Add initial project structure with environment configuration, README, and core functionality

- Created .env file for database and Hugging Face API configuration
- Added README.md with project description, features, setup, and usage instructions
- Implemented agent_core.py for SQL agent logic and database connection
- Developed app.py for FastAPI integration with SQL agent
- Included sql_agent.py for command-line interaction with the agent
- Established requirements.txt for project dependencies
- Added .gitignore to exclude unnecessary files

.env

@@ -0,0 +1,15 @@
+
+# Database configuration
+PG_DATABASE=logbert_rca
+PG_USER=trans_owner
+PG_PASSWORD=BookMyService7
+PG_HOST=ep-sweet-surf-a1qeduoy.ap-southeast-1.aws.neon.tech
+PG_PORT=5432
+# Optionally, you can use the full SQLAlchemy URI if needed:
+# DATABASE_URI=postgresql+asyncpg://trans_owner:BookMyService7@ep-sweet-surf-a1qeduoy.ap-southeast-1.aws.neon.tech/logbert_rca?options=-csearch_path%3Dtrans
+ 
+HUGGINGFACEHUB_API_TOKEN=       
+
+# Hugging Face/Model configuration
+HUGGINGFACE_MODEL=distilgpt2
+HF_CACHE_DIR=.cache

README.md

@@ -1,3 +1,31 @@
+# RCA SQL Agent
+
+This project is an intelligent SQL agent that uses LangChain and Hugging Face SLM to generate and execute SQL queries on a PostgreSQL database.
+
+## Features
+- Natural language to SQL query generation using Hugging Face SLM via LangChain
+- Executes generated queries on a PostgreSQL database
+- Returns results to the user
+
+## Setup
+1. Install dependencies:
+   ```bash
+   pip install langchain[all] psycopg2-binary transformers
+   ```
+2. Set your PostgreSQL connection details in environment variables or update the script:
+   - `PG_HOST`, `PG_PORT`, `PG_USER`, `PG_PASSWORD`, `PG_DATABASE`
+3. Set your Hugging Face API key in the environment variable `HUGGINGFACEHUB_API_TOKEN`.
+
+## Usage
+Run the agent script and enter your question in natural language. The agent will generate and execute the SQL query, then display the results.
+
+```bash
+python sql_agent.py
+```
+
+Type your question (e.g., "How many users signed up last month?") and get the result from your Postgres database.
+
+---
 ---
 title: Rca Sqlagent
 emoji: 👀

agent_core.py

@@ -0,0 +1,39 @@
+
+import os
+from dotenv import load_dotenv
+load_dotenv()
+from langchain_huggingface import HuggingFaceEndpoint
+from langchain_community.utilities.sql_database import SQLDatabase
+from langchain_community.agent_toolkits.sql.base import SQLDatabaseToolkit, create_sql_agent
+from langchain.agents.agent_types import AgentType
+
+# Set your Hugging Face API key and model
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+HUGGINGFACE_MODEL = os.getenv("HUGGINGFACE_MODEL", "microsoft/phi-2")
+
+# Set your Postgres connection details
+PG_HOST = os.getenv("PG_HOST", "localhost")
+PG_PORT = os.getenv("PG_PORT", "5432")
+PG_USER = os.getenv("PG_USER", "postgres")
+PG_PASSWORD = os.getenv("PG_PASSWORD", "password")
+PG_DATABASE = os.getenv("PG_DATABASE", "postgres")
+
+
+# Create the SQLAlchemy connection string
+connection_string = f"postgresql+psycopg2://{PG_USER}:{PG_PASSWORD}@{PG_HOST}:{PG_PORT}/{PG_DATABASE}"
+
+def get_sql_agent(verbose=False):
+    db = SQLDatabase.from_uri(connection_string)
+    llm = HuggingFaceEndpoint(
+        repo_id=HUGGINGFACE_MODEL,
+        huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
+        temperature=0.2,
+        max_new_tokens=256
+    )
+    agent_executor = create_sql_agent(
+        llm=llm,
+        db=db,
+        agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+        verbose=verbose
+    )
+    return agent_executor

app.py

@@ -0,0 +1,24 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import os
+
+from agent_core import get_sql_agent
+
+_db_chain = get_sql_agent(verbose=True)
+
+app = FastAPI()
+
+class QueryRequest(BaseModel):
+    question: str
+
+@app.post("/query")
+def query_sql_agent(request: QueryRequest):
+    try:
+        result = _db_chain.invoke(request.question)
+        return {"result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/")
+def root():
+    return {"message": "RCA SQL Agent API. POST to /query with {'question': ...}"}

requirements.txt

@@ -0,0 +1,11 @@
+
+fastapi
+uvicorn
+langchain[all]
+transformers
+psycopg2-binary
+asyncpg
+pydantic
+python-dotenv
+redis
+langchain_community

sql_agent.py

@@ -0,0 +1,18 @@
+
+from agent_core import get_sql_agent
+
+def main():
+    db_chain = get_sql_agent(verbose=True)
+    print("Welcome to the RCA SQL Agent! Type your question (or 'exit' to quit):")
+    while True:
+        user_input = input("\n> ")
+        if user_input.lower() in ("exit", "quit"): 
+            break
+        try:
+            result = db_chain.invoke(user_input)
+            print("\nResult:\n", result)
+        except Exception as e:
+            print("Error:", e)
+
+if __name__ == "__main__":
+    main()