Metadata-Version: 2.2
Name: empire-chain
Version: 0.2.3
Summary: An orchestration framework for all your AI needs
Home-page: https://github.com/manas95826/empire-chain
Author: Manas Chopra
Author-email: manaschopra95826@gmail.com
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: openai
Requires-Dist: anthropic
Requires-Dist: groq
Requires-Dist: qdrant-client
Requires-Dist: chromadb
Requires-Dist: sentence-transformers
Requires-Dist: PyPDF2
Requires-Dist: python-docx
Dynamic: author
Dynamic: author-email
Dynamic: home-page
Dynamic: requires-python

An orchestration framework for all your AI needs.

## Installation

```bash
pip install empire_chain
```

## Usage

```python
from empire_chain.vector_stores import QdrantVectorStore
from empire_chain.embeddings import OpenAIEmbeddings
from empire_chain.llms import OpenAILLM
from empire_chain.file_reader import DocumentReader
import os
from dotenv import load_dotenv

def main():
    load_dotenv()
    
    vector_store = QdrantVectorStore(":memory:")
    embeddings = OpenAIEmbeddings("text-embedding-3-small")
    llm = OpenAILLM("gpt-4o-mini")
    reader = DocumentReader()
    
    file_path = "input.pdf"
    text = reader.read(file_path)
    
    text_embedding = embeddings.embed(text)
    vector_store.add(text, text_embedding)
    
    query = "What is the main topic of this document?"
    query_embedding = embeddings.embed(query)
    relevant_texts = vector_store.query(query_embedding, k=3)
    
    context = "\n".join(relevant_texts)
    prompt = f"Based on the following context, {query}\n\nContext: {context}"
    response = llm.generate(prompt)
    print(f"Query: {query}")
    print(f"Response: {response}")

if __name__ == "__main__":
    main()
```

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
