index_builder.py

import os, json
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from transcription import run_whisper_transcription
from lc_utils import segments_to_documents
from logging_config import logger

EMBED_MODEL = "sentence-transformers/all-MiniLM-L6-v2"


def build_index(media_path: str, out_dir: str = "data"):
    """Transcribe media_path and build a FAISS index in out_dir."""
    try:
        logger.info(f"Starting transcription for {media_path}")
        
        # Ensure output directory exists
        os.makedirs(out_dir, exist_ok=True)
        
        # Run Whisper transcription
        segments = run_whisper_transcription(media_path)
        if not segments:
            raise ValueError("No transcription segments were generated")
            
        logger.info(f"Transcription complete. Generated {len(segments)} segments.")
        
        # Convert to documents
        docs = segments_to_documents(segments, media_path)
        
        # Create embeddings and build index
        logger.info("Creating embeddings...")
        embeddings = HuggingFaceEmbeddings(model_name=EMBED_MODEL)
        
        logger.info("Building FAISS index...")
        store = FAISS.from_documents(docs, embeddings)
        
        # Save the index and segments
        store.save_local(out_dir)
        segments_path = os.path.join(out_dir, "segments.json")
        with open(segments_path, "w") as f:
            json.dump(segments, f)
            
        logger.info(f"Index successfully written to {out_dir}")
        return store
        
    except Exception as e:
        logger.error(f"Error in build_index: {str(e)}", exc_info=True)
        raise


if __name__ == "__main__":
    import sys

    if len(sys.argv) != 2:
        print("Usage: python index_builder.py <media_path>")
        sys.exit(1)
    build_index(sys.argv[1])