References
This module provides functions and classes for embedding queries, files, and directories using different embedding models.
The module includes the following functions:
embed_query
: Embeds the given query and returns an EmbedData object.embed_file
: Embeds the file at the given path and returns a list of EmbedData objects.embed_directory
: Embeds all the files in the given directory and returns a list of EmbedData objects.
The module also includes the EmbedData
class, which represents the data of an embedded file.
Usage:
-
To embed a query, use the
embed_query
function:embed_query(query: list[str], embeder: str) -> list[EmbedData]
-
To embed a file, use the
embed_file
function:embed_file(file_path: str, embeder: str) -> list[EmbedData]
-
To embed a directory, use the
embed_directory
function:embed_directory(file_path: str, embeder: str) -> list[EmbedData]
The EmbedData
class has the following attributes:
- embedding
: The embedding of the file.
- text
: The text for which the embedding is generated for.
- metadata
: Additional metadata associated with the embedding.
Supported Embedding Models:
-
Text Embedding Models:
- "OpenAI"
- "Bert"
-
Image Embedding Models:
- "Clip"
-
Audio Embedding Models:
- "Whisper-Bert"
EmbedData
Represents the data of an embedded file.
Attributes:
Name | Type | Description |
---|---|---|
embedding |
list[float]
|
The embedding of the file. |
text |
str
|
The text for which the embedding is generated for. |
metadata |
dict[str, str]
|
Additional metadata associated with the embedding. |
Source code in python/embed_anything/embed_anything.pyi
82 83 84 85 86 87 88 89 90 91 92 93 94 |
|
embed_directory(file_path, embeder)
Embeds all the files in the given directory and returns a list of EmbedData objects.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
file_path |
str
|
The path to the directory containing the files to embed. |
required |
embeder |
str
|
The name of the embedding model to use. Choose between "OpenAI" and "Bert" |
required |
Returns: - A list of EmbedData objects.
Source code in python/embed_anything/embed_anything.pyi
70 71 72 73 74 75 76 77 78 79 80 |
|
embed_file(file_path, embeder)
Embeds the file at the given path and returns a list of EmbedData objects.
- Text -> "OpenAI", "Bert"
- Image -> "Clip"
- Audio -> "Whisper-Bert"
Parameters:
Name | Type | Description | Default |
---|---|---|---|
file_path |
str
|
The path to the file to embed. |
required |
embeder |
str
|
The name of the embedding model to use. |
required |
Returns:
Type | Description |
---|---|
list[EmbedData]
|
A list of EmbedData objects. |
Source code in python/embed_anything/embed_anything.pyi
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
|
embed_query(query, embeder)
Embeds the given query and returns an EmbedData object.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
query |
list[str]
|
The query to embed. |
required |
embeder |
str
|
The name of the embedding model to use. Choose between "OpenAI" and "Bert" |
required |
Returns:
Type | Description |
---|---|
list[EmbedData]
|
An EmbedData object. |
Source code in python/embed_anything/embed_anything.pyi
42 43 44 45 46 47 48 49 50 51 |
|