beekeeper-ai 0.6.6__py3-none-any.whl → 1.0.1__py3-none-any.whl

beekeeper_ai-1.0.1.dist-info/METADATA

@@ -0,0 +1,46 @@
+Metadata-Version: 2.4
+Name: beekeeper-ai
+Version: 1.0.1
+Summary: Load any data in one line of code and connect with AI applications
+Project-URL: Documentation, https://beekeeper-ai.github.io/beekeeper
+Project-URL: Repository, https://github.com/beekeeper-ai/beekeeper
+Author-email: Leonardo Furnielis <leonardofurnielis@outlook.com>
+License: Apache-2.0
+License-File: LICENSE
+Keywords: AI,LLM,QA,RAG,data,observability,retrieval,semantic-search
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: <4.0,>=3.10
+Requires-Dist: beekeeper-core<2.0.0,>=1.0.1
+Requires-Dist: beekeeper-embeddings-huggingface<2.0.0,>=1.0.0
+Requires-Dist: beekeeper-llms-litellm<2.0.0,>=1.0.0
+Requires-Dist: beekeeper-readers-file<2.0.0,>=1.0.0
+Provides-Extra: dev
+Requires-Dist: ruff>=0.11.13; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: furo>=2024.8.6; extra == 'docs'
+Requires-Dist: sphinx-copybutton>=0.5.2; extra == 'docs'
+Requires-Dist: sphinx-favicon>=1.0.1; extra == 'docs'
+Requires-Dist: sphinx>=8.1.3; extra == 'docs'
+Description-Content-Type: text/markdown
+
+# 🗂️ Beekeeper 🐝
+
+![PyPI - Version](https://img.shields.io/pypi/v/beekeeper-ai)
+[![Hatch project](https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg)](https://github.com/pypa/hatch)
+![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)
+![Pepy Total Downloads](https://img.shields.io/pepy/dt/beekeeper-ai)
+![PyPI - License](https://img.shields.io/pypi/l/beekeeper-ai)
+
+## Installation 
+
+```bash
+pip install beekeeper-ai
+```
+
+## 📄 Documentation
+
+The documentation can be found Click [here](https://beekeeper-ai.github.io/beekeeper/)!
+
+Please check it out for overview of the interfaces, components, integrations and other resources!

beekeeper_ai-1.0.1.dist-info/RECORD

@@ -0,0 +1,5 @@
+beekeeper/_bundle/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+beekeeper_ai-1.0.1.dist-info/METADATA,sha256=FzTW4lyNBMp8AODDS34MLYex8dZKVnqlSLHNsEVxs1s,1955
+beekeeper_ai-1.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+beekeeper_ai-1.0.1.dist-info/licenses/LICENSE,sha256=bR2Wj7Il7KNny38LiDGrASo12StUfpReF--OewXD5cw,10349
+beekeeper_ai-1.0.1.dist-info/RECORD,,

{beekeeper_ai-0.6.6.dist-info → beekeeper_ai-1.0.1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any

beekeeper_ai-1.0.1.dist-info/licenses/LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

beekeeper/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.6.6"

beekeeper/core/document/__init__.py

@@ -1,6 +0,0 @@
-from beekeeper.core.document.schema import Document, DocumentWithScore
-
-__all__ = [
-    "Document",
-    "DocumentWithScore"
-]

