How arnabdhaliofficial/ai_sql_analyst works
SQL Agent is a Streamlit natural-language PostgreSQL assistant. A user submits a question in the app, which invokes the LangGraph analyst: it curates the question, gathers database schema context, generates SQL, judges its safety, executes approved queries, and turns results into a human-readable answer for display. The app also exposes a database schema browser. Model selection and PostgreSQL access are separate internal layers. The README documents the supported model providers; unsampled implementation details are not inferred beyond those documented capabilities.
Main entry points: app.py Streamlit app · llm_pick.py Model selector · sql_analyst.py Agent graph · database.py Database access
Components 16
User interface
- Streamlit app
app.py - Schema browser
app.py
SQL agent workflow
- Agent graph
agents/sql_analyst.py - Question curation
agents/sql_analyst.py - Schema context
agents/sql_analyst.py - SQL generation
agents/sql_analyst.py - SQL safety judge
agents/sql_analyst.py - Unsafe query response
agents/sql_analyst.py - Query execution
agents/sql_analyst.py - Answer synthesis
agents/sql_analyst.py
Internal services
- Agent state schemas
Models/schema.py - Model selector
utils/llm_pick.py - Database access
utils/database.py
External systems
- PostgreSQL
- LLM providers
Other components
- User
Connections 21
- User → Streamlit app: asks question
app.py - Streamlit app → Agent graph: invokes
app.py - Agent graph → Streamlit app: returns result
app.py - Streamlit app → Schema browser: renders
app.py - Streamlit app → PostgreSQL: inspects schema
app.py - Agent graph → Question curation: starts
agents/sql_analyst.py - Question curation → Schema context: continues
agents/sql_analyst.py - Schema context → SQL generation: continues
agents/sql_analyst.py - SQL generation → SQL safety judge: continues
agents/sql_analyst.py - SQL safety judge → Query execution: routes if safe
agents/sql_analyst.py - SQL safety judge → Unsafe query response: routes if unsafe
agents/sql_analyst.py - Query execution → Answer synthesis: continues
agents/sql_analyst.py - Question curation → Model selector: selects model
agents/sql_analyst.py - SQL generation → Model selector: selects model
agents/sql_analyst.py - SQL safety judge → Model selector: selects model
agents/sql_analyst.py - Answer synthesis → Model selector: selects model
agents/sql_analyst.py - Schema context → Database access: reads schema
agents/sql_analyst.py - Query execution → Database access: executes query
agents/sql_analyst.py - Database access → PostgreSQL: queries
utils/database.py - Model selector → LLM providers: calls selected provider
utils/llm_pick.py - Agent graph → Agent state schemas: uses state types
agents/sql_analyst.py