/RAPIDS), and ML-specific performance tuning (skew, OOM, multi-pass chunking).

Exasol User Defined Functions (UDFs) and Script Language Containers (SLCs). Covers CREATE SCRIPT, SCALAR and SET functions, ExaIterator API, Python/Java/Lua/R scripts, BucketFS file access, GPU-accelerated UDFs, and building/deploying custom Script Language Containers with exaslct.

Deploy and use the Exasol Text AI Extension with notebook-connector. Covers deploy_license, initialize_text_ai_extension, the Extraction API, default-model installation, result-table querying, and pipeline or branch-based text extraction workflows.

Deploy and use the Exasol Transformers Extension for NLP inference inside Exasol with notebook-connector. Covers initialize_te_extension, deploy_scripts, activation SQL, model-installation workflows, and the current TE SQL UDF surface.

Use notebook-connector's Python connection helpers for Exasol, BucketFS, SQLAlchemy, and Ibis. Covers open_pyexasol_connection, open_sqlalchemy_connection, open_ibis_connection, open_bucketfs_bucket, open_bucketfs_location, get_backend, and related helper functions.

Use notebook-connector's itde_manager to run a local Docker-based Exasol database. Covers bring_itde_up, get_itde_status, restart_itde, take_itde_down, and how ITDE populates notebook-connector configuration automatically.

Set up notebook-connector configuration for Exasol AI workflows through the Secrets Python API. Covers secure-store creation, backend-specific config values, Python validation, and handoff to downstream notebook-connector skills.

Guided setup of Exasol Personal — a single-node Exasol database deployed to your own cloud account. Covers AWS account preparation, CLI installation, deployment, sample data loading, and MCP server setup.

Exasol BucketFS file system management via exapump CLI. Covers listing, uploading, downloading, and deleting files and directories in BucketFS, BucketFS configuration, bucket structure, and use with UDFs.