_load_hyde_chain() — langchain Function Reference

Architecture documentation for the _load_hyde_chain() function in loading.py from the langchain codebase.

Function python AgentOrchestration ClassicChains calls 2

Entity Profile

AgentOrchestration→ ClassicChains→ _load_hyde_chain() — langchain Function Reference

Dependency Diagram

graph TD
  4ddb582b_99b9_6a77_bef5_4f9ee7f6cf2e["_load_hyde_chain()"]
  61dd5a0b_3bf7_b973_6dac_edfd465b21fb["loading.py"]
  4ddb582b_99b9_6a77_bef5_4f9ee7f6cf2e -->|defined in| 61dd5a0b_3bf7_b973_6dac_edfd465b21fb
  7c915b91_f326_1908_9969_d0cb1f4f7e34["load_chain_from_config()"]
  4ddb582b_99b9_6a77_bef5_4f9ee7f6cf2e -->|calls| 7c915b91_f326_1908_9969_d0cb1f4f7e34
  ab90e794_4e78_646b_dee9_e87a00250d94["load_chain()"]
  4ddb582b_99b9_6a77_bef5_4f9ee7f6cf2e -->|calls| ab90e794_4e78_646b_dee9_e87a00250d94
  style 4ddb582b_99b9_6a77_bef5_4f9ee7f6cf2e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/loading.py lines 96–115

def _load_hyde_chain(config: dict, **kwargs: Any) -> HypotheticalDocumentEmbedder:
    """Load hypothetical document embedder chain from config dict."""
    if "llm_chain" in config:
        llm_chain_config = config.pop("llm_chain")
        llm_chain = load_chain_from_config(llm_chain_config, **kwargs)
    elif "llm_chain_path" in config:
        llm_chain = load_chain(config.pop("llm_chain_path"), **kwargs)
    else:
        msg = "One of `llm_chain` or `llm_chain_path` must be present."
        raise ValueError(msg)
    if "embeddings" in kwargs:
        embeddings = kwargs.pop("embeddings")
    else:
        msg = "`embeddings` must be present."
        raise ValueError(msg)
    return HypotheticalDocumentEmbedder(
        llm_chain=llm_chain,
        base_embeddings=embeddings,
        **config,
    )