langchain/langchain/vectorstores/base.py

"""Interface for vector stores."""
from __future__ import annotations

from abc import ABC, abstractmethod
from typing import Any, Dict, Iterable, List, Optional

from pydantic import BaseModel, Field, root_validator

from langchain.docstore.document import Document
from langchain.embeddings.base import Embeddings
from langchain.schema import BaseRetriever


class VectorStore(ABC):
    """Interface for vector stores."""

    @abstractmethod
    def add_texts(
        self,
        texts: Iterable[str],
        metadatas: Optional[List[dict]] = None,
        **kwargs: Any,
    ) -> List[str]:
        """Run more texts through the embeddings and add to the vectorstore.

        Args:
            texts: Iterable of strings to add to the vectorstore.
            metadatas: Optional list of metadatas associated with the texts.
            kwargs: vectorstore specific parameters

        Returns:
            List of ids from adding the texts into the vectorstore.
        """

    def add_documents(self, documents: List[Document], **kwargs: Any) -> List[str]:
        """Run more documents through the embeddings and add to the vectorstore.

        Args:
            documents (List[Document]: Documents to add to the vectorstore.


        Returns:
            List[str]: List of IDs of the added texts.
        """
        # TODO: Handle the case where the user doesn't provide ids on the Collection
        texts = [doc.page_content for doc in documents]
        metadatas = [doc.metadata for doc in documents]
        return self.add_texts(texts, metadatas, **kwargs)

    @abstractmethod
    def similarity_search(
        self, query: str, k: int = 4, **kwargs: Any
    ) -> List[Document]:
        """Return docs most similar to query."""

    def similarity_search_by_vector(
        self, embedding: List[float], k: int = 4, **kwargs: Any
    ) -> List[Document]:
        """Return docs most similar to embedding vector.

        Args:
            embedding: Embedding to look up documents similar to.
            k: Number of Documents to return. Defaults to 4.

        Returns:
            List of Documents most similar to the query vector.
        """
        raise NotImplementedError

    def max_marginal_relevance_search(
        self, query: str, k: int = 4, fetch_k: int = 20
    ) -> List[Document]:
        """Return docs selected using the maximal marginal relevance.

        Maximal marginal relevance optimizes for similarity to query AND diversity
        among selected documents.

        Args:
            query: Text to look up documents similar to.
            k: Number of Documents to return. Defaults to 4.
            fetch_k: Number of Documents to fetch to pass to MMR algorithm.

        Returns:
            List of Documents selected by maximal marginal relevance.
        """
        raise NotImplementedError

    def max_marginal_relevance_search_by_vector(
        self, embedding: List[float], k: int = 4, fetch_k: int = 20
    ) -> List[Document]:
        """Return docs selected using the maximal marginal relevance.

        Maximal marginal relevance optimizes for similarity to query AND diversity
        among selected documents.

        Args:
            embedding: Embedding to look up documents similar to.
            k: Number of Documents to return. Defaults to 4.
            fetch_k: Number of Documents to fetch to pass to MMR algorithm.

        Returns:
            List of Documents selected by maximal marginal relevance.
        """
        raise NotImplementedError

    @classmethod
    def from_documents(
        cls,
        documents: List[Document],
        embedding: Embeddings,
        **kwargs: Any,
    ) -> VectorStore:
        """Return VectorStore initialized from documents and embeddings."""
        texts = [d.page_content for d in documents]
        metadatas = [d.metadata for d in documents]
        return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)

    @classmethod
    @abstractmethod
    def from_texts(
        cls,
        texts: List[str],
        embedding: Embeddings,
        metadatas: Optional[List[dict]] = None,
        **kwargs: Any,
    ) -> VectorStore:
        """Return VectorStore initialized from texts and embeddings."""

    def as_retriever(self, **kwargs: Any) -> BaseRetriever:
        return VectorStoreRetriever(vectorstore=self, **kwargs)


class VectorStoreRetriever(BaseRetriever, BaseModel):
    vectorstore: VectorStore
    search_type: str = "similarity"
    search_kwargs: dict = Field(default_factory=dict)

    class Config:
        """Configuration for this pydantic object."""

        arbitrary_types_allowed = True

    @root_validator()
    def validate_search_type(cls, values: Dict) -> Dict:
        """Validate search type."""
        if "search_type" in values:
            search_type = values["search_type"]
            if search_type not in ("similarity", "mmr"):
                raise ValueError(f"search_type of {search_type} not allowed.")
        return values

    def get_relevant_documents(self, query: str) -> List[Document]:
        if self.search_type == "similarity":
            docs = self.vectorstore.similarity_search(query, **self.search_kwargs)
        elif self.search_type == "mmr":
            docs = self.vectorstore.max_marginal_relevance_search(
                query, **self.search_kwargs
            )
        else:
            raise ValueError(f"search_type of {self.search_type} not allowed.")
        return docs

    async def aget_relevant_documents(self, query: str) -> List[Document]:
        raise NotImplementedError("VectorStoreRetriever does not support async")