maximal_marginal_relevance() — langchain Function Reference

Architecture documentation for the maximal_marginal_relevance() function in vectorstores.py from the langchain codebase.

Function python CoreAbstractions MessageSchema calls 1 called by 1

Entity Profile

CoreAbstractions→ MessageSchema→ maximal_marginal_relevance() — langchain Function Reference

Dependency Diagram

graph TD
  55b0a21b_5337_4fdd_b25d_653f07cfa6f7["maximal_marginal_relevance()"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef["vectorstores.py"]
  55b0a21b_5337_4fdd_b25d_653f07cfa6f7 -->|defined in| d4a05de9_1f0f_3b21_8171_181bb47227ef
  378e0b38_bb8f_784a_79fc_8a1db9ac20d6["max_marginal_relevance_search_by_vector()"]
  378e0b38_bb8f_784a_79fc_8a1db9ac20d6 -->|calls| 55b0a21b_5337_4fdd_b25d_653f07cfa6f7
  1a299491_e5bd_b5e4_d5ab_33de41c800e1["cosine_similarity()"]
  55b0a21b_5337_4fdd_b25d_653f07cfa6f7 -->|calls| 1a299491_e5bd_b5e4_d5ab_33de41c800e1
  style 55b0a21b_5337_4fdd_b25d_653f07cfa6f7 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/chroma/langchain_chroma/vectorstores.py lines 109–152

def maximal_marginal_relevance(
    query_embedding: np.ndarray,
    embedding_list: list,
    lambda_mult: float = 0.5,
    k: int = 4,
) -> list[int]:
    """Calculate maximal marginal relevance.

    Args:
        query_embedding: Query embedding.
        embedding_list: List of embeddings to select from.
        lambda_mult: Number between `0` and `1` that determines the degree
            of diversity among the results with `0` corresponding
            to maximum diversity and `1` to minimum diversity.
        k: Number of Documents to return.

    Returns:
        List of indices of embeddings selected by maximal marginal relevance.
    """
    if min(k, len(embedding_list)) <= 0:
        return []
    if query_embedding.ndim == 1:
        query_embedding = np.expand_dims(query_embedding, axis=0)
    similarity_to_query = cosine_similarity(query_embedding, embedding_list)[0]
    most_similar = int(np.argmax(similarity_to_query))
    idxs = [most_similar]
    selected = np.array([embedding_list[most_similar]])
    while len(idxs) < min(k, len(embedding_list)):
        best_score = -np.inf
        idx_to_add = -1
        similarity_to_selected = cosine_similarity(embedding_list, selected)
        for i, query_score in enumerate(similarity_to_query):
            if i in idxs:
                continue
            redundant_score = max(similarity_to_selected[i])
            equation_score = (
                lambda_mult * query_score - (1 - lambda_mult) * redundant_score
            )
            if equation_score > best_score:
                best_score = equation_score
                idx_to_add = i
        idxs.append(idx_to_add)
        selected = np.append(selected, [embedding_list[idx_to_add]], axis=0)
    return idxs