beekeeper/core/document/schema.py

@@ -1,97 +0,0 @@
-import uuid
-from abc import ABC, abstractmethod
-from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any, Dict, Optional
-
-from pydantic.v1 import BaseModel, Field, validator
-
-if TYPE_CHECKING:
-    from langchain_core.documents import Document as LangChainDocument
-
-
-class BaseDocument(ABC, BaseModel):
-    """Generic abstract interface for retrievable documents."""
-
-    doc_id: str = Field(
-        default_factory=lambda: str(uuid.uuid4()),
-        description="Unique ID of the document.")
-    metadata: Dict[str, Any] = Field(
-        default_factory=dict,
-        description="A flat dictionary of metadata fields.")
-
-    @validator("metadata", pre=True)
-    def _validate_metadata(cls, v) -> Dict:
-        if v is None:
-            return {}
-        return v
-
-    @abstractmethod
-    def get_content(self) -> str:
-        """Get document content."""
-
-    @abstractmethod
-    def get_metadata(self) -> str:
-        """Get metadata."""
-
-
-class Document(BaseDocument):
-    """Generic interface for data document."""
-
-    text: str = Field(default="", description="Text content of the document.")
-
-    @classmethod
-    def class_name(cls) -> str:
-        return "Document"
-
-    def get_content(self) -> str:
-        """Get the text content."""
-        return self.text
-
-    def get_metadata(self) -> dict:
-        """Get metadata."""
-        return self.metadata
-
-    @classmethod
-    def from_langchain_format(cls, doc: "LangChainDocument") -> "Document":
-        """
-        Convert a document from LangChain  format.
-
-        Args:
-            doc (LangChainDocument): Document in LangChain format.
-        """
-        return cls(text=doc.page_content, metadata=doc.metadata)
-
-
-@dataclass
-class DocumentWithScore:
-    document: BaseDocument
-    score: Optional[float] = None
-
-    @classmethod
-    def class_name(cls) -> str:
-        return "DocumentWithScore"
-
-    def get_score(self) -> float:
-        """Get score."""
-        if self.score is None:
-            return 0.0
-        else:
-            return self.score
-
-    # #### pass through methods to BaseDocument ####
-    @property
-    def doc_id(self) -> str:
-        return self.document.doc_id
-
-    @property
-    def text(self) -> str:
-        if isinstance(self.document, Document):
-            return self.document.text
-        else:
-            raise ValueError("Must be a Document to get text")
-
-    def get_content(self) -> str:
-        return self.document.get_content()
-
-    def get_metadata(self) -> str:
-        return self.document.get_metadata()

beekeeper/core/document_loaders/__init__.py

@@ -1,5 +0,0 @@
-from beekeeper.core.document_loaders.base import BaseLoader
-
-__all__ = [
-    "BaseLoader",
-]

beekeeper/core/document_loaders/base.py

@@ -1,24 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List, Optional
-
-from pydantic.v1 import BaseModel
-
-from beekeeper.core.document import Document
-
-
-class BaseLoader(ABC, BaseModel):
-    """An interface for document loader."""
-
-    @classmethod
-    def class_name(cls) -> str:
-        return "BaseLoader"
-
-    @abstractmethod
-    def load_data(self, extra_info: Optional[dict] = None) -> List[Document]:
-        """Loads data."""
-
-    def load(self) -> List[Document]:
-        return self.load_data()
-
-    def lazy_load(self) -> List[Document]:
-        return self.load_data()

beekeeper/core/embeddings/__init__.py

@@ -1,6 +0,0 @@
-from beekeeper.core.embeddings.base import BaseEmbedding, Embedding
-
-__all__ = [
-    "BaseEmbedding",
-    "Embedding",
-]

beekeeper/core/embeddings/base.py

@@ -1,44 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List, Literal
-
-import numpy as np
-
-from beekeeper.core.utils.pairwise import cosine_similarity
-
-Embedding = List[float]
-
-
-class BaseEmbedding(ABC):
-    """An interface for embedding models."""
-
-    @classmethod
-    def class_name(cls) -> str:
-        return "BaseEmbedding"
-
-    @abstractmethod
-    def get_query_embedding(self, query: str) -> Embedding:
-        """Get query embedding."""
-
-    @abstractmethod
-    def get_texts_embedding(self, texts: List[str]) -> List[Embedding]:
-        """Get text embeddings."""
-
-    @abstractmethod
-    def get_documents_embedding(self, documents: List[str]) -> List[Embedding]:
-        """Get documents embeddings."""
-
-    def embed_documents(self, texts: List[str]) -> List[Embedding]:
-        return self.get_texts_embedding(texts=texts)
-
-    @staticmethod
-    def similarity(embedding1: Embedding, embedding2: Embedding,
-                   mode: Literal["cosine", "dot_product", "euclidean"] = "cosine"):
-        """Get embedding similarity."""
-        if mode == "euclidean":
-            return -float(np.linalg.norm(np.array(embedding1) - np.array(embedding2)))
-
-        elif mode == "dot_product":
-            return np.dot(embedding1, embedding2)
-
-        else:
-            return cosine_similarity(embedding1, embedding2)

