Skip to content

📚 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:

import embed_anything
from embed_anything import EmbedData

#For text files

model = EmbeddingModel.from_pretrained_local(
    WhichModel.Bert, model_id="Hugging_face_link"
)
data = embed_anything.embed_file("test_files/test.pdf", embeder=model)


#For images
model = embed_anything.EmbeddingModel.from_pretrained_local(
    embed_anything.WhichModel.Clip,
    model_id="openai/clip-vit-base-patch16",
    # revision="refs/pr/15",
)
data: list[EmbedData] = embed_anything.embed_directory("test_files", embeder=model)
embeddings = np.array([data.embedding for data in data])
query = ["Photo of a monkey?"]
query_embedding = np.array(
    embed_anything.embed_query(query, embeder=model)[0].embedding
)
# For audio files
from embed_anything import (
    AudioDecoderModel,
    EmbeddingModel,
    embed_audio_file,
    TextEmbedConfig,
)
# choose any whisper or distilwhisper model from https://huggingface.co/distil-whisper or https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013
audio_decoder = AudioDecoderModel.from_pretrained_hf(
    "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
)
embeder = EmbeddingModel.from_pretrained_hf(
    embed_anything.WhichModel.Bert,
    model_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="main",
)
config = TextEmbedConfig(chunk_size=200, batch_size=32)
data = embed_anything.embed_audio_file(
    "test_files/audio/samples_hp0.wav",
    audio_decoder=audio_decoder,
    embeder=embeder,
    text_embed_config=config,
)

You can also store the embeddings to a vector database and not keep them on memory. Here is an example of how to use the PineconeAdapter class:

import embed_anything
import os

from embed_anything.vectordb import PineconeAdapter


# Initialize the PineconeEmbedder class
api_key = os.environ.get("PINECONE_API_KEY")
index_name = "anything"
pinecone_adapter = PineconeAdapter(api_key)

try:
    pinecone_adapter.delete_index("anything")
except:
    pass

# Initialize the PineconeEmbedder class

pinecone_adapter.create_index(dimension=512, metric="cosine")

# bert_model = EmbeddingModel.from_pretrained_hf(
#     WhichModel.Bert, "sentence-transformers/all-MiniLM-L12-v2", revision="main"
# )

clip_model = EmbeddingModel.from_pretrained_hf(
    WhichModel.Clip, "openai/clip-vit-base-patch16", revision="main"
)

embed_config = TextEmbedConfig(chunk_size=512, batch_size=32)


data = embed_anything.embed_image_directory(
    "test_files",
    embeder=clip_model,
    adapter=pinecone_adapter,
    # config=embed_config,

Supported Embedding Models:

  • Text Embedding Models:

    • "OpenAI"
    • "Bert"
    • "Jina"

  • Image Embedding Models:

    • "Clip"
    • "SigLip" (Coming Soon)

  • Audio Embedding Models:

    • "Whisper"

AudioDecoderModel

Represents an audio decoder model.

Attributes:

Name Type Description
model_id str

The ID of the audio decoder model.
revision str

The revision of the audio decoder model.
model_type str

The type of the audio decoder model.
quantized bool

A flag indicating whether the audio decoder model is quantized or not.

Example: 

model = embed_anything.AudioDecoderModel.from_pretrained_hf(
    model_id="openai/whisper-tiny.en",
    revision="main",
    model_type="tiny-en",
    quantized=False
)

Source code in python/python/embed_anything/_embed_anything.pyi 
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
class AudioDecoderModel:
    """
    Represents an audio decoder model.

    Attributes:
        model_id: The ID of the audio decoder model.
        revision: The revision of the audio decoder model.
        model_type: The type of the audio decoder model.
        quantized: A flag indicating whether the audio decoder model is quantized or not.

    Example:
    ```python

    model = embed_anything.AudioDecoderModel.from_pretrained_hf(
        model_id="openai/whisper-tiny.en",
        revision="main",
        model_type="tiny-en",
        quantized=False
    )
    ```
    """

    model_id: str
    revision: str
    model_type: str
    quantized: bool

    def from_pretrained_hf(
        model_id: str | None = None,
        revision: str | None = None,
        model_type: str | None = None,
        quantized: bool | None = None,
    ): ...

