llama_index.embedding.requests

LlamaIndex embedding operations consume excessive tokens due to redundant document processing, lack of caching, or inefficient chunking strategies, increasing costs and latency.

Embedding API failures during document indexing or query time cause incomplete indexes or degraded retrieval quality without proper error handling and retry logic.

Document embedding during indexing is inefficient due to small batch sizes or lack of batching, causing excessive API calls, increased latency, and higher costs compared to batch processing.