beekeeper-ai 0.6.6__py3-none-any.whl → 1.0.0__py3-none-any.whl

beekeeper/vector_stores/elasticsearch.py

@@ -1,183 +0,0 @@
-import uuid
-from logging import getLogger
-from typing import List, Literal
-
-from beekeeper.core.document import Document, DocumentWithScore
-from beekeeper.core.embeddings import BaseEmbedding
-
-logger = getLogger(__name__)
-
-
-class ElasticsearchVectorStore:
-    """Provides functionality to interact with Elasticsearch for storing and querying document embeddings.
-
-    Args:
-        index_name (str): Name of the Elasticsearch index.
-        url (str): Elasticsearch instance url.
-        user (str): Elasticsearch username.
-        password (str): Elasticsearch password.
-        dims_length (int): Length of the embedding dimensions.
-        embed_model (BaseEmbedding):
-        batch_size (int, optional): Batch size for bulk operations. Defaults to ``200``.
-        ssl (bool, optional): Whether to use SSL. Defaults to ``False``.
-        distance_strategy (str, optional): Distance strategy for similarity search. Currently supports "cosine", "dot_product" and "l2_norm". Defaults to ``cosine``.
-        text_field (str, optional): Name of the field containing text. Defaults to ``text``.
-        vector_field (str, optional): Name of the field containing vector embeddings. Defaults to ``embedding``.
-    """
-
-    def __init__(self,
-                 index_name: str,
-                 url: str,
-                 user: str,
-                 password: str,
-                 dims_length: int,
-                 embed_model: BaseEmbedding,
-                 batch_size: int = 200,
-                 ssl: bool = False,
-                 distance_strategy: Literal["cosine", "dot_product", "l2_norm"] = "cosine",
-                 text_field: str = "text",
-                 vector_field: str = "embedding",
-                 ) -> None:
-        try:
-            from elasticsearch import Elasticsearch
-            from elasticsearch.helpers import bulk
-
-            self._es_bulk = bulk
-        except ImportError:
-            raise ImportError("elasticsearch package not found, please install it with `pip install elasticsearch`")
-
-        #  TO-DO: Add connections types e.g: cloud
-        self._embed_model = embed_model
-        self.index_name = index_name
-        self.batch_size = batch_size
-        self.dims_length = dims_length
-        self.distance_strategy = distance_strategy
-        self.vector_field = vector_field
-        self.text_field = text_field
-
-        self._client = Elasticsearch(
-            hosts=[url],
-            basic_auth=(
-                user,
-                password
-            ),
-            verify_certs=ssl,
-            ssl_show_warn=False
-        )
-
-        try:
-            self._client.info()
-        except Exception as e:
-            logger.error(f"Error connecting to Elasticsearch: {e}")
-            raise
-
-    def _create_index_if_not_exists(self) -> None:
-        """Creates the Elasticsearch index if it doesn't already exist."""
-        if self._client.indices.exists(index=self.index_name):
-            logger.info(f"Index {self.index_name} already exists. Skipping creation.")
-
-        else:
-            if self.dims_length is None:
-                raise ValueError(
-                    "Cannot create index without specifying dims_length. "
-                    "When the index doesn't already exist."
-                )
-
-            index_mappings = {
-                "properties": {
-                    self.text_field: {"type": "text"},
-                    self.vector_field: {
-                        "type": "dense_vector",
-                        "dims": self.dims_length,
-                        "index": True,
-                        "similarity": self.distance_strategy,
-                    },
-                    "metadata": {
-                        "properties": {
-                            "creation_date": {"type": "keyword"},
-                            "filename": {"type": "keyword"},
-                            "file_type": {"type": "keyword"},
-                            "page": {"type": "keyword"},
-                        }
-                    }
-                }
-            }
-
-            print(f"Creating index {self.index_name}")
-
-            self._client.indices.create(index=self.index_name, mappings=index_mappings)
-
-    def add_documents(self, documents: List[Document], create_index_if_not_exists: bool = True) -> None:
-        """Add documents to the Elasticsearch index.
-
-        Args:
-            documents (List[Document]): List of `Document` objects to add to the index.
-            create_index_if_not_exists (bool, optional): Whether to create the index if it doesn't exist. Defaults to ``True``.
-        """
-        if create_index_if_not_exists:
-            self._create_index_if_not_exists()
-
-        vector_store_data = []
-        for doc in documents:
-            _id = doc.doc_id if doc.doc_id else str(uuid.uuid4())
-            _metadata = doc.get_metadata()
-            vector_store_data.append({
-                "_index": self.index_name,
-                "_id": _id,
-                self.text_field: doc.get_content(),
-                self.vector_field: self._embed_model.get_query_embedding(doc.get_content()),
-                "metadata": _metadata,
-                "metadata.creation_date": _metadata["creation_date"] if _metadata["creation_date"] else None,
-                "metadata.filename": _metadata["filename"] if _metadata["filename"] else None,
-                "metadata.file_type": _metadata["file_type"] if _metadata["file_type"] else None,
-                "metadata.page": _metadata["page"] if _metadata["page"] else None,
-            })
-
-        self._es_bulk(self._client, vector_store_data, chunk_size=self.batch_size, refresh=True)
-        print(f"Added {len(vector_store_data)} documents to `{self.index_name}`")
-
-    def query(self, query: str, top_k: int = 4) -> List[DocumentWithScore]:
-        """Performs a similarity search for top-k most similar documents.
-
-        Args:
-            query (str): Query text.
-            top_k (int, optional): Number of top results to return. Defaults to ``4``.
-        """
-        query_embedding = self._embed_model.get_query_embedding(query)
-        #  TO-DO: Add elasticsearch `filter` option
-        es_query = {"knn": {
-            # "filter": filter,
-            "field": self.vector_field,
-            "query_vector": query_embedding,
-            "k": top_k,
-            "num_candidates": top_k * 10,
-        }}
-
-        results = self._client.search(index=self.index_name,
-                                      **es_query,
-                                      size=top_k,
-                                      _source={"excludes": [self.vector_field]})
-
-        hits = results["hits"]["hits"]
-
-        return [DocumentWithScore(
-            document=Document(
-                doc_id=hit["_id"],
-                text=hit["_source"]["text"],
-                metadata=hit["_source"]["metadata"],
-            ),
-            score=hit["_score"])
-            for hit in hits
-        ]
-
-    def delete_documents(self, ids: List[str] = None) -> None:
-        """Delete documents from the Elasticsearch index.
-
-        Args:
-            ids (List[str]): List of `Document` IDs to delete.
-        """
-        if not ids:
-            raise ValueError("No ids provided to delete.")
-
-        for id in ids:
-            self._client.delete(index=self.index_name, id=id)

