v2.1.0 — AI Native Dashboards

This release introduces AI-native dashboard generation, transforming NeoBase from a
conversational database tool into a complete database observability & analytics platform.

Highlights

AI Generates Your Dashboards

No more manual query writing or widget configuration. Just describe what you want:

• "Create a dashboard for my e-commerce database"
• "Show me database health metrics"
• "I want to see daily revenue, active users, and error rates"

The AI analyzes your schema, leverages your Knowledge Base, and generates a complete dashboard
with queries, widgets, and real-time refresh — all in seconds.

11 Widget Types for Every Visualization Need

From simple KPI cards to advanced Grafana-style widgets:

• Stat cards for key metrics at-a-glance
• Line, bar, area, pie, combo charts for standard analytics
• Gauge widgets for speedometer-style indicators with thresholds
• Bar gauge widgets for progress tracking and quota monitoring
• Heatmap widgets for pattern analysis (time-based activity, correlation matrices)
• Histogram widgets for distribution analysis with statistical markers
• Data tables for detailed record views

Zero-Config, Maximum Intelligence

The AI knows your database:

• Detects schema patterns and suggests relevant dashboard templates
• Chooses appropriate widget types for your data (percentages → gauge, time-series → line)
• Generates optimal queries leveraging existing RAG/Knowledge Base context
• Sets sensible refresh intervals based on data volatility

Real-Time Auto-Refresh

Dashboards stay current with configurable auto-refresh (10s to 15m intervals). Watch your
metrics update live without manual re-execution.

Multi-Dashboard Support

Create unlimited dashboards per database connection:

• Operations Dashboard — Database health, query performance, connection stats
• Analytics Dashboard — Business KPIs, revenue trends, user metrics
• Management Dashboard — High-level summaries for stakeholders

🔧 What's New

Backend

• Dashboard Service — AI generation, CRUD operations, refresh orchestration
• Dashboard Tool Executor — Dedicated tool-calling system for dashboard operations
• Widget System — 11 widget types with standardized data contracts
• Dashboard Repository — MongoDB persistence with layout storage
• Template Engine — AI-driven template suggestions based on schema analysis
• Refresh Pipeline — Parallel widget execution with error isolation

Frontend

• Dashboard Tab — Toggle between Chat and Dashboard modes in chat header
• Dashboard Grid — Responsive widget layout with proper spacing and alignment
• 11 Widget Renderers — Specialized rendering for each widget type using Recharts
• Widget Actions — Edit with AI, refresh, duplicate, delete per widget
• Dashboard Chat — Mini prompt interface for conversational dashboard editing
• Empty State — Animated illustration for first-time dashboard creation
• Auto-Refresh UI — Interval selector, last refresh timestamp, manual refresh controls

AI Capabilities

• Template Auto-Detection — Suggests E-Commerce, SaaS, Database Health, User Analytics,
  Data Pipeline, IoT, and Custom templates
• Smart Widget Selection — Chooses gauge for percentages, histogram for distributions,
  heatmap for time-based patterns
• Conversational Editing — Edit any widget with natural language prompts
• Knowledge Base Integration — Leverages existing KB descriptions for semantic understanding

Use Cases

Persona	Dashboard
DBA / DevOps	Table sizes, index usage, slow queries, replication lag, connection counts
Data Engineer	Row count trends, data freshness, pipeline health, stale table alerts
Backend Developer	User signups, order volumes, error rates from app tables
Data Analyst	Revenue trends, user funnels, retention cohorts, business KPIs
Manager	High-level business metrics without SQL knowledge

v2.0.0 — RAG + Multi-Tool-Calling AI Agent

🚀 NeoBase v2.0.0 — RAG + Multi-Tool-Calling AI Agent

This is a major release that completely re-architects NeoBase's AI engine. The LLM no longer
generates queries in a single shot — it now operates as an autonomous AI agent with tool access,
backed by vector search (RAG) for intelligent context retrieval.

