ehzawad

● 🔍 YOUR PROBLEMS (Comprehensive Summary)

Your core issue was that while your Bengali Legal RAG system achieved 94.7% test accuracy using EmbeddingGemma-300M, it suffered from four critical limitations that threatened scalability and real-world usability. First, Bengali linguistic confusion where syntactically similar legal terms like "khatian_correction" vs "khatian_copy" caused 11 classification errors due to EmbeddingGemma's 768D embedding space limitations and under-representation of Bengali legal terminology in multilingual training. Second, rigid threshold problems where your 0.932 FAISS threshold resulted in 0% complex query acceptance, while Linear Head's 0.60 threshold only achieved 14.3% acceptance - both failing to handle compound Bengali queries like "নামজারি করতে কি কি কাগজপত্র লাগে এবং কত টাকা লাগবে?" (documents + fee questions). Third, scalability anxiety about expanding from 14 tags to 200-300+ tags (evidenced by the EC dataset's 221 tags), where current O(n) FAISS complexity wou

ehzawad

examples/basic/hello_world.py
examples/basic/hello_world_gpt_5.py
examples/basic/hello_world_gpt_oss.py
examples/basic/stream_text.py
examples/basic/stream_items.py
examples/basic/stream_function_call_args.py
examples/basic/dynamic_system_prompt.py
examples/basic/prompt_template.py
examples/basic/agent_lifecycle_example.py
examples/basic/lifecycle_example.py

ehzawad

# PyTorch 2.x; Apple Silicon; runs on MPS if available, else CPU.
import math
import torch

if torch.backends.mps.is_available():  # official API to detect MPS
    device = torch.device("mps")
else:
    device = torch.device("cpu")

# --- Quantization helpers (per-tensor, symmetric) ---

ehzawad

import React, { useMemo, useRef, useState, useEffect } from "react";

// Simple FAISS-like toy: IndexFlatL2
class IndexFlatL2 {
  constructor(d) {
    this.d = d; // dimensionality
    this.vectors = []; // each item: {id, x: number[], label?: string}
    this._nextId = 1;
  }
  add(vecs) {

ehzawad

Looking at your GeForce RTX 2050 laptop GPU, here's what I recommend:

Best Driver Options for RTX 2050 Laptop:

1. nvidia-driver-575-open (RECOMMENDED)

• Version: 575.64.03
• Why: Ubuntu specifically recommends this for your RTX 2050
• Benefits for laptops: the driver also added NVIDIA Dynamic Boost support for Linux notebooks running on battery power
• CUDA: Fully compatible with CUDA 12.9

ehzawad

#!/usr/bin/env python3
"""
Run GPT-OSS using the Metal implementation for Apple Silicon
This requires downloading and converting the model first.
"""

import os
import subprocess
import sys

ehzawad

// file: vecadd_test.cu
#include <cstdio>
#include <cstdlib>

#define CUDA_CHECK(call) do {                                  \
    cudaError_t err = call;                                    \
    if (err != cudaSuccess) {                                  \
        fprintf(stderr, "CUDA error %s:%d: %s\n",             \
                __FILE__, __LINE__, cudaGetErrorString(err));  \
        exit(EXIT_FAILURE);                                   \

ehzawad

import re
from typing import Any, Text, Dict, List


bn_num_string = [
        'শূন্য', 'এক', 'দুই', 'তিন', 'চার', 'পাঁচ', 'ছয়', 'সাত', 'আট', 'নয়', 'দশ', 'এগারো', 'বারো', \
        'তেরো', 'চৌদ্দ', 'পনেরো', 'ষোলো', 'সতেরো', 'আঠারো', 'উনিশ','বিশ','একুশ', 'বাইশ', 'তেইশ', 'চব্বিশ', 'পঁচিশ', 'ছাব্বিশ', \
        'সাতাশ', 'আঠাশ', 'উনোতিরিশ', 'তিরিশ', 'একতিরিশ', 'বতিরিশ', 'তেতিরিশ', 'চৌতিরিশ', 'পঁয়তিরিশ', 'ছতিরিশ', 'সাঁইতিরিশ', 'আটতিরিশ', 'উনোচল্লিশ',\
        'চল্লিশ','একচল্লিশ', 'বিয়াল্লিশ', 'তেতাল্লিশ', 'চুয়াল্লিশ', 'পঁয়তাল্লিশ', 'ছেচল্লিশ', 'সাতচল্লিশ', 'আটচল্লিশ', 'উনোপঞ্চাশ', 'পঞ্চাশ', 'একান্ন',\
        'বাহান্ন', 'তিপ্পান্ন', 'চুয়ান্ন', 'পঞ্চান্ন', 'ছাপ্পান্ন', 'সাতান্ন', 'আটান্ন', 'উনোষাট','ষাট','একষট্টি', 'বাষট্টি', 'তেষট্টি', 'চৌষট্টি', 'পঁয়ষট্টি', \

ehzawad

---- resume-to-JSON prompt ----

parser_prompt = f""" You are an intelligent resume parser for the HR department. Read the raw CV text delimited by <<< and >>>, then return a single valid JSON object—no markdown, no commentary.

<<< {text}

Schema to follow exactly:

ehzawad

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.optim.lr_scheduler import ReduceLROnPlateau
from torch.utils.data import random_split, DataLoader
from multiprocessing import freeze_support

def main():