ColpaliModel

Represents the Colpali model.

Source code in python/python/embed_anything/_embed_anything.pyi 
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
class ColpaliModel:
    """
    Represents the Colpali model.
    """

    def __init__(self, model_id: str, revision: str | None = None):
        """
        Initializes the ColpaliModel object.

        Args:
            model_id: The ID of the model from Hugging Face.
            revision: The revision of the model.
        """

    def from_pretrained(model_id: str, revision: str | None = None) -> ColpaliModel:
        """
        Loads a pre-trained Colpali model from the Hugging Face model hub.

        Args:
            model_id: The ID of the model from Hugging Face.
            revision: The revision of the model.

        Returns:
            A ColpaliModel object.
        """

    def from_pretrained_onnx(
        model_id: str, revision: str | None = None
    ) -> ColpaliModel:
        """
        Loads a pre-trained Colpali model from the Hugging Face model hub.

        Args:
            model_id: The ID of the model from Hugging Face.
            revision: The revision of the model.

        Returns:
            A ColpaliModel object.
        """

    def embed_file(self, file_path: str, batch_size: int | None = 1) -> list[EmbedData]:
        """
        Embeds the given pdf file and returns a list of EmbedData objects for each page in the file This first convert the pdf file into images and then embed each image.

        Args:
            file_path: The path to the pdf file to embed.
            batch_size: The batch size for processing the embeddings. Default is 1.

        Returns:
            A list of EmbedData objects for each page in the file.
        """

    def embed_query(self, query: str) -> list[EmbedData]:
        """
        Embeds the given query and returns a list of EmbedData objects.

        Args:
            query: The query to embed.

        Returns:
            A list of EmbedData objects.
        """

__init__(model_id, revision=None)

Initializes the ColpaliModel object.

Parameters:

Name Type Description Default
model_id str

The ID of the model from Hugging Face.

 required
revision str | None

The revision of the model.

 None
Source code in python/python/embed_anything/_embed_anything.pyi 
260
261
262
263
264
265
266
267
def __init__(self, model_id: str, revision: str | None = None):
    """
    Initializes the ColpaliModel object.

    Args:
        model_id: The ID of the model from Hugging Face.
        revision: The revision of the model.
    """

embed_file(file_path, batch_size=1)

Embeds the given pdf file and returns a list of EmbedData objects for each page in the file This first convert the pdf file into images and then embed each image.

Parameters:

Name Type Description Default
file_path str

The path to the pdf file to embed.

 required
batch_size int | None

The batch size for processing the embeddings. Default is 1.

 1

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects for each page in the file.
Source code in python/python/embed_anything/_embed_anything.pyi 
295
296
297
298
299
300
301
302
303
304
305
def embed_file(self, file_path: str, batch_size: int | None = 1) -> list[EmbedData]:
    """
    Embeds the given pdf file and returns a list of EmbedData objects for each page in the file This first convert the pdf file into images and then embed each image.

    Args:
        file_path: The path to the pdf file to embed.
        batch_size: The batch size for processing the embeddings. Default is 1.

    Returns:
        A list of EmbedData objects for each page in the file.
    """

embed_query(query)

Embeds the given query and returns a list of EmbedData objects.

Parameters:

Name Type Description Default
query str

The query to embed.

 required

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.
Source code in python/python/embed_anything/_embed_anything.pyi 
307
308
309
310
311
312
313
314
315
316
def embed_query(self, query: str) -> list[EmbedData]:
    """
    Embeds the given query and returns a list of EmbedData objects.

    Args:
        query: The query to embed.

    Returns:
        A list of EmbedData objects.
    """

from_pretrained(model_id, revision=None)

Loads a pre-trained Colpali model from the Hugging Face model hub.

Parameters:

Name Type Description Default
model_id str

The ID of the model from Hugging Face.

 required
revision str | None

The revision of the model.

 None

Returns:

Type Description
ColpaliModel

A ColpaliModel object.
Source code in python/python/embed_anything/_embed_anything.pyi 
269
270
271
272
273
274
275
276
277
278
279
def from_pretrained(model_id: str, revision: str | None = None) -> ColpaliModel:
    """
    Loads a pre-trained Colpali model from the Hugging Face model hub.

