combine_embeddings() — langchain Function Reference

Architecture documentation for the combine_embeddings() function in base.py from the langchain codebase.

Function python AgentOrchestration ClassicChains called by 1

Entity Profile

AgentOrchestration→ ClassicChains→ combine_embeddings() — langchain Function Reference

Dependency Diagram

graph TD
  28b658bd_49a9_57f4_afd1_c492036ca171["combine_embeddings()"]
  4ca44101_1e0d_43e9_f420_35c5afe4173a["HypotheticalDocumentEmbedder"]
  28b658bd_49a9_57f4_afd1_c492036ca171 -->|defined in| 4ca44101_1e0d_43e9_f420_35c5afe4173a
  dcdba7e0_a4e9_895f_80dd_67dcdcbaa922["embed_query()"]
  dcdba7e0_a4e9_895f_80dd_67dcdcbaa922 -->|calls| 28b658bd_49a9_57f4_afd1_c492036ca171
  style 28b658bd_49a9_57f4_afd1_c492036ca171 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/hyde/base.py lines 56–76

    def combine_embeddings(self, embeddings: list[list[float]]) -> list[float]:
        """Combine embeddings into final embeddings."""
        try:
            import numpy as np

            return list(np.array(embeddings).mean(axis=0))
        except ImportError:
            logger.warning(
                "NumPy not found in the current Python environment. "
                "HypotheticalDocumentEmbedder will use a pure Python implementation "
                "for internal calculations, which may significantly impact "
                "performance, especially for large datasets. For optimal speed and "
                "efficiency, consider installing NumPy: pip install numpy",
            )
            if not embeddings:
                return []
            num_vectors = len(embeddings)
            return [
                sum(dim_values) / num_vectors
                for dim_values in zip(*embeddings, strict=False)
            ]