Documentation Index
Fetch the complete documentation index at: https://docs.cyborg.co/llms.txt
Use this file to discover all available pages before exploring further.
Generates embeddings for the given texts using the configured embedding model.
Available in Embedded and Python SDK. The JS/TS SDK handles embedding generation internally.
get_embeddings(texts: Union[str, List[str]]) -> np.ndarray
Parameters
| Parameter | Type | Description |
|---|
texts | Union[str, List[str]] | Single text string or list of text strings to embed |
Returns
np.ndarray: NumPy array of embeddings
- If single text: 1-D array of shape
(dimension,)
- If list of texts: 2-D array of shape
(num_texts, dimension)
Exceptions
- Throws if no embedding model is available
- Throws if embedding model type is not supported
Example Usage
# Single text embedding
embedding = store.get_embeddings("Hello, world!")
print(f"Embedding shape: {embedding.shape}") # (384,)
# Multiple text embeddings
texts = ["First document", "Second document", "Third document"]
embeddings = store.get_embeddings(texts)
print(f"Embeddings shape: {embeddings.shape}") # (3, 384)
get_embeddings(texts: Union[str, List[str]]) -> np.ndarray
Parameters
| Parameter | Type | Description |
|---|
texts | Union[str, List[str]] | Single text string or list of text strings to embed |
Returns
np.ndarray: NumPy array of embeddings
- If single text: 1-D array of shape
(dimension,)
- If list of texts: 2-D array of shape
(num_texts, dimension)
Delegates to the configured LangChain Embeddings object for embedding generation.Example Usage
embedding = store.get_embeddings("Hello, world!")
print(f"Embedding shape: {embedding.shape}") # (384,)
texts = ["First document", "Second document"]
embeddings = store.get_embeddings(texts)
print(f"Embeddings shape: {embeddings.shape}") # (2, 384)