    Args:
        model_id: The ID of the model from Hugging Face.
        revision: The revision of the model.

    Returns:
        A ColpaliModel object.
    """

from_pretrained_onnx(model_id, revision=None)

Loads a pre-trained Colpali model from the Hugging Face model hub.

Parameters:

Name Type Description Default
model_id str

The ID of the model from Hugging Face.

 required
revision str | None

The revision of the model.

 None

Returns:

Type Description
ColpaliModel

A ColpaliModel object.
Source code in python/python/embed_anything/_embed_anything.pyi 
281
282
283
284
285
286
287
288
289
290
291
292
293
def from_pretrained_onnx(
    model_id: str, revision: str | None = None
) -> ColpaliModel:
    """
    Loads a pre-trained Colpali model from the Hugging Face model hub.

    Args:
        model_id: The ID of the model from Hugging Face.
        revision: The revision of the model.

    Returns:
        A ColpaliModel object.
    """

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/python/embed_anything/_embed_anything.pyi 
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
class EmbedData:
    """Represents the data of an embedded file.

    Attributes:
        embedding: The embedding of the file.
        text: The text for which the embedding is generated for.
        metadata: Additional metadata associated with the embedding.
    """

    def __init__(self, embedding: list[float], text: str, metadata: dict[str, str]):
        self.embedding = embedding
        self.text = text
        self.metadata = metadata
    embedding: list[float]
    text: str
    metadata: dict[str, str]

EmbeddingModel

Represents an embedding model.

Source code in python/python/embed_anything/_embed_anything.pyi 
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
class EmbeddingModel:
    """
    Represents an embedding model.
    """

    """
    Loads an embedding model from the Hugging Face model hub.

    Args:
        model_id: The ID of the model.
        revision: The revision of the model.

    Returns:
        An EmbeddingModel object.

    Example:
    ```python
    model = EmbeddingModel.from_pretrained_hf(
        model_id="prithivida/miniMiracle_te_v1",
        revision="main"
    )
    ```

    """
    def from_pretrained_hf(
        model: WhichModel, model_id: str, revision: str | None = None
    ) -> EmbeddingModel: ...

    """
    Loads an embedding model from a cloud-based service.

    Args:
        model (WhichModel): The cloud service to use. Currently supports WhichModel.OpenAI and WhichModel.Cohere.
        model_id (str): The ID of the model to use.
            - For OpenAI, see available models at https://platform.openai.com/docs/guides/embeddings/embedding-models
            - For Cohere, see available models at https://docs.cohere.com/docs/cohere-embed
        api_key (str | None, optional): The API key for accessing the model. If not provided, it is taken from the environment variable:
            - For OpenAI: OPENAI_API_KEY
            - For Cohere: CO_API_KEY

    Returns:
        EmbeddingModel: An initialized EmbeddingModel object.

    Raises:
        ValueError: If an unsupported model is specified.

    Example:
    ```python
    # Using Cohere
    model = EmbeddingModel.from_pretrained_cloud(
        model=WhichModel.Cohere, 
        model_id="embed-english-v3.0"
    )

    # Using OpenAI
    model = EmbeddingModel.from_pretrained_cloud(
        model=WhichModel.OpenAI, 
        model_id="text-embedding-3-small"
    )
    ```
    """
    def from_pretrained_cloud(
        model: WhichModel, model_id: str, api_key: str | None = None
    ) -> EmbeddingModel: ...
    """
    Loads an ONNX embedding model.

    Args:
        model_architecture (WhichModel): The architecture of the embedding model to use.
        model_id (str): The ID of the model.
        revision (str | None, optional): The revision of the model. Defaults to None.

    Returns:
        EmbeddingModel: An initialized EmbeddingModel object.

    Example:
    ```python
    model = EmbeddingModel.from_pretrained_onnx(
        model_architecture=WhichModel.Bert,
        model_id="BGESmallENV15Q"
    )
    ```

    Note:
    This method loads a pre-trained model in ONNX format, which can offer improved inference speed
    compared to standard PyTorch models. ONNX models are particularly useful for deployment
    scenarios where performance is critical.
    """
    def from_pretrained_onnx(
        model_architecture: WhichModel, model_id: str, revision: str | None = None
    ) -> EmbeddingModel: ...

