@classmethod
from_documents(
documents: List[Document],
embedding: Union[str, Embeddings, SentenceTransformer],
**kwargs
) -> CyborgVectorStore
Parameters
| Parameter | Type | Description |
|---|---|---|
documents | List[Document] | List of LangChain Document objects |
embedding | Union[str, Embeddings, SentenceTransformer] | Embedding model or model name |
**kwargs | Any | Additional arguments passed to from_texts |
Returns
CyborgVectorStore: Initialized vector store with documents added
Example Usage
from langchain_core.documents import Document
from cyborgdb_core import DBConfig
# Create documents
documents = [
Document(
page_content="Introduction to natural language processing",
metadata={"source": "nlp_guide.pdf", "page": 1}
),
Document(
page_content="Tokenization and text preprocessing",
metadata={"source": "nlp_guide.pdf", "page": 15}
),
Document(
page_content="Word embeddings and semantic similarity",
metadata={"source": "nlp_guide.pdf", "page": 42}
)
]
# Create store from documents
store = CyborgVectorStore.from_documents(
documents=documents,
embedding="sentence-transformers/all-mpnet-base-v2",
index_name="nlp_documents",
index_key=CyborgVectorStore.generate_key(save=True),
api_key="your-api-key",
index_location=DBConfig("memory"),
config_location=DBConfig("memory")
)