Hugging Face's logo

jyotirmoy05
/
VivekanandaAI

GGUF
Model card Files
xet
 Community
VivekanandaAI
File size: 4,981 Bytes
e889148
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
#!/bin/bash

# ============================================================================
# VIVEKANANDA AI - AUTOMATED SETUP SCRIPT
# Sets up entire project structure and dependencies
# ============================================================================

set -e  # Exit on error

echo "========================================================================"
echo "🕉️  VIVEKANANDA AI - PROJECT SETUP"
echo "========================================================================"

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
NC='\033[0m' # No Color

# ============================================================================
# STEP 1: CREATE DIRECTORY STRUCTURE
# ============================================================================

echo ""
echo "${GREEN}[STEP 1/7] Creating directory structure...${NC}"

mkdir -p data/raw/complete_works
mkdir -p data/raw/individual_books
mkdir -p data/processed
mkdir -p data/extracted_text
mkdir -p vectorstore
mkdir -p models/base
mkdir -p models/fine_tuned
mkdir -p scripts
mkdir -p notebooks
mkdir -p outputs/logs
mkdir -p outputs/results

echo "✓ Directory structure created"

# ============================================================================
# STEP 2: CREATE PYTHON VIRTUAL ENVIRONMENT
# ============================================================================

echo ""
echo "${GREEN}[STEP 2/7] Creating Python virtual environment...${NC}"

if [ ! -d "venv" ]; then
    python3 -m venv venv
    echo "✓ Virtual environment created"
else
    echo "✓ Virtual environment already exists"
fi

# Activate virtual environment
source venv/bin/activate

# ============================================================================
# STEP 3: UPGRADE PIP
# ============================================================================

echo ""
echo "${GREEN}[STEP 3/7] Upgrading pip...${NC}"

pip install --upgrade pip setuptools wheel
echo "✓ Pip upgraded"

# ============================================================================
# STEP 4: INSTALL DEPENDENCIES
# ============================================================================

echo ""
echo "${GREEN}[STEP 4/7] Installing dependencies...${NC}"

if [ -f "requirements.txt" ]; then
    pip install -r requirements.txt
    echo "✓ Dependencies installed"
else
    echo "${RED}✗ requirements.txt not found!${NC}"
    exit 1
fi

# ============================================================================
# STEP 5: DOWNLOAD SPACY MODEL
# ============================================================================

echo ""
echo "${GREEN}[STEP 5/7] Downloading spaCy model...${NC}"

python -m spacy download en_core_web_sm
echo "✓ spaCy model downloaded"

# ============================================================================
# STEP 6: DOWNLOAD NLTK DATA
# ============================================================================

echo ""
echo "${GREEN}[STEP 6/7] Downloading NLTK data...${NC}"

python -c "
import nltk
nltk.download('punkt', quiet=True)
nltk.download('stopwords', quiet=True)
print('✓ NLTK data downloaded')
"

# ============================================================================
# STEP 7: VERIFY INSTALLATION
# ============================================================================

echo ""
echo "${GREEN}[STEP 7/7] Verifying installation...${NC}"

python -c "
import sys
import torch
import spacy
import nltk
from langchain import __version__ as lc_version

print(f'Python: {sys.version.split()[0]}')
print(f'PyTorch: {torch.__version__}')
print(f'spaCy: {spacy.__version__}')
print(f'NLTK: {nltk.__version__}')
print(f'LangChain: {lc_version}')

# Check device
if torch.backends.mps.is_available():
    print('Device: MPS (Apple Silicon) ✓')
elif torch.cuda.is_available():
    print('Device: CUDA ✓')
else:
    print('Device: CPU')
"

echo ""
echo "✓ Installation verified"

# ============================================================================
# FINAL INSTRUCTIONS
# ============================================================================

echo ""
echo "========================================================================"
echo "${GREEN}🎉 SETUP COMPLETE!${NC}"
echo "========================================================================"
echo ""
echo "Next steps:"
echo ""
echo "1. ${YELLOW}Add your data:${NC}"
echo "   - PDFs → data/raw/"
echo "   - JSON dataset → data/processed/"
echo "   - Mistral model → models/base/"
echo ""
echo "2. ${YELLOW}Configure:${NC}"
echo "   - Edit config.yaml to customize settings"
echo ""
echo "3. ${YELLOW}Create embeddings:${NC}"
echo "   source venv/bin/activate"
echo "   python scripts/01_embed_data.py"
echo ""
echo "4. ${YELLOW}Test RAG:${NC}"
echo "   python scripts/02_query_rag.py"
echo ""
echo "5. ${YELLOW}Run Streamlit:${NC}"
echo "   streamlit run app.py"
echo ""
echo "========================================================================"