ImageEmbedConfig

Represents the configuration for the Image Embedding model.

Attributes:

Name Type Description
buffer_size int | None

The buffer size for the Image Embedding model. Default is 100.
Source code in python/python/embed_anything/_embed_anything.pyi 
351
352
353
354
355
356
357
358
359
360
361
class ImageEmbedConfig:
    """
    Represents the configuration for the Image Embedding model.

    Attributes:
        buffer_size: The buffer size for the Image Embedding model. Default is 100.
    """

    def __init__(self, buffer_size: int | None = None):
        self.buffer_size = buffer_size
    buffer_size: int | None

ONNXModel

Bases: Enum

Enum representing various ONNX models.

| Enum Variant                     | Description                                      |
|----------------------------------|--------------------------------------------------|
| `AllMiniLML6V2`                  | sentence-transformers/all-MiniLM-L6-v2           |
| `AllMiniLML6V2Q`                 | Quantized sentence-transformers/all-MiniLM-L6-v2 |
| `AllMiniLML12V2`                 | sentence-transformers/all-MiniLM-L12-v2          |
| `AllMiniLML12V2Q`                | Quantized sentence-transformers/all-MiniLM-L12-v2|
| `BGEBaseENV15`                   | BAAI/bge-base-en-v1.5                            |
| `BGEBaseENV15Q`                  | Quantized BAAI/bge-base-en-v1.5                  |
| `BGELargeENV15`                  | BAAI/bge-large-en-v1.5                           |
| `BGELargeENV15Q`                 | Quantized BAAI/bge-large-en-v1.5                 |
| `BGESmallENV15`                  | BAAI/bge-small-en-v1.5 - Default                 |
| `BGESmallENV15Q`                 | Quantized BAAI/bge-small-en-v1.5                 |
| `NomicEmbedTextV1`               | nomic-ai/nomic-embed-text-v1                     |
| `NomicEmbedTextV15`              | nomic-ai/nomic-embed-text-v1.5                   |
| `NomicEmbedTextV15Q`             | Quantized nomic-ai/nomic-embed-text-v1.5         |
| `ParaphraseMLMiniLML12V2`        | sentence-transformers/paraphrase-MiniLM-L6-v2    |
| `ParaphraseMLMiniLML12V2Q`       | Quantized sentence-transformers/paraphrase-MiniLM-L6-v2 |
| `ParaphraseMLMpnetBaseV2`        | sentence-transformers/paraphrase-mpnet-base-v2   |
| `BGESmallZHV15`                  | BAAI/bge-small-zh-v1.5                           |
| `MultilingualE5Small`            | intfloat/multilingual-e5-small                   |
| `MultilingualE5Base`             | intfloat/multilingual-e5-base                    |
| `MultilingualE5Large`            | intfloat/multilingual-e5-large                   |
| `MxbaiEmbedLargeV1`              | mixedbread-ai/mxbai-embed-large-v1               |
| `MxbaiEmbedLargeV1Q`             | Quantized mixedbread-ai/mxbai-embed-large-v1     |
| `GTEBaseENV15`                   | Alibaba-NLP/gte-base-en-v1.5                     |
| `GTEBaseENV15Q`                  | Quantized Alibaba-NLP/gte-base-en-v1.5           |
| `GTELargeENV15`                  | Alibaba-NLP/gte-large-en-v1.5                    |
| `GTELargeENV15Q`                 | Quantized Alibaba-NLP/gte-large-en-v1.5          |
| `JINAV2SMALLEN`                  | jinaai/jina-embeddings-v2-small-en               |
| `JINAV2BASEEN`                   | jinaai/jina-embeddings-v2-base-en                |
| `JINAV2LARGEEN`                  | jinaai/jina-embeddings-v2-large-en               |
Source code in python/python/embed_anything/_embed_anything.pyi 
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
class ONNXModel(Enum):

    """
    Enum representing various ONNX models.