beekeeper/core/text_splitters/utils.py

@@ -1,142 +0,0 @@
-from typing import Callable, List, Tuple
-
-
-def tokenizer(text: str) -> List:
-    try:
-        import tiktoken
-    except ImportError:
-        raise ImportError("tiktoken package not found, please install it with `pip install tiktoken`")
-
-    enc = tiktoken.get_encoding("cl100k_base")
-    return enc.encode(text)
-
-
-def split_by_sep(sep) -> Callable[[str], List[str]]:
-    """Split text by separator."""
-    return lambda text: text.split(sep)
-
-
-def split_by_regex(regex: str) -> Callable[[str], List[str]]:
-    """Split text by regex."""
-    import re
-
-    return lambda text: re.findall(regex, text)
-
-
-def split_by_char() -> Callable[[str], List[str]]:
-    """Split text by character."""
-    return lambda text: list(text)
-
-
-def split_by_sentence_tokenizer() -> Callable[[str], List[str]]:
-    try:
-        import nltk
-    except ImportError:
-        raise ImportError("nltk package not found, please install it with `pip install nltk`")
-
-    sentence_tokenizer = nltk.tokenize.PunktSentenceTokenizer()
-    return lambda text: _split_by_sentence_tokenizer(text, sentence_tokenizer)
-
-
-def _split_by_sentence_tokenizer(text: str, sentence_tokenizer) -> List[str]:
-    """Get the spans and then return the sentences.
-
-    Using the start index of each span
-    Instead of using end, use the start of the next span
-    """
-    spans = list(sentence_tokenizer.span_tokenize(text))
-    sentences = []
-    for i, span in enumerate(spans):
-        start = span[0]
-        if i < len(spans) - 1:
-            end = spans[i + 1][0]
-        else:
-            end = len(text)
-        sentences.append(text[start:end])
-    return sentences
-
-
-def split_by_fns(text: str,
-                 split_fns: List[Callable],
-                 sub_split_fns: List[Callable] = None) -> Tuple[List[str], bool]:
-    """Split text by defined list of split functions."""
-    if not split_fns:
-        raise ValueError("Must provide a `split_fns` parameter")
-
-    for split_fn in split_fns:
-        splits = split_fn(text)
-        if len(splits) > 1:
-            return splits, True
-
-    if sub_split_fns: # noqa: RET503
-        for split_fn in sub_split_fns: # noqa: RET503
-            splits = split_fn(text)
-            if len(splits) > 1:
-                return splits, False
-
-
-def merge_splits(splits: List[dict],
-                 chunk_size: int,
-                 chunk_overlap: int) -> List[str]:
-    """Merge splits into chunks."""
-    chunks: List[str] = []
-    cur_chunk: List[Tuple[str, int]] = []
-    cur_chunk_len = 0
-    last_chunk: List[Tuple[str, int]] = []
-    new_chunk = True
-
-    def close_chunk() -> None:
-        nonlocal chunks, cur_chunk, last_chunk, cur_chunk_len, new_chunk
-
-        chunks.append("".join([text for text, length in cur_chunk]))
-        last_chunk = cur_chunk
-        cur_chunk = []
-        cur_chunk_len = 0
-        new_chunk = True
-
-        # add overlap to the next chunk using previous chunk
-        if len(last_chunk) > 0:
-            last_index = len(last_chunk) - 1
-            while (
-                    last_index >= 0
-                    and cur_chunk_len + last_chunk[last_index][1] <= chunk_overlap):
-                text, length = last_chunk[last_index]
-                cur_chunk_len += length
-                cur_chunk.insert(0, (text, length))
-                last_index -= 1
-
-    def postprocess_chunks(_chunks: List[str]) -> List[str]:
-        """Post-process chunks."""
-        post_chunks = []
-        for _chunk in _chunks:
-            stripped_chunk = _chunk.strip()
-            if stripped_chunk == "":
-                continue
-            post_chunks.append(stripped_chunk)
-        return post_chunks
-
-    while len(splits) > 0:
-        cur_split = splits[0]
-
-        if cur_split["token_size"] > chunk_size:
-            raise ValueError("Got a split size that exceeded chunk size")
-
-        if cur_chunk_len + cur_split["token_size"] > chunk_size and not new_chunk:
-            close_chunk()
-        else:
-            if (cur_split["is_sentence"]
-                    or cur_chunk_len + cur_split["token_size"] <= chunk_size
-                    or new_chunk):  # If `new_chunk`, always add at least one split
-
-                cur_chunk_len += cur_split["token_size"]
-                cur_chunk.append((cur_split["text"], cur_split["token_size"]))
-                splits.pop(0)
-                new_chunk = False
-            else:
-                close_chunk()
-
-    if not new_chunk:
-        chunk = "".join([text for text, length in cur_chunk])
-        chunks.append(chunk)
-
-    return postprocess_chunks(chunks)