beekeeper_ai-0.6.6.dist-info/LICENSE

@@ -1,7 +0,0 @@
-Copyright 2024 Leonardo Furnielis
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

beekeeper_ai-0.6.6.dist-info/METADATA

@@ -1,49 +0,0 @@
-Metadata-Version: 2.1
-Name: beekeeper-ai
-Version: 0.6.6
-Summary: Load any data in one line of code and connect with AI applications
-Home-page: https://github.com/leonardofurnielis/beekeeper
-License: MIT
-Keywords: AI,LLM,QA,RAG,data,monitor,retrieval,semantic-search
-Author: Leonardo Furnielis
-Author-email: leonardofurnielis@outlook.com
-Requires-Python: >=3.10,<4.0
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Dist: nltk (>=3.8.1,<4.0.0)
-Requires-Dist: numpy (>=1.26.4,<2.0.0)
-Requires-Dist: pydantic (>=2.7.1,<3.0.0)
-Requires-Dist: sentence-transformers (>=2.7.0,<3.0.0)
-Requires-Dist: tiktoken (>=0.7.0,<0.8.0)
-Requires-Dist: torch (==2.1.0)
-Project-URL: Documentation, https://leonardofurnielis.github.io/beekeeper
-Project-URL: Repository, https://github.com/leonardofurnielis/beekeeper
-Description-Content-Type: text/markdown
-
-# Beekeeper
-
-![PyPI - Version](https://img.shields.io/pypi/v/beekeeper-ai)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-![PyPI - Downloads](https://img.shields.io/pypi/dm/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://leonardofurnielis.github.io/beekeeper)!
-
-Please check it out for overview of the interfaces, components, integrations and other resources!
-