    ```markdown
    | Enum Variant                     | Description                                      |
    |----------------------------------|--------------------------------------------------|
    | `AllMiniLML6V2`                  | sentence-transformers/all-MiniLM-L6-v2           |
    | `AllMiniLML6V2Q`                 | Quantized sentence-transformers/all-MiniLM-L6-v2 |
    | `AllMiniLML12V2`                 | sentence-transformers/all-MiniLM-L12-v2          |
    | `AllMiniLML12V2Q`                | Quantized sentence-transformers/all-MiniLM-L12-v2|
    | `BGEBaseENV15`                   | BAAI/bge-base-en-v1.5                            |
    | `BGEBaseENV15Q`                  | Quantized BAAI/bge-base-en-v1.5                  |
    | `BGELargeENV15`                  | BAAI/bge-large-en-v1.5                           |
    | `BGELargeENV15Q`                 | Quantized BAAI/bge-large-en-v1.5                 |
    | `BGESmallENV15`                  | BAAI/bge-small-en-v1.5 - Default                 |
    | `BGESmallENV15Q`                 | Quantized BAAI/bge-small-en-v1.5                 |
    | `NomicEmbedTextV1`               | nomic-ai/nomic-embed-text-v1                     |
    | `NomicEmbedTextV15`              | nomic-ai/nomic-embed-text-v1.5                   |
    | `NomicEmbedTextV15Q`             | Quantized nomic-ai/nomic-embed-text-v1.5         |
    | `ParaphraseMLMiniLML12V2`        | sentence-transformers/paraphrase-MiniLM-L6-v2    |
    | `ParaphraseMLMiniLML12V2Q`       | Quantized sentence-transformers/paraphrase-MiniLM-L6-v2 |
    | `ParaphraseMLMpnetBaseV2`        | sentence-transformers/paraphrase-mpnet-base-v2   |
    | `BGESmallZHV15`                  | BAAI/bge-small-zh-v1.5                           |
    | `MultilingualE5Small`            | intfloat/multilingual-e5-small                   |
    | `MultilingualE5Base`             | intfloat/multilingual-e5-base                    |
    | `MultilingualE5Large`            | intfloat/multilingual-e5-large                   |
    | `MxbaiEmbedLargeV1`              | mixedbread-ai/mxbai-embed-large-v1               |
    | `MxbaiEmbedLargeV1Q`             | Quantized mixedbread-ai/mxbai-embed-large-v1     |
    | `GTEBaseENV15`                   | Alibaba-NLP/gte-base-en-v1.5                     |
    | `GTEBaseENV15Q`                  | Quantized Alibaba-NLP/gte-base-en-v1.5           |
    | `GTELargeENV15`                  | Alibaba-NLP/gte-large-en-v1.5                    |
    | `GTELargeENV15Q`                 | Quantized Alibaba-NLP/gte-large-en-v1.5          |
    | `JINAV2SMALLEN`                  | jinaai/jina-embeddings-v2-small-en               |
    | `JINAV2BASEEN`                   | jinaai/jina-embeddings-v2-base-en                |
    | `JINAV2LARGEEN`                  | jinaai/jina-embeddings-v2-large-en               |
    ```
    """

    AllMiniLML6V2 = "AllMiniLML6V2"

    AllMiniLML6V2Q = "AllMiniLML6V2Q"

    AllMiniLML12V2 = "AllMiniLML12V2"

    AllMiniLML12V2Q = "AllMiniLML12V2Q"

    BGEBaseENV15 = "BGEBaseENV15"

    BGEBaseENV15Q = "BGEBaseENV15Q"

    BGELargeENV15 = "BGELargeENV15"

    BGELargeENV15Q = "BGELargeENV15Q"

    BGESmallENV15 = "BGESmallENV15"

    BGESmallENV15Q = "BGESmallENV15Q"

    NomicEmbedTextV1 = "NomicEmbedTextV1"

    NomicEmbedTextV15 = "NomicEmbedTextV15"

    NomicEmbedTextV15Q = "NomicEmbedTextV15Q"

    ParaphraseMLMiniLML12V2 = "ParaphraseMLMiniLML12V2"

    ParaphraseMLMiniLML12V2Q = "ParaphraseMLMiniLML12V2Q"

    ParaphraseMLMpnetBaseV2 = "ParaphraseMLMpnetBaseV2"

