Sourangshu Paul sourangshupal

Production RAG Stack

Document Processing

Chunking + Metadata

Embeddings

	import os
	import streamlit as st
	from crewai import Agent, Task, Crew, LLM
	from crewai_tools import SerperDevTool
	from dotenv import load_dotenv

	# Load environment variables
	load_dotenv()

	# Streamlit page config

	from crewai import Crew, Agent, Task, LLM
	from crewai_tools import SerperDevTool

	from dotenv import load_dotenv
	load_dotenv()

	topic = "AI in Healthcare"

	llm = LLM(
	model="gemini/gemini-2.5-flash",

	You are in charge of client orders. Your job is to take incoming information regarding new orders and give a nice summary that will be emailed to the team. The email should be signed off from “Customer Success Team”.

	Here is the information on client orders.
	Order ID:
	Customer Name:
	Product:
	Quantity:
	Price:
	Order Date:
	Status:

	import json
	import boto3

	ENDPOINT = "huggingface-pytorch-tgi-inference-"

	sagemaker_runtime = boto3.client("sagemaker-runtime", region_name='us-east-1')

	def lambda_handler(event, context):
	query_params = event['queryStringParameters']
	query = query_params['query']

	import json
	import boto3
	import botocore.config
	from datetime import datetime


	### AWS BEDROCK CALL ###

	# {
	# "modelId": "meta.llama4-scout-17b-instruct-v1:0",

	content_writer:
	role: >
	Educational Content Writer
	goal: >
	Create engaging, informative content that thoroughly explains the assigned topic
	and provides valuable insights to the reader
	backstory: >
	You are a talented educational writer with expertise in creating clear, engaging
	content. You have a gift for explaining complex concepts in accessible language
	and organizing information in a way that helps readers build their understanding.

 # You can use mlflow context manager to log any param or metric values. One example is shown below
 with mlflow.start_run():
     mlflow.log_param("param_name", param_value)
     mlflow.log_metric("metric_name", metric_value)