Selcan Yukcu commited on
Commit ·
0d6f96c
1
Parent(s): 86fa3b8
fix: ReadMe
Browse files
README.md
CHANGED
|
@@ -1,11 +1,9 @@
|
|
| 1 |
# PostgreSQL NLP Query Bot
|
| 2 |
|
| 3 |
-
---
|
| 4 |
A PostgreSQL MCP server and client system that accepts natural language queries from the user, translates them into SQL using an LLM agent (powered by LangChain), executes the query on the database, and returns the results in a human-readable format.
|
| 5 |
|
| 6 |
## Features
|
| 7 |
|
| 8 |
-
---
|
| 9 |
* Natural Language to SQL Translation
|
| 10 |
* Live Interaction with PostgreSQL via MCP Protocol
|
| 11 |
* Tool Integration with Database Metadata
|
|
@@ -21,7 +19,7 @@ A PostgreSQL MCP server and client system that accepts natural language queries
|
|
| 21 |
| LLM Framework | [LangChain](https://www.langchain.com/) | Manages agent behavior, memory, and tool interaction |
|
| 22 |
| LLM Provider | Google Gemini (via LangChain) | Converts natural language into SQL queries |
|
| 23 |
| Agent Runtime | LangGraph’s `create_react_agent` | Runs the ReAct-style LLM agent |
|
| 24 |
-
| Communication | Modular Command Protocol (MCP) | Handles communication between client and PostgreSQL backend
|
| 25 |
| Tooling | `langchain_mcp_adapters` | Loads and manages tools for the agent |
|
| 26 |
| Database | PostgreSQL | Serves queried data |
|
| 27 |
| UI (optional) | [Gradio](https://www.gradio.app/) | Provides a lightweight web interface for querying |
|
|
@@ -31,7 +29,6 @@ A PostgreSQL MCP server and client system that accepts natural language queries
|
|
| 31 |
|
| 32 |
## Installation
|
| 33 |
|
| 34 |
-
---
|
| 35 |
|
| 36 |
1. **Clone the repository**
|
| 37 |
|
|
@@ -54,7 +51,6 @@ Make sure the server path is correctly set in get_server_params() in your code.
|
|
| 54 |
|
| 55 |
## Configuration
|
| 56 |
|
| 57 |
-
---
|
| 58 |
|
| 59 |
Before running the application, make sure to set your configuration values in a `.env` file.
|
| 60 |
|
|
@@ -73,7 +69,6 @@ You can start by copying the example file provided:
|
|
| 73 |
|
| 74 |
## Running the Project
|
| 75 |
|
| 76 |
-
---
|
| 77 |
|
| 78 |
Once you've installed the dependencies and configured the `.env` file, you're ready to run the app.
|
| 79 |
|
|
|
|
| 1 |
# PostgreSQL NLP Query Bot
|
| 2 |
|
|
|
|
| 3 |
A PostgreSQL MCP server and client system that accepts natural language queries from the user, translates them into SQL using an LLM agent (powered by LangChain), executes the query on the database, and returns the results in a human-readable format.
|
| 4 |
|
| 5 |
## Features
|
| 6 |
|
|
|
|
| 7 |
* Natural Language to SQL Translation
|
| 8 |
* Live Interaction with PostgreSQL via MCP Protocol
|
| 9 |
* Tool Integration with Database Metadata
|
|
|
|
| 19 |
| LLM Framework | [LangChain](https://www.langchain.com/) | Manages agent behavior, memory, and tool interaction |
|
| 20 |
| LLM Provider | Google Gemini (via LangChain) | Converts natural language into SQL queries |
|
| 21 |
| Agent Runtime | LangGraph’s `create_react_agent` | Runs the ReAct-style LLM agent |
|
| 22 |
+
| Communication | Modular Command Protocol (MCP) | Handles communication between client and PostgreSQL backend|
|
| 23 |
| Tooling | `langchain_mcp_adapters` | Loads and manages tools for the agent |
|
| 24 |
| Database | PostgreSQL | Serves queried data |
|
| 25 |
| UI (optional) | [Gradio](https://www.gradio.app/) | Provides a lightweight web interface for querying |
|
|
|
|
| 29 |
|
| 30 |
## Installation
|
| 31 |
|
|
|
|
| 32 |
|
| 33 |
1. **Clone the repository**
|
| 34 |
|
|
|
|
| 51 |
|
| 52 |
## Configuration
|
| 53 |
|
|
|
|
| 54 |
|
| 55 |
Before running the application, make sure to set your configuration values in a `.env` file.
|
| 56 |
|
|
|
|
| 69 |
|
| 70 |
## Running the Project
|
| 71 |
|
|
|
|
| 72 |
|
| 73 |
Once you've installed the dependencies and configured the `.env` file, you're ready to run the app.
|
| 74 |
|