    BGESmallZHV15 = "BGESmallZHV15"

    MultilingualE5Small = "MultilingualE5Small"

    MultilingualE5Base = "MultilingualE5Base"

    MultilingualE5Large = "MultilingualE5Large"

    MxbaiEmbedLargeV1 = "MxbaiEmbedLargeV1"

    MxbaiEmbedLargeV1Q = "MxbaiEmbedLargeV1Q"

    GTEBaseENV15 = "GTEBaseENV15"

    GTEBaseENV15Q = "GTEBaseENV15Q"

    GTELargeENV15 = "GTELargeENV15"

    GTELargeENV15Q = "GTELargeENV15Q"

    JINAV2SMALLEN = "JINAV2SMALLEN"

    JINAV2BASEEN = "JINAV2BASEEN"

    JINAV2LARGEEN = "JINAV2LARGEEN"

TextEmbedConfig

Represents the configuration for the Text Embedding model.

Attributes:

Name Type Description
chunk_size int | None

The chunk size for the Text Embedding model.
batch_size int | None

The batch size for processing the embeddings. Default is 32. Based on the memory, you can increase or decrease the batch size.
splitting_strategy

The strategy to use for splitting the text into chunks. Default is "sentence".
semantic_encoder EmbeddingModel | None

The semantic encoder for the Text Embedding model. Default is None.
use_ocr bool | None

A flag indicating whether to use OCR for the Text Embedding model. Default is False.
Source code in python/python/embed_anything/_embed_anything.pyi 
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
class TextEmbedConfig:
    """
    Represents the configuration for the Text Embedding model.

    Attributes:
        chunk_size: The chunk size for the Text Embedding model.
        batch_size: The batch size for processing the embeddings. Default is 32. Based on the memory, you can increase or decrease the batch size.
        splitting_strategy: The strategy to use for splitting the text into chunks. Default is "sentence".
        semantic_encoder: The semantic encoder for the Text Embedding model. Default is None.
        use_ocr: A flag indicating whether to use OCR for the Text Embedding model. Default is False.
    """

    def __init__(
        self,
        chunk_size: int | None = 256,
        batch_size: int | None = 32,
        buffer_size: int | None = 100,
        splitting_strategy: str | None = "sentence",
        semantic_encoder: EmbeddingModel | None = None,
        use_ocr: bool | None = False,
    ):
        self.chunk_size = chunk_size
        self.batch_size = batch_size
        self.buffer_size = buffer_size
        self.splitting_strategy = splitting_strategy
        self.semantic_encoder = semantic_encoder
        self.use_ocr = use_ocr
    chunk_size: int | None
    batch_size: int | None
    buffer_size: int | None
    semantic_encoder: EmbeddingModel | None
    use_ocr: bool | None

embed_audio_file(file_path, audio_decoder, embeder, text_embed_config=TextEmbedConfig(chunk_size=200, batch_size=32))

Embeds the given audio file and returns a list of EmbedData objects.

Parameters:

Name Type Description Default
file_path str

The path to the audio file to embed.

 required
audio_decoder AudioDecoderModel

The audio decoder model to use.

 required
embeder EmbeddingModel

The embedding model to use.

 required
text_embed_config TextEmbedConfig | None

The configuration for the embedding model.

 TextEmbedConfig(chunk_size=200, batch_size=32)

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.

Example: 

import embed_anything
audio_decoder = embed_anything.AudioDecoderModel.from_pretrained_hf(
    "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
)

embeder = embed_anything.EmbeddingModel.from_pretrained_hf(
    embed_anything.WhichModel.Bert,
    model_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="main",
)

config = embed_anything.TextEmbedConfig(chunk_size=200, batch_size=32)
data = embed_anything.embed_audio_file(
    "test_files/audio/samples_hp0.wav",
    audio_decoder=audio_decoder,
    embeder=embeder,
    text_embed_config=config,
)

Source code in python/python/embed_anything/_embed_anything.pyi 
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
def embed_audio_file(
    file_path: str,
    audio_decoder: AudioDecoderModel,
    embeder: EmbeddingModel,
    text_embed_config: TextEmbedConfig | None = TextEmbedConfig(
        chunk_size=200, batch_size=32
    ),
) -> list[EmbedData]:
    """
    Embeds the given audio file and returns a list of EmbedData objects.