beekeeper/core/utils/pairwise.py

@@ -1,20 +0,0 @@
-from typing import List
-
-import numpy as np
-
-Matrix = List[float]
-
-def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
-    """Row-wise cosine similarity between two equal-width matrices."""
-    X = np.array(X)
-    Y = np.array(Y)
-    
-    if X.shape[0] != Y.shape[0]:
-        raise ValueError(
-            f"Number of rows in X and Y must be the same. X has shape {X.shape} "
-            f"and Y has shape {Y.shape}."
-        )
-    product = np.dot(X, Y)
-    norm = np.linalg.norm(X) * np.linalg.norm(Y)
-    
-    return product / norm

beekeeper/document_loaders/__init__.py

@@ -1,17 +0,0 @@
-from beekeeper.document_loaders.directory import DirectoryLoader
-from beekeeper.document_loaders.docx import DocxLoader
-from beekeeper.document_loaders.html import HTMLLoader
-from beekeeper.document_loaders.json import JSONLoader
-from beekeeper.document_loaders.pdf import PDFLoader
-from beekeeper.document_loaders.s3 import S3Loader
-from beekeeper.document_loaders.watson_discovery import WatsonDiscoveryLoader
-
-__all__ = [
-    "DirectoryLoader",
-    "DocxLoader",
-    "HTMLLoader",
-    "JSONLoader",
-    "PDFLoader",
-    "S3Loader",
-    "WatsonDiscoveryLoader",
-]

beekeeper/document_loaders/directory.py

@@ -1,65 +0,0 @@
-import glob
-import os
-from pathlib import Path
-from typing import List, Optional, Type
-
-from beekeeper.core.document import Document
-from beekeeper.core.document_loaders import BaseLoader
-
-
-def _loading_default_supported_loaders():
-    from beekeeper.document_loaders import DocxLoader, HTMLLoader, PDFLoader
-
-    return {
-    ".docx": DocxLoader,
-    ".html": HTMLLoader,
-    ".pdf": PDFLoader,
-}
-
-
-class DirectoryLoader(BaseLoader):
-    """Simple directory loader.
-
-    Args:
-        required_exts: (List[str], optional): List of file extensions to only load files with those extensions.
-        recursive (str, optional): Whether to recursively search for files. Defaults to ``False``.
-    """
-    
-    required_exts: List[str] = [".pdf", ".docx", ".html"]
-    recursive: Optional[bool] = False
-    file_loader: Optional[dict[str, Type[BaseLoader]]] = None
-
-    def load_data(self, input_dir: str, extra_info: Optional[dict] = None) -> List[Document]:
-        """Loads data from the specified directory.
-        
-        Args:
-            input_dir (str): Directory path from which to load the documents.
-        """
-        if not os.path.isdir(input_dir):
-            raise ValueError(f"`{input_dir}` is not a valid directory.")
-        
-        if self.file_loader is None:
-            self.file_loader = _loading_default_supported_loaders()
-        
-        input_dir = Path(input_dir)
-        documents = []
-        
-        pattern_prefix = "**/*" if self.recursive else ""
-
-        for extension in self.required_exts:
-            files = glob.glob(os.path.join(input_dir, pattern_prefix + extension), recursive=self.recursive)
-            
-            for file_dir in files:
-                loader_cls = self.file_loader.get(extension)
-                if loader_cls:
-                    try:
-                        #TO-DO add `file_loader_kwargs`
-                        doc = loader_cls().load_data(file_dir)
-                        documents.extend(doc)
-                    except Exception as e:
-                        raise f"Error reading {file_dir}: {e}"
-                else:
-                    #TO-DO add `unstructured file` support
-                    raise f"Unsupported file type: {extension}"
-
-        return documents