embeddings.py — langchain Source File

Source Code

"""Ollama embeddings models."""

from __future__ import annotations

from typing import Any

from langchain_core.embeddings import Embeddings
from ollama import AsyncClient, Client
from pydantic import BaseModel, ConfigDict, PrivateAttr, model_validator
from typing_extensions import Self

from langchain_ollama._utils import (
    merge_auth_headers,
    parse_url_with_auth,
    validate_model,
)


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.

// ... (273 more lines)