VLite(
self,
embedding_function: Embeddings,
collection: Optional[str] = None,
**kwargs| Name | Type |
|---|---|
| embedding_function | Embeddings |
| collection | Optional[str] |
VLite is a simple and fast vector database for semantic search.
Run more texts through the embeddings and add to the vectorstore.
Add a list of documents to the vectorstore.
Return docs most similar to query.
Return docs most similar to query.
Update an existing document in the vectorstore.
Get documents by their IDs.
Delete by ids.
Load an existing VLite index.
Construct VLite wrapper from raw documents.
This is a user-friendly interface that:
This is intended to be a quick way to get started.
Example: .. code-block:: python
from langchain import VLite
from langchain_classic.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
vlite = VLite.from_texts(texts, embeddings)
Construct VLite wrapper from a list of documents.
This is a user-friendly interface that:
This is intended to be a quick way to get started.
Example: .. code-block:: python
from langchain import VLite
from langchain_classic.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
vlite = VLite.from_documents(documents, embeddings)