✨ Highlights

From Single API Call to Iterative AI Agent

The LLM now has access to 3 tools (get_table_info, execute_read_query,
generate_final_response) and can iterate up to 10 times per request — inspecting tables,
running test queries, and self-correcting before delivering results. Implemented natively
across Gemini, OpenAI, Claude, and Ollama.

RAG-Powered Context (80-95% Token Savings)

Instead of injecting the entire database schema into every prompt, NeoBase now uses vector
embeddings (via Qdrant) to retrieve only the relevant 2-5 tables per query. This reduces
prompt tokens by 80-95% for large schemas and dramatically improves accuracy by reducing noise.

Auto-Generated Knowledge Base

Every database connection gets an AI-generated Knowledge Base — natural language descriptions
of every table and field. These descriptions enrich vector embeddings and are available for
users to view and edit through a new UI tab.

Self-Improving Context

User queries and AI responses are embedded into a message history vector collection, enabling
the system to leverage past conversations for better context in future queries.

🔧 What's New

• Multi-Tool-Calling Agent — Iterative tool execution across all 4 LLM providers
• RAG Pipeline — Qdrant vector DB + OpenAI/Gemini embedding providers
• Knowledge Base — Auto-generated table/field descriptions stored in MongoDB
• Smart Schema Chunking — DB-aware chunking that respects table boundaries
• Message Vectorization — Conversation history embedded for cross-query context
• Empty Response Retry — Automatic retry with nudge prompts on LLM failures
• Anti-Refusal Rules — LLMs cannot refuse data-related queries
• Query Self-Correction — Failed queries retried with error context
• Markdown Improvements — GFM tables, proper list rendering, dedup
• KB Fallback for Recommendations — Graceful degradation when schema unavailable
• DB-Aware Table Discovery — Fallback queries per database type
• Auto-Vectorization — Legacy chats vectorized on first access

🐳 Infrastructure

• New Dependency: Qdrant vector database (added to all Docker Compose files)
• New Env Vars: QDRANT_HOST, QDRANT_PORT, embedding provider API keys

🗄️ Supported Databases

PostgreSQL · MySQL · MongoDB · ClickHouse · YugabyteDB · Google Sheets

⚠️ Breaking Changes

• Qdrant is now a required dependency
• New environment variables must be configured (see SETUP.md)
• Full schema is no longer sent to LLM — replaced by RAG retrieval

Improved Backend Performance By Caching Entities

What's Changed

• perf: Implement Redis caching with compression and optimize API call deduplication by @bhaskarblur in #90
• fix: redis cache related issue by @bhaskarblur in #91

Full Changelog: enchancements-visualization...1.1.1

Introducing Query Visualization, Improvements to LLM Model selection, SSH Tunnel & more

What's Changed

• feat: Added Google OAuth, Query Visualization, Support for Dynamic model selection, Claude & Ollama Introduced, Support for SSH tunnel etc by @bhaskarblur in #88
• Improved visualization handling & added export feature for it by @bhaskarblur in #89