    Args:
        file_path: The path to the audio file to embed.
        audio_decoder: The audio decoder model to use.
        embeder: The embedding model to use.
        text_embed_config: The configuration for the embedding model.

    Returns:
        A list of EmbedData objects.

    Example:
    ```python

    import embed_anything
    audio_decoder = embed_anything.AudioDecoderModel.from_pretrained_hf(
        "openai/whisper-tiny.en", revision="main", model_type="tiny-en", quantized=False
    )

    embeder = embed_anything.EmbeddingModel.from_pretrained_hf(
        embed_anything.WhichModel.Bert,
        model_id="sentence-transformers/all-MiniLM-L6-v2",
        revision="main",
    )

    config = embed_anything.TextEmbedConfig(chunk_size=200, batch_size=32)
    data = embed_anything.embed_audio_file(
        "test_files/audio/samples_hp0.wav",
        audio_decoder=audio_decoder,
        embeder=embeder,
        text_embed_config=config,
    )
    ```

    """

embed_directory(file_path, embeder, extensions, config=None, adapter=None)

Embeds 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 EmbeddingModel

The embedding model to use.

 required
extensions list[str]

The list of file extensions to consider for embedding.

 required
config TextEmbedConfig | None

The configuration for the embedding model.

 None
adapter Adapter | None

The adapter to use for storing the embeddings in a vector database.

 None

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.

Example: 

import embed_anything
model = embed_anything.EmbeddingModel.from_pretrained_hf(
    embed_anything.WhichModel.Bert,
    model_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="main",
)
data = embed_anything.embed_directory("test_files", embeder=model, extensions=[".pdf"])

Source code in python/python/embed_anything/_embed_anything.pyi 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
def embed_directory(
    file_path: str,
    embeder: EmbeddingModel,
    extensions: list[str],
    config: TextEmbedConfig | None = None,
    adapter: Adapter | None = None,
) -> list[EmbedData]:
    """
    Embeds the files in the given directory and returns a list of EmbedData objects.

    Args:
        file_path: The path to the directory containing the files to embed.
        embeder: The embedding model to use.
        extensions: The list of file extensions to consider for embedding.
        config: The configuration for the embedding model.
        adapter: The adapter to use for storing the embeddings in a vector database.

    Returns:
        A list of EmbedData objects.

    Example:
    ```python
    import embed_anything
    model = embed_anything.EmbeddingModel.from_pretrained_hf(
        embed_anything.WhichModel.Bert,
        model_id="sentence-transformers/all-MiniLM-L6-v2",
        revision="main",
    )
    data = embed_anything.embed_directory("test_files", embeder=model, extensions=[".pdf"])
    ```
    """

embed_file(file_path, embeder, config=None, adapter=None)

Embeds the given file and returns a list of EmbedData objects.

Parameters:

Name Type Description Default
file_path str

The path to the file to embed.

 required
embeder EmbeddingModel

The embedding model to use.

 required
config TextEmbedConfig | None

The configuration for the embedding model.

 None
adapter Adapter | None

The adapter to use for storing the embeddings in a vector database.

 None

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.

Example: 

import embed_anything
model = embed_anything.EmbeddingModel.from_pretrained_hf(
    embed_anything.WhichModel.Bert,
    model_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="main",
)
data = embed_anything.embed_file("test_files/test.pdf", embeder=model)

Source code in python/python/embed_anything/_embed_anything.pyi 
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
def embed_file(
    file_path: str,
    embeder: EmbeddingModel,
    config: TextEmbedConfig | None = None,
    adapter: Adapter | None = None,
) -> list[EmbedData]:
    """
    Embeds the given file and returns a list of EmbedData objects.

    Args:
        file_path: The path to the file to embed.
        embeder: The embedding model to use.
        config: The configuration for the embedding model.
        adapter: The adapter to use for storing the embeddings in a vector database.

    Returns:
        A list of EmbedData objects.

