Faiss

Langchain vector store for FAISS. Supports save/load to disk.

Install

pip install langchain-faiss-vectorstore

or

uv add langchain-faiss-vectorstore

API Reference

__init__

def __init__(
    self,
    embedding_function: Embeddings | None = None,
    index: faiss.Index | None = None,
    **kwargs,
)

Parameter	Type	Description
embedding_function	Embeddings | None	Embedding function used to embed queries and texts (e.g., FastEmbedEmbeddings).
index	faiss.Index | None	Optional pre-built FAISS index. If None, creates an IndexIDMap wrapping IndexFlatL2 with dimension 0 (auto-sized on first add_texts).

---

from_texts

def from_texts(
    cls,
    texts: list[str],
    embedding: Embeddings | None = None,
    metadatas: list[dict] | None = None,
    ids: list[str] | None = None,
    **kwargs,
) -> Faiss

Parameter	Type	Description
texts	list[str]	Texts to index.
embedding	Embeddings | None	Embedding function.
metadatas	list[dict] | None	Optional metadata dicts, one per text.
ids	list[str] | None	Optional document IDs. Auto-generated if not provided.

Returns: Faiss — a new vector store with the texts indexed.

---

add_texts

def add_texts(
    self,
    texts: list[str],
    metadatas: list[dict] | None = None,
    ids: list[str] | None = None,
    **kwargs,
) -> list[str]

Parameter	Type	Description
texts	list[str]	Texts to add to the index.
metadatas	list[dict] | None	Optional metadata dicts, one per text. Defaults to {}.
ids	list[str] | None	Optional document IDs. Auto-generated if not provided.

Returns: list[str] — the IDs of the added texts.

---

delete

def delete(
    self,
    ids: list[str] | None = None,
    **kwargs,
) -> bool | None

Parameter	Type	Description
ids	list[str] | None	List of document IDs to remove.

Returns: bool — True if deletion succeeded. Raises ValueError if ids is None.

---

similarity_search

def similarity_search(
    self,
    query: str,
    k: int = 4,
    **kwargs,
) -> list[Document]

Parameter	Type	Description
query	str	Query text.
k	int	Number of documents to return. Default 4.

Returns: list[Document] — documents most similar to the query, ordered by L2 distance (ascending).

---

similarity_search_with_score

def similarity_search_with_score(
    self,
    query: str,
    k: int = 4,
    **kwargs,
) -> list[tuple[Document, float]]

Parameter	Type	Description
query	str	Query text.
k	int	Number of documents to return. Default 4.

Returns: list[tuple[Document, float]] — tuples of (Document, L2_distance). Lower distance = more similar.

---

save_local

def save_local(
    self,
    folder_path: str | Path,
) -> None

Parameter	Type	Description
folder_path	str | Path	Directory to save the index and document data. Created if it doesn't exist.

Writes two files into folder_path:

• index.faiss — the serialized FAISS index.
• docs.json — document contents and metadata.

---

load_local

def load_local(
    cls,
    folder_path: str | Path,
    embedding_function: Embeddings,
    allow_dangerous_deserialization: bool = False,
) -> Faiss

Parameter	Type	Description
folder_path	str | Path	Directory containing index.faiss and docs.json.
embedding_function	Embeddings	Embedding function to use for future queries.
allow_dangerous_deserialization	bool	Safety flag (acknowledged). Default False.

Returns: Faiss — a restored vector store instance.