# sam-garg/sql_text_app architecture

> Architecture diagram of the GitHub repository sam-garg/sql_text_app, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sam-garg/sql_text_app
- Repository: https://github.com/sam-garg/sql_text_app

## Overview

This is a Streamlit CSV-to-SQL analysis app. A user uploads a CSV, the app parses and previews it, stores it in a temporary SQLite database, then uses the database schema and a natural-language question to generate SQL with an Ollama-backed LangChain pipeline. The app executes the SQL and displays the query and results. The graph reflects the sampled app.py workflow; create_db.py appears to be a separate sample-database utility, not part of the documented dynamic workflow.

Main entry points: [`app.py`](https://github.com/sam-garg/sql_text_app/blob/main/app.py) (Question Handling)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["User Interface"]
  node_streamlit["Streamlit Interface<br/>[app.py]"]
  node_results["Results Display<br/>[app.py]"]
end

subgraph group_data["Data Preparation"]
  node_csv_parser["CSV Parsing<br/>[app.py]"]
  node_preview["Data Preview<br/>[app.py]"]
  node_sqlite[("Temporary SQLite<br/>[app.py]")]
  node_sql_database["SQL Database Adapter<br/>[app.py]"]
end

subgraph group_query["SQL Analysis"]
  node_question["Question Handling<br/>[app.py]"]
  node_schema["Schema Retrieval<br/>[app.py]"]
  node_prompt["SQL Prompt<br/>[app.py]"]
  node_chain["LangChain Pipeline<br/>[app.py]"]
  node_llm["ChatOllama Model<br/>[app.py]"]
  node_parser["SQL Output Parser<br/>[app.py]"]
  node_execution["SQL Execution<br/>[app.py]"]
end

node_user(("Analyst"))
node_ollama["Ollama Service"]

node_user -->|"uploads CSV"| node_streamlit
node_streamlit -->|"passes file"| node_csv_parser
node_csv_parser -->|"provides rows"| node_preview
node_csv_parser -->|"writes table"| node_sqlite
node_sqlite -->|"opens database"| node_sql_database
node_streamlit -->|"accepts question"| node_question
node_question -->|"reads schema"| node_schema
node_schema -->|"requests table info"| node_sql_database
node_question -->|"invokes pipeline"| node_chain
node_chain -->|"formats input"| node_prompt
node_prompt -->|"supplies prompt"| node_llm
node_llm -->|"requests completion"| node_ollama
node_llm -->|"returns model output"| node_parser
node_question -->|"runs generated SQL"| node_execution
node_execution -->|"executes query"| node_sql_database
node_execution -->|"displays result"| node_results
node_question -->|"shows generated SQL"| node_results

click node_streamlit "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_csv_parser "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_preview "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_sqlite "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_sql_database "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_question "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_schema "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_prompt "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_chain "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_llm "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_parser "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_execution "https://github.com/sam-garg/sql_text_app/blob/main/app.py"
click node_results "https://github.com/sam-garg/sql_text_app/blob/main/app.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_streamlit,node_results toneBlue
class node_csv_parser,node_preview,node_sqlite,node_sql_database toneAmber
class node_question,node_schema,node_prompt,node_chain,node_llm,node_parser,node_execution toneMint
class node_user,node_ollama toneIndigo
```

## Components

### User Interface

- [Streamlit Interface](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [Results Display](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`

### Data Preparation

- [CSV Parsing](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [Data Preview](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [Temporary SQLite](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [SQL Database Adapter](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`

### SQL Analysis

- [Question Handling](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [Schema Retrieval](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [SQL Prompt](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [LangChain Pipeline](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [ChatOllama Model](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [SQL Output Parser](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`
- [SQL Execution](https://github.com/sam-garg/sql_text_app/blob/main/app.py): `app.py`

### Other components

- **Analyst**
- **Ollama Service**

## Connections

- Analyst → Streamlit Interface: uploads CSV (evidence: `app.py`)
- Streamlit Interface → CSV Parsing: passes file (evidence: `app.py`)
- CSV Parsing → Data Preview: provides rows (evidence: `app.py`)
- CSV Parsing → Temporary SQLite: writes table (evidence: `app.py`)
- Temporary SQLite → SQL Database Adapter: opens database (evidence: `app.py`)
- Streamlit Interface → Question Handling: accepts question (evidence: `app.py`)
- Question Handling → Schema Retrieval: reads schema (evidence: `app.py`)
- Schema Retrieval → SQL Database Adapter: requests table info (evidence: `app.py`)
- Question Handling → LangChain Pipeline: invokes pipeline (evidence: `app.py`)
- LangChain Pipeline → SQL Prompt: formats input (evidence: `app.py`)
- SQL Prompt → ChatOllama Model: supplies prompt (evidence: `app.py`)
- ChatOllama Model → Ollama Service: requests completion (evidence: `app.py`)
- ChatOllama Model → SQL Output Parser: returns model output (evidence: `app.py`)
- Question Handling → SQL Execution: runs generated SQL (evidence: `app.py`)
- SQL Execution → SQL Database Adapter: executes query (evidence: `app.py`)
- SQL Execution → Results Display: displays result (evidence: `app.py`)
- Question Handling → Results Display: shows generated SQL (evidence: `app.py`)
