check_index.py

#!/usr/bin/env python3
"""
Quick script to check what's saved in Elasticsearch
"""

from elasticsearch_indexer import ElasticsearchIndexer

def main():
    try:
        indexer = ElasticsearchIndexer()
    except Exception as e:
        print(f"Error connecting to Elasticsearch: {e}")
        return
    
    # Get index stats
    stats = indexer.get_index_stats('rag_chunks')
    if 'error' in stats:
        print(f"Error: {stats['error']}")
        return
    
    print(f"Index: rag_chunks")
    print(f"Total documents: {stats.get('document_count', 0)}")
    print("=" * 80)
    
    # Get all documents
    try:
        # Elasticsearch 8.x API
        response = indexer.client.search(
            index='rag_chunks',
            query={'match_all': {}},
            size=100,
            _source=['chunk_id', 'type', 'page', 'content', 'embedding_model', 'embedding_dim', 'metadata', 'document_info']
        )
    except Exception as e:
        # Fallback for older API
        try:
            response = indexer.client.search(
                index='rag_chunks',
                body={'query': {'match_all': {}}, 'size': 100},
                _source=['chunk_id', 'type', 'page', 'content', 'embedding_model', 'embedding_dim', 'metadata', 'document_info']
            )
        except Exception as e2:
            print(f"Error retrieving documents: {e2}")
            return
    
    print(f"\nRetrieved {len(response['hits']['hits'])} documents:\n")
    
    for i, hit in enumerate(response['hits']['hits'], 1):
        doc = hit['_source']
        print(f"[{i}] Chunk ID: {doc.get('chunk_id')} | Type: {doc.get('type')} | Page: {doc.get('page')}")
        content = doc.get('content', '')
        if len(content) > 150:
            content = content[:150] + '...'
        print(f"    Content: {content}")
        print()


if __name__ == "__main__":
    main()