OllamaEmbeddings Class — langchain Architecture

Architecture documentation for the OllamaEmbeddings class in embeddings.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  0c74773d_9131_7802_d6df_f19bff9e4247["OllamaEmbeddings"]
  b1e4f760_c634_d3bf_ca9a_db7ab899cc4a["Embeddings"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|extends| b1e4f760_c634_d3bf_ca9a_db7ab899cc4a
  3e58a54c_dcc6_1588_0a1f_39de205758ef["embeddings.py"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|defined in| 3e58a54c_dcc6_1588_0a1f_39de205758ef
  ed61a297_f8eb_5ecc_600b_c3611d9d8499["_default_params()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| ed61a297_f8eb_5ecc_600b_c3611d9d8499
  dbc1866e_deaa_7ac7_a687_6050b5213b30["_set_clients()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| dbc1866e_deaa_7ac7_a687_6050b5213b30
  05b784d6_9929_b505_8950_cd1c3c4296a3["embed_documents()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| 05b784d6_9929_b505_8950_cd1c3c4296a3
  28d29cd2_4f8f_d548_96c7_0edf8c40fb71["embed_query()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| 28d29cd2_4f8f_d548_96c7_0edf8c40fb71
  6da257f1_8f04_1bab_2705_6a6c38ec8575["aembed_documents()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| 6da257f1_8f04_1bab_2705_6a6c38ec8575
  889b8605_e993_3a76_573b_2207ae285cbe["aembed_query()"]
  0c74773d_9131_7802_d6df_f19bff9e4247 -->|method| 889b8605_e993_3a76_573b_2207ae285cbe

Relationship Graph

Source Code

libs/partners/ollama/langchain_ollama/embeddings.py lines 19–332

class OllamaEmbeddings(BaseModel, Embeddings):
    """Ollama embedding model integration.

    Set up a local Ollama instance:
        [Install the Ollama package](https://github.com/ollama/ollama) and set up a
        local Ollama instance.

        You will need to choose a model to serve.

        You can view a list of available models via [the model library](https://ollama.com/library).

        To fetch a model from the Ollama model library use `ollama pull <name-of-model>`.

        For example, to pull the llama3 model:

        ```bash
        ollama pull llama3
        ```

        This will download the default tagged version of the model.
        Typically, the default points to the latest, smallest sized-parameter model.

        * On Mac, the models will be downloaded to `~/.ollama/models`
        * On Linux (or WSL), the models will be stored at `/usr/share/ollama/.ollama/models`

        You can specify the exact version of the model of interest
        as such `ollama pull vicuna:13b-v1.5-16k-q4_0`.

        To view pulled models:

        ```bash
        ollama list
        ```

        To start serving:

        ```bash
        ollama serve
        ```

        View the Ollama documentation for more commands.

        ```bash
        ollama help
        ```

    Install the `langchain-ollama` integration package:
        ```bash
        pip install -U langchain_ollama
        ```

    Key init args — completion params:
        model: str
            Name of Ollama model to use.
        base_url: str | None
            Base url the model is hosted under.

    See full list of supported init args and their descriptions in the params section.

    Instantiate:
        ```python
        from langchain_ollama import OllamaEmbeddings

        embed = OllamaEmbeddings(model="llama3")
        ```

    Embed single text:
        ```python
        input_text = "The meaning of life is 42"
        vector = embed.embed_query(input_text)
        print(vector[:3])
        ```

        ```python
        [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915]
        ```

    Embed multiple texts:
        ```python
        input_texts = ["Document 1...", "Document 2..."]
        vectors = embed.embed_documents(input_texts)