Prompt Symbol Standard Technology - 88.6% token reduction with perfect semantic fidelity
Achieving 80-90% token reduction with perfect semantic fidelity
PSST (Prompt Symbol Standard Technology) is a revolutionary token-efficient AI prompting system that reduces prompt length by 88.6% while maintaining perfect semantic fidelity. It works by mapping frequently used phrases to compact Unicode symbols, dramatically reducing API costs for AI applications.
# Run the installation script
./install_psst.sh
# Or install manually
python3 -m pip install jellyfish numpy
# Compress a file (88.6% reduction)
python3 psst_ultimate.py compress input.txt
# Expand a compressed file
python3 psst_ultimate.py expand input_ultimate.psst --output expanded.txt
# Verify perfect fidelity
diff input.txt expanded.txt
# Should return no differences
Original (543 characters):
Please act as a legal assistant. Highlight key rulings and arguments in the case below.
Summarize the following text in 3 bullet points.
Respond in a warm, casual tone when explaining the legal concepts to make them accessible to the client.
Case Details:
The plaintiff filed a motion for summary judgment claiming breach of contract. The defendant argues that the contract was void due to mutual mistake regarding the property's zoning classification. The court must determine whether the evidence shows a genuine issue of material fact.
Compressed (62 characters):
Please act as a legal assistant. 🔍
⊕summarize
🎨
📋
📜 ⚔️ 🏗️
Results: 88.6% compression with perfect fidelity!
| System | Compression | Fidelity | Best For |
|---|---|---|---|
| Ultimate PSST | 88.6% | Perfect | Production |
| Dynamic Learning | 80-90% | High | Learning |
| Enhanced PSST | 87.1% | High | Semantic |
psst_ultimate.py)Production-ready system with maximum compression and perfect fidelity
# Basic compression
python3 psst_ultimate.py compress input.txt
# With custom output
python3 psst_ultimate.py compress input.txt --output compressed.psst
# With custom glossary
python3 psst_ultimate.py compress input.txt --glossary custom.json
dynamic_psst_compiler.py)Self-improving system that learns patterns automatically
# Learn from files
python3 psst-learn learn input.txt
python3 psst-learn batch-learn /path/to/prompts/
# Compress with learning
python3 psst-learn compress input.txt
# Check statistics
python3 psst-learn stats
enhanced_psst_compiler.py)Semantic preservation with domain-specific optimization
# Enhanced compression
python3 enhanced_psst_compiler.py compress input.txt
# Enhanced expansion
python3 enhanced_psst_compiler.py expand input_enhanced.psst
psst_hybrid_integration.py)Production-ready OpenAI integration with hybrid approach
# Basic usage
python3 psst_hybrid_integration.py --prompt "Your prompt here"
# PSST response
python3 psst_hybrid_integration.py --prompt "Analyze this case" --psst-response
# CLI wrapper
./psst-hybrid "Your prompt here"
./psst-hybrid "Analyze this case" --psst-response
Create domain-specific glossaries for better compression:
{
"version": "3.0.0",
"glossary": {
"⚖️": "You are a legal assistant. Highlight key rulings and arguments in the case below.",
"🔍": "Analyze the following text and identify key issues.",
"📄": "Summarize the following text in 3 bullet points.",
"💻": "Implement the following functionality in Python:",
"🔧": "Debug the following code and provide fixes:"
}
}
from psst_ultimate import UltimatePsstCompiler
# Initialize
compiler = UltimatePsstCompiler()
# Compress text
compressed = compiler.compress("Your text here")
# Expand text
expanded = compiler.expand(compressed)
# Get statistics
stats = compiler.get_compression_stats(original, compressed)
from psst_hybrid_integration import PsstHybridIntegration
# Initialize with API key
integration = PsstHybridIntegration(api_key="your-api-key")
# Send prompt with hybrid approach
result = integration.send_hybrid_prompt("Your prompt here")
# Get AI response with PSST symbols
result = integration.send_with_psst_response("Analyze this case")
# Basic usage
./psst-hybrid "Your prompt here"
# PSST response (AI responds with symbols)
./psst-hybrid "Analyze this case" --psst-response
# Force expansion approach
./psst-hybrid "Complex analysis" --force-expansion
import openai
from psst_ultimate import UltimatePsstCompiler
compiler = UltimatePsstCompiler()
compressed_prompt = compiler.compress(original_prompt)
response = openai.ChatCompletion.create(
model="gpt-4",
messages=[{"role": "user", "content": compressed_prompt}]
)
# Process all .txt files
for file in *.txt; do
python3 psst_ultimate.py compress "$file"
done
# Check results
ls -la *.psst
| Model | Original Cost | PSST Cost | Monthly Savings |
|---|---|---|---|
| GPT-4 | $320/month | $36/month | $284/month |
| GPT-3.5 | $21/month | $2.40/month | $18.60/month |
Total annual savings: $3,636 (GPT-4) or $223 (GPT-3.5)
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Original │ │ PSST │ │ Compressed │
│ Prompt │───▶│ Compressor │───▶│ Output │
│ (543 chars) │ │ │ │ (62 chars) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│
▼
┌─────────────────┐
│ Glossary │
│ (Symbols) │
└─────────────────┘
./install_psst.sh
python3 psst_ultimate.py compress examples/legal_prompt.txt
# Create a test file
echo "Your prompt content here" > test.txt
# Compress it
python3 psst_ultimate.py compress test.txt
# Expand it
python3 psst_ultimate.py expand test_ultimate.psst --output test_expanded.txt
# Verify fidelity
diff test.txt test_expanded.txt
# Clone the repository
git clone https://github.com/your-repo/psst.git
cd psst
# Install dependencies
python3 -m pip install jellyfish numpy
# Run tests
python3 psst_ultimate.py compress examples/legal_prompt.txt
PSST is open-source software. See the LICENSE file for details.
examples/ directory# Python not found
python3 --version
# Missing dependencies
python3 -m pip install jellyfish numpy
# Poor compression
python3 psst-learn learn input.txt
# Expansion mismatch
python3 psst_ultimate.py expand input.psst --output test.txt
diff original.txt test.txt
PSST: Prompt Symbol Standard Technology
Version: 3.0.0 | Compression: 88.6% | Fidelity: Perfect
Target: 80-90% token reduction with perfect semantic fidelity
FAQs
Prompt Symbol Standard Technology - 88.6% token reduction with perfect semantic fidelity
We found that psst-toolkit demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
/Security News
Two npm packages masquerading as WhatsApp developer libraries include a kill switch that deletes all files if the phone number isn’t whitelisted.
Research
/Security News
Socket uncovered 11 malicious Go packages using obfuscated loaders to fetch and execute second-stage payloads via C2 domains.
Security News
TC39 advances 11 JavaScript proposals, with two moving to Stage 4, bringing better math, binary APIs, and more features one step closer to the ECMAScript spec.