Integration involves modifying backend/app/main.py to register discovery API routes. The backend/app/main.py file starts the FastAPI app that exposes the API Layer.

Coolify Integration includes deployment for datalens.exerun.com domain.

DataLensVannaAgent uses DataLensAgentMemory backed by Qdrant for semantic search and memory. DataLensAgentMemory is backed by QdrantService to provide vector-based agent memory.

DataLensPostgresRunner wraps PgDataService to enforce project-scoped schema isolation for SQL execution. DataLensVannaAgent uses DataLensPostgresRunner to run SQL queries with project schema isolation.

DataLensVannaAgent uses DataLensAgentMemory backed by Qdrant for semantic search and memory. DataLensVannaAgent uses DataLensPostgresRunner to run SQL with project-specific schema isolation. DataLensVannaAgent uses DataLensPostgresRunner to run SQL queries with project schema isolation.

DataLens Platform requires setting a strong DB_PASSWORD environment variable to secure the PostgreSQL database connection.

Commit 507c94b adds support for decimal types by importing Decimal and updating numeric column detection.

Decimal type support contributes to fixing SQL syntax errors by enabling proper support for decimal types in queries. Commit 507c94b adds Decimal type support by importing Decimal from the decimal module and updating the numeric column detection logic.

The decision to revert to the last known good commit and deploy applies to the DataLens OpenClaw Integration as a strategy to resolve recent issues. The Commit identification and deployment process is part of the decision to revert to the last known good commit and deploy.

DeepAnalyze-8B model download failed (requires 22-26GB VRAM, only 20GB available). Alternative models like SQLCoder-7B deployed for faster SQL generation (3-5x speedup) on elin GPU. Current setup uses Ollama on elin to serve SQLCoder-7B, improving inference from 40-50s to 2-3s.

Dismiss a finding through DELETE /findings/{finding_id}. Updating and deleting a finding relate to managing the lifecycle of findings in the agent backend.

File deletion endpoint in backend/api/files.py, status unspecified.

Delete project endpoint, status unspecified.

deploy_elin.sh is an automated backend deployment script for elin. deploy_elin.sh is an automated deployment script for the backend on elin.

The Deploy_gpu_extractors.sh script installs and configures the Docling extraction system and related GPU-first extraction components.

DataLens OpenClaw Integration is preparing deployment by reverting code and pushing to master branch, with deployment expected to follow automatically with Coolify.

Docker Deployment includes the DEPLOYMENT.md acceptance document guiding deployment via Coolify. DEPLOYMENT.md documents the Coolify-ready configuration DEPLOYMENT.md provides comprehensive deployment instructions for Coolify. The DataLens platform includes the DEPLOYMENT.md document providing a guide for Coolify deployment.

Hybrid deployment guide combining backend on elin with GPU-accelerated DataLens AI and frontend on theo via Coolify, ensuring separation of infrastructure and detailed setup instructions. The hybrid deployment involves backend running on elin. The hybrid deployment includes the frontend running on theo. DEPLOYMENT_HYBRID.md provides a complete guide for the hybrid deployment. DEPLOYMENT_HYBRID.md provides a complete guide for the hybrid deployment. Hybrid deployment architecture runs all Python and AI workloads on elin. The hybrid deployment involves backend running on elin. The hybrid deployment includes the frontend running on theo. DEPLOYMENT_HYBRID.md provides a complete guide for the hybrid deployment. DEPLOYMENT_HYBRID.md provides a complete guide for the hybrid deployment. Hybrid deployment architecture runs all Python and AI workloads on elin.

DataLens submits commits to DEPLOYMENT_QUEUE.md to request deployments, which are reviewed by the Ops Engineer. DataLens agent deployment requests are appended to DEPLOYMENT_QUEUE.md for review and approval by Ops Engineer. Ops Engineer approves deployments listed in DEPLOYMENT_QUEUE.md and authorizes execution. DataLens uses DEPLOYMENT_QUEUE.md to track deployment requests and statuses via the Ops Engineer workflow.

Decided to keep column and table names unchanged to maintain data integrity and avoid query errors, using prompts to instruct language responses instead.

The architecture comparison document validates design decisions. The architecture comparison with Vanna 2.0 and WrenAI validates design decisions made.

DataLens agent interacts with DevOps processes and personnel for deployment and infrastructure coordination.

Direct SQL is an option in the Agent Selector Dropdown for performing raw structured queries. Agent Selector directs queries to Direct SQL agent

DataLens Agent Mode incorporates the discover-insights skill to perform statistical profiling and anomaly detection.

DiscoverInsightsSkill uses SkillResult when performing statistical profiling and anomaly detection.