beekeeper_ai-0.6.6.dist-info/RECORD

@@ -1,37 +0,0 @@
-beekeeper/__init__.py,sha256=I3h5MyD10PkOUQEBnR6L9ja7s4WeTEg8rRjRKTCWYWQ,22
-beekeeper/core/document/__init__.py,sha256=6l28uskkwzxQhnX_Ov9NmXQ3JAF5vXJk6cuQR3zRqwg,126
-beekeeper/core/document/schema.py,sha256=72jWAkBAU8DtRA90jYdhbUqax1a0Yx76NgAYxQj6UFU,2534
-beekeeper/core/document_loaders/__init__.py,sha256=OH0Y6Nf66bdi8vv_o-dldndHhmfM74y8s9ilgvG_Crk,93
-beekeeper/core/document_loaders/base.py,sha256=ojJ4cC2H47hJUbDPwfAK-QXihrjjBjBUq4N0vTHwaZM,581
-beekeeper/core/embeddings/__init__.py,sha256=y5mtk3vSn4toM9z-zYRtagYHJiiTcNUdxuT6EBuoYto,121
-beekeeper/core/embeddings/base.py,sha256=JjtSs_RyGMZgSLwKUYlLt5snBrE3gNIqvwjC8ySGb9w,1326
-beekeeper/core/text_splitters/utils.py,sha256=5bDbTr_NLeTyJBIUjnsd4Jm9DkAbzR3EjvK3dF0R3iQ,4544
-beekeeper/core/utils/pairwise.py,sha256=G4ud6yGtDIuwVeQ9uv9tX8kISXYbPV73_DOjko8TdX4,542
-beekeeper/document_loaders/__init__.py,sha256=VOQI6bSNNw76y_wOrw7v8wu424w1Rya6ld_fPJDOuIk,566
-beekeeper/document_loaders/directory.py,sha256=wp8XhrlzyaPZGH3JUIgD0wgtprsI4RDFkli3vOw6A2M,2245
-beekeeper/document_loaders/docx.py,sha256=EQ9WLdhUnxsqnztMJVTYO6MtyoJx5z_pRO4VL9a294I,990
-beekeeper/document_loaders/html.py,sha256=JpYQFrjl7nGLLaypPfhQNmDYwB1I-m7rfqTqf90V8Eo,2408
-beekeeper/document_loaders/json.py,sha256=r4qprhL66UFA8dN_NbSa7y5jxXEs7ULvfxfVhAf0aYQ,1672
-beekeeper/document_loaders/pdf.py,sha256=A6fuSieakWiVA5RjSUsTqJ8FMllMNujSrSlIPLWH7CU,1194
-beekeeper/document_loaders/s3.py,sha256=iTdjPIxP8nF3Zeehtqq7xplQfB8CmF8TDD56pv5E-pQ,2545
-beekeeper/document_loaders/watson_discovery.py,sha256=eIR4mYARMck3S9q-mMOPX1X5BYqEL7ePH-50emz6HE0,4880
-beekeeper/embeddings/__init__.py,sha256=enRONiVzIgDSpxcQshBKrqNQD8tQ7JACzHzowcL_N1w,190
-beekeeper/embeddings/huggingface.py,sha256=wmKnEyTzLlf_MtmKjUFiULZjxRk5RJ_W-_4YC6ifcAQ,2176
-beekeeper/embeddings/watsonx.py,sha256=w7Fbz74B_XDLu7aE9_haXI77oCUyFLhrSFgHuMCZ3qg,3605
-beekeeper/evaluation/__init__.py,sha256=SzRQHkUqgzRoiccHknu0juMutSyF1dI_-AeuBZOCe_E,123
-beekeeper/evaluation/knowledge_base_coverage.py,sha256=YkjrqQAmUU7ul0ZVcO7MN62EIkk-nMKQCRF-HD19WmU,2268
-beekeeper/monitor/__init__.py,sha256=Zgx2OaGiid3pnNnBrI-YjCNE0KdWX3g3sOhbCEhhYY8,258
-beekeeper/monitor/watsonx.py,sha256=lB8y0H1H_zhmsXo4pgxpi4ZeC1V4_KIHY2jQzqO3MQQ,42576
-beekeeper/retrievers/__init__.py,sha256=Py1X7DfxNyMozQX1LBl0jSZyft05OD04yglqBVpP3mQ,122
-beekeeper/retrievers/watson_discovery.py,sha256=evn9MGBUE2WkL7r_mg1zlSNZpp7XuxfG0HgeDiSeUyU,5121
-beekeeper/text_splitters/__init__.py,sha256=HkRHuwi-v5Xtwnr3ELkf_eG9WfXtuq3FFf_Zn8QUOuE,275
-beekeeper/text_splitters/semantic.py,sha256=4dK5cY5ZI4uXJhr9xcc6njPnytMlEWs9GvFEEBErGGk,5292
-beekeeper/text_splitters/sentence.py,sha256=F4PhqN_Q4MdNF-CDmS03Q4I9OuecTLhMOnFvqA8dzR8,3399
-beekeeper/text_splitters/token.py,sha256=HgGf7V_RHvkl0C_Jmjr0pgdAqmcI9qKBeVqDEb-6SXc,3138
-beekeeper/vector_stores/__init__.py,sha256=sH7pUh-3ln9EzZOJm4mz2z1BJFqJStsuogl-XvuatvQ,208
-beekeeper/vector_stores/chroma.py,sha256=89ebsNs4JYCpM6SYY6pYy2nuH5gv4TxjxMrz729XE1w,3997
-beekeeper/vector_stores/elasticsearch.py,sha256=GTLCvxv8ne-S3fEG8HcONlpagJ1o5PJxtdE_JoM4aTs,7318
-beekeeper_ai-0.6.6.dist-info/LICENSE,sha256=TC5Fo1FSsyuLJTlNFbY0zCa08wcY5OmMW3RdKOId37s,1071
-beekeeper_ai-0.6.6.dist-info/METADATA,sha256=VtdhFpHrTKNmug0q4JFbd2VAZGVc1Oyf37JAEvEO-TM,1962
-beekeeper_ai-0.6.6.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-beekeeper_ai-0.6.6.dist-info/RECORD,,