Full Changelog: data-copilot...enchancements-visualization

Release 1.0.1: Improved performance of chat & fixed minor issues

What's Changed

• Added support for Yugabyte, large data( >50 records), fixed postgres, schema comparison by @bhaskarblur in #8
• Enabled Pagination for Large results, Gemini support & more by @bhaskarblur in #9
• Public Landing page designed by @bhaskarblur in #10
• Landing page UI responsive fixes by @bhaskarblur in #11
• Video added by @bhaskarblur in #12
• Fix: Responsive landing page by @bhaskarblur in #13
• Added auto fetch results feature by @bhaskarblur in #14
• Analytics in Landing page by @bhaskarblur in #15
• feat: video heading size by @bhaskarblur in #16
• fix: analytics by @bhaskarblur in #17
• Added Support for MySQL & Clickhouse with Native Features by @bhaskarblur in #18
• Added Environment based specs by @bhaskarblur in #19
• fix: user context on signup by @bhaskarblur in #20
• Edit message & connection properly handled by @bhaskarblur in #21
• feat: added example db for new user creation by @bhaskarblur in #23
• fix: connection update & properties by @bhaskarblur in #24
• Added SSL for connection, database Manager lvl Connection Sharing, Encrypted DB details by @bhaskarblur in #29
• Supported MongoDB + minor bugs fixed by @bhaskarblur in #30
• Added Action Buttons for Messages, Fix MongoDB Queries by @bhaskarblur in #35
• Fix: MongoDB Query expressions, Improved pagination support for large data. by @bhaskarblur in #37
• Refactored backend code, fixed mongodb query parsing etc by @bhaskarblur in #39
• Fixed Connection pooling issue for diff DBs on Same host, prompts by @bhaskarblur in #40
• Improved Loading state, scroll page issue, openai fix etc.. by @bhaskarblur in #44
• fix analytics by @bhaskarblur in #45
• Improved prompts, fixed mongodb parsing, app code split by @bhaskarblur in #46
• feat: AI Text MD formatting by @bhaskarblur in #47
• fix: build failed by @bhaskarblur in #48
• refact: changed md module by @bhaskarblur in #49
• feat: timestamp for query execution & rollback by @bhaskarblur in #50
• Added Duplicate chat & Example DB Label by @bhaskarblur in #51
• feat: date based grouping chats in sidebar by @bhaskarblur in #52
• MongoDB Regex issue, DB Reconnect on message by @bhaskarblur in #53
• Added SSL Mode Configuration, Multi tab connection layout by @bhaskarblur in #55
• Enhanced visualization of nested fields, date for query results. by @bhaskarblur in #56
• Introduce Docker Compose configuration for Dokploy deployment by @imajus in #58
• Fix MongoDB connection issues & introduce "Authentication Database" setting by @imajus in #60
• Added Support for Email Signup, Reset Password, And Usability Improvement by @bhaskarblur in #64
• Refactor email template loading to support Docker and local environments by @bhaskarblur in #65
• Enhance email service by adding email templates to Docker build by @bhaskarblur in #66
• Improved Analytics & Usability features by @bhaskarblur in #67
• Added chat Id Page navigation, Improved Usability more, Scroll state etc by @bhaskarblur in #68
• fix url based nav by @bhaskarblur in #69
• feat: Add Enterprise waitlist, enhance UI/UX, and improve performance by @bhaskarblur in #70
• Refined text in UI components for clarity and consistency by @bhaskarblur in #71
• feat: Add message search, non-technical mode, and improved MongoDB query handling by @bhaskarblur in #72
• improved design for mode indicator by @bhaskarblur in #73
• Improved LLM prompts + MD rendered by @bhaskarblur in #75
• cleaned msg rendering by @bhaskarblur in #76
• feat: Add message pinning functionality & Improved Landing page by @bhaskarblur in #77
• Added Support for Uploading Spreadsheet - CSV, XLSX by @bhaskarblur in #78
• Voice Mode overlay, Recommended queries UX with shimmer + auto-send, SSE/AI flow hardening, ChatHeader UI, and Redis ACL persistence by @bhaskarblur in #79
• Fix Voice Mode & Recommendation by @bhaskarblur in #80
• improved voice mode on IoS by @bhaskarblur in #81
• Removed Voice Mode & Improved recommendations rendering by @bhaskarblur in #82
• Improved landing page content & technology logos by @bhaskarblur in #83
• Added TOS & Privacy Policy to Landing page by @bhaskarblur in #84
• fix: privacy, terms link in footer by @bhaskarblur in #85
• Implemented Google Sheets & Improved Spreadsheet handling by @bhaskarblur in #86

New Contributors

• @imajus made their first contribution in #58

Full Changelog: https://github.com/bhaskarblur/NeoBaseAI-Copilot-for-database/commits/data-copilot