    Example:
    ```python
    import embed_anything
    model = embed_anything.EmbeddingModel.from_pretrained_hf(
        embed_anything.WhichModel.Bert,
        model_id="sentence-transformers/all-MiniLM-L6-v2",
        revision="main",
    )
    data = embed_anything.embed_file("test_files/test.pdf", embeder=model)
    ```
    """

embed_image_directory(file_path, embeder, config=None, adapter=None)

Embeds the images 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 images to embed.

 required
embeder EmbeddingModel

The embedding model to use.

 required
config ImageEmbedConfig | None

The configuration for the embedding model.

 None
adapter Adapter | None

The adapter to use for storing the embeddings in a vector database.

 None

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.
Source code in python/python/embed_anything/_embed_anything.pyi 
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
def embed_image_directory(
    file_path: str,
    embeder: EmbeddingModel,
    config: ImageEmbedConfig | None = None,
    adapter: Adapter | None = None,
) -> list[EmbedData]:
    """
    Embeds the images in the given directory and returns a list of EmbedData objects.

    Args:
        file_path: The path to the directory containing the images to embed.
        embeder: The embedding model to use.
        config: The configuration for the embedding model.
        adapter: The adapter to use for storing the embeddings in a vector database.

    Returns:
        A list of EmbedData objects.
    """

embed_query(query, embeder, config=None)

Embeds the given query and returns a list of EmbedData objects.

Parameters:

Name Type Description Default
query list[str]

The query to embed.

 required
embeder EmbeddingModel

The embedding model to use.

 required
config TextEmbedConfig | None

The configuration for the embedding model.

 None

Returns:

Type Description
list[EmbedData]

A list of EmbedData objects.

Example:

import embed_anything
model = embed_anything.EmbeddingModel.from_pretrained_hf(
    embed_anything.WhichModel.Bert,
    model_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="main",
)
Source code in python/python/embed_anything/_embed_anything.pyi 
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
def embed_query(
    query: list[str], embeder: EmbeddingModel, config: TextEmbedConfig | None = None
) -> list[EmbedData]:
    """
    Embeds the given query and returns a list of EmbedData objects.

    Args:
        query: The query to embed.
        embeder: The embedding model to use.
        config: The configuration for the embedding model.

    Returns:
        A list of EmbedData objects.

    Example:

    ```python
    import embed_anything
    model = embed_anything.EmbeddingModel.from_pretrained_hf(
        embed_anything.WhichModel.Bert,
        model_id="sentence-transformers/all-MiniLM-L6-v2",
        revision="main",
    )
    ```
    """

embed_webpage(url, embeder, config, adapter)

Embeds the webpage at the given URL and returns a list of EmbedData objects.

Parameters:

Name Type Description Default
url str

The URL of the webpage to embed.

 required
embeder EmbeddingModel

The name of the embedding model to use. Choose between "OpenAI", "Jina", "Bert"

 required
config TextEmbedConfig | None

The configuration for the embedding model.

 required
adapter Adapter | None

The adapter to use for storing the embeddings.

 required

Returns:

Type Description
list[EmbedData] | None

A list of EmbedData objects

Example: 

import embed_anything

config = embed_anything.EmbedConfig(
    openai_config=embed_anything.OpenAIConfig(model="text-embedding-3-small")
)
data = embed_anything.embed_webpage(
    "https://www.akshaymakes.com/", embeder="OpenAI", config=config
)

Source code in python/python/embed_anything/_embed_anything.pyi 
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
def embed_webpage(
    url: str,
    embeder: EmbeddingModel,
    config: TextEmbedConfig | None,
    adapter: Adapter | None,
) -> list[EmbedData] | None:
    """Embeds the webpage at the given URL and returns a list of EmbedData
    objects.

    Args:
        url: The URL of the webpage to embed.
        embeder: The name of the embedding model to use. Choose between "OpenAI", "Jina", "Bert"
        config: The configuration for the embedding model.
        adapter: The adapter to use for storing the embeddings.

    Returns:
        A list of EmbedData objects

    Example:
    ```python
    import embed_anything

    config = embed_anything.EmbedConfig(
        openai_config=embed_anything.OpenAIConfig(model="text-embedding-3-small")
    )
    data = embed_anything.embed_webpage(
        "https://www.akshaymakes.com/", embeder="OpenAI", config=config
    )
    ```
    """