Skip to main content

AI-powered marketing analysis framework using RAG technology

Project description

🍰 Tiramisu Framework

AI-powered marketing consultancy framework using RAG (Retrieval-Augmented Generation) technology with strategic marketing knowledge.

📦 Installation

pip install tiramisu-framework

🚀 Quick Start

from tiramisu_framework.engine.analyzer import TiramisuAnalyzer
from tiramisu_framework.models.schemas import AnalysisType

# Initialize analyzer
analyzer = TiramisuAnalyzer()

# Analyze content
result = analyzer.analyze(
    content="Your marketing content here",
    analysis_type=AnalysisType.SOCIAL_MEDIA_POST,
    context="Additional context"
)

print(result.summary)

⚠️ Important: Data Setup

This framework requires marketing knowledge data to function.

Setup Your Knowledge Base

  1. Add your marketing PDFs/documents to data/ folder
  2. Run the indexing script to create FAISS vectors
  3. The system will use your custom knowledge base

Note: This framework is designed to work with any marketing literature. Users must provide their own knowledge sources in compliance with copyright laws.

🏗️ Architecture

  • FastAPI backend with RESTful API
  • RAG System with FAISS vector store
  • GPT Integration for intelligent analysis
  • SQLite for conversation management
  • Pydantic for data validation

📚 Features

  • 8 types of marketing analysis
  • Conversation context management
  • Three Trees analysis framework (Roots, Trunk, Branches)
  • Multi-perspective expert insights (Strategic, Execution, Technology)
  • Structured JSON responses

🛠️ Development

# Clone repository
git clone https://github.com/tiramisu-framework/tiramisu-framework.git
cd tiramisu-framework

# Install dependencies
pip install -r requirements.txt

# Run API
python -m uvicorn api.main:app --reload

⚖️ Legal Disclaimer

This framework is a technical tool for marketing analysis. Users are responsible for:

  • Providing their own knowledge sources
  • Ensuring compliance with copyright laws
  • Obtaining necessary permissions for any copyrighted materials used

📄 License

MIT License - See LICENSE file for details

👨‍💻 Author

Developed by Jony Wolff with Claude AI assistance

🤝 Contributing

Contributions welcome! Please open an issue or submit a PR.

📚 Setting Up Your Knowledge Base

Important: This framework does not include pre-loaded content. You must provide your own marketing knowledge sources.

Steps:

  1. Add Your Documents:
   mkdir -p data/sources
   # Add your PDF/TXT files to data/sources/
  1. Index Your Content:
   python -m tiramisu_framework.scripts.index_documents
  1. Configure API Key:
   export OPENAI_API_KEY="your-key-here"

Recommended Sources:

  • Marketing strategy books and articles
  • Digital marketing guides
  • Industry reports and case studies
  • Your own proprietary content

Note: Ensure you have rights to use any content you add to the framework.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tiramisu_framework-0.1.2.tar.gz (25.4 kB view details)

Uploaded Source

File details

Details for the file tiramisu_framework-0.1.2.tar.gz.

File metadata

  • Download URL: tiramisu_framework-0.1.2.tar.gz
  • Upload date:
  • Size: 25.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for tiramisu_framework-0.1.2.tar.gz
Algorithm Hash digest
SHA256 bb3a56ee27f1e97607026219779bac5b7898938778339fe3608dd5b6579d4845
MD5 ee87ef24a11387e25ecf4fac60dfca9d
BLAKE2b-256 5580a9d1fb8cb3683f2e3199f1643108bdfef14019d46c958fcb33d741af0f63

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page