InMemoryVectorStore Class — langchain Architecture

Architecture documentation for the InMemoryVectorStore class in in_memory.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  aca2549c_644c_9cf1_03c9_ee00daa0cf81["InMemoryVectorStore"]
  9d2a2799_754f_4de7_e4e6_081d8ea620e0["VectorStore"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|extends| 9d2a2799_754f_4de7_e4e6_081d8ea620e0
  eb1e92dc_3a47_90f7_13c1_755c92499dc6["in_memory.py"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|defined in| eb1e92dc_3a47_90f7_13c1_755c92499dc6
  a1922a1a_912b_609d_d433_8a2532f2a72d["__init__()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| a1922a1a_912b_609d_d433_8a2532f2a72d
  d14ed12a_5076_d4b8_cbe0_5bd2bef5a2dd["embeddings()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| d14ed12a_5076_d4b8_cbe0_5bd2bef5a2dd
  65ea77d3_d5cd_2930_3ebe_0b4059b5d282["delete()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| 65ea77d3_d5cd_2930_3ebe_0b4059b5d282
  a5151b07_8782_9466_29b2_6df15bd1c297["adelete()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| a5151b07_8782_9466_29b2_6df15bd1c297
  557a1ecd_355d_48cb_2a6e_9b9305511155["add_documents()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| 557a1ecd_355d_48cb_2a6e_9b9305511155
  fb3be94a_25d7_d4ae_d705_fd7f03009c39["aadd_documents()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| fb3be94a_25d7_d4ae_d705_fd7f03009c39
  cbda0446_eb8e_ed27_3028_57b7f98d103c["get_by_ids()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| cbda0446_eb8e_ed27_3028_57b7f98d103c
  bf59d277_fba5_2eac_22c6_532bd2afc538["aget_by_ids()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| bf59d277_fba5_2eac_22c6_532bd2afc538
  9bec299a_baf3_fdf5_93a1_256035671565["_similarity_search_with_score_by_vector()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| 9bec299a_baf3_fdf5_93a1_256035671565
  1570a5e6_2ce6_e0a2_369f_cbe0aee465ce["similarity_search_with_score_by_vector()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| 1570a5e6_2ce6_e0a2_369f_cbe0aee465ce
  49567762_9dfd_9b31_5408_4b2976edc7da["similarity_search_with_score()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| 49567762_9dfd_9b31_5408_4b2976edc7da
  c22130e3_6028_83c3_978e_cce8c6aabc6b["asimilarity_search_with_score()"]
  aca2549c_644c_9cf1_03c9_ee00daa0cf81 -->|method| c22130e3_6028_83c3_978e_cce8c6aabc6b

Relationship Graph

Source Code

libs/core/langchain_core/vectorstores/in_memory.py lines 34–546

class InMemoryVectorStore(VectorStore):
    """In-memory vector store implementation.

    Uses a dictionary, and computes cosine similarity for search using numpy.

    Setup:
        Install `langchain-core`.

        ```bash
        pip install -U langchain-core
        ```

    Key init args — indexing params:

        * embedding_function: Embeddings
            Embedding function to use.

    Instantiate:
        ```python
        from langchain_core.vectorstores import InMemoryVectorStore
        from langchain_openai import OpenAIEmbeddings

        vector_store = InMemoryVectorStore(OpenAIEmbeddings())
        ```

    Add Documents:
        ```python
        from langchain_core.documents import Document

        document_1 = Document(id="1", page_content="foo", metadata={"baz": "bar"})
        document_2 = Document(id="2", page_content="thud", metadata={"bar": "baz"})
        document_3 = Document(id="3", page_content="i will be deleted :(")

        documents = [document_1, document_2, document_3]
        vector_store.add_documents(documents=documents)
        ```

    Inspect documents:
        ```python
        top_n = 10
        for index, (id, doc) in enumerate(vector_store.store.items()):
            if index < top_n:
                # docs have keys 'id', 'vector', 'text', 'metadata'
                print(f"{id}: {doc['text']}")
            else:
                break
        ```

    Delete Documents:
        ```python
        vector_store.delete(ids=["3"])
        ```

    Search:
        ```python
        results = vector_store.similarity_search(query="thud", k=1)
        for doc in results:
            print(f"* {doc.page_content} [{doc.metadata}]")
        ```

        ```txt
        * thud [{'bar': 'baz'}]
        ```

    Search with filter:
        ```python
        def _filter_function(doc: Document) -> bool:
            return doc.metadata.get("bar") == "baz"


        results = vector_store.similarity_search(
            query="thud", k=1, filter=_filter_function
        )
        for doc in results:
            print(f"* {doc.page_content} [{doc.metadata}]")
        ```

        ```txt
        * thud [{'bar': 'baz'}]
        ```