langsmith.py — langchain Source File

Source Code

"""LangSmith document loader."""

import datetime
import json
import uuid
from collections.abc import Callable, Iterator, Sequence
from typing import Any

from langsmith import Client as LangSmithClient
from typing_extensions import override

from langchain_core.document_loaders.base import BaseLoader
from langchain_core.documents import Document
from langchain_core.tracers._compat import pydantic_to_dict


class LangSmithLoader(BaseLoader):
    """Load LangSmith Dataset examples as `Document` objects.

    Loads the example inputs as the `Document` page content and places the entire
    example into the `Document` metadata. This allows you to easily create few-shot
    example retrievers from the loaded documents.

    ??? example "Lazy loading"

        ```python
        from langchain_core.document_loaders import LangSmithLoader

        loader = LangSmithLoader(dataset_id="...", limit=100)
        docs = []
        for doc in loader.lazy_load():
            docs.append(doc)
        ```

        ```python
        # -> [Document("...", metadata={"inputs": {...}, "outputs": {...}, ...}), ...]
        ```
    """

    def __init__(
        self,
        *,
        dataset_id: uuid.UUID | str | None = None,
        dataset_name: str | None = None,
        example_ids: Sequence[uuid.UUID | str] | None = None,
        as_of: datetime.datetime | str | None = None,
        splits: Sequence[str] | None = None,
        inline_s3_urls: bool = True,
        offset: int = 0,
        limit: int | None = None,
        metadata: dict | None = None,
        filter: str | None = None,  # noqa: A002
        content_key: str = "",
        format_content: Callable[..., str] | None = None,
        client: LangSmithClient | None = None,
        **client_kwargs: Any,
    ) -> None:
        """Create a LangSmith loader.

        Args:
// ... (84 more lines)