kennethreitz/langchain
1
0
Fork 0
mirror of https://github.com/kennethreitz/langchain.git synced 2026-06-05 23:00:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add DocArray vector stores (#4483)

Browse Source 
Thanks to @anna-charlotte and @jupyterjazz for the contribution! Made
few small changes to get it across the finish line

---------

Signed-off-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Signed-off-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Co-authored-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: Saba Sturua <45267439+jupyterjazz@users.noreply.github.com>
This commit is contained in:
Davis Chase
2023-05-10 15:22:16 -07:00
committed by GitHub
parent f2a536b445
commit 46b100ea63
12 changed files with 1333 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/modules/indexes/vectorstores/examples/docarray_hnsw.ipynb
+227
View File
@@ -0,0 +1,227 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "2ce41f46-5711-4311-b04d-2fe233ac5b1b",
"metadata": {},
"source": [
"# DocArrayHnswSearch\n",
"\n",
">[DocArrayHnswSearch](https://docs.docarray.org/user_guide/storing/index_hnswlib/) is a lightweight Document Index implementation provided by [Docarray](https://docs.docarray.org/) that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in [hnswlib](https://github.com/nmslib/hnswlib), and stores all other data in [SQLite](https://www.sqlite.org/index.html).\n",
"\n",
"This notebook shows how to use functionality related to the `DocArrayHnswSearch`."
]
},
{
"cell_type": "markdown",
"id": "7ee37d28",
"metadata": {},
"source": [
"# Setup\n",
"\n",
"Uncomment the below cells to install docarray and get/set your OpenAI api key if you haven't already done so."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8ce1b8cb-dbf0-40c3-99ee-04f28143331b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# !pip install \"docarray[hnswlib]\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "878f17df-100f-4854-9e87-472cf36d51f3",
"metadata": {
"scrolled": true,
"tags": []
},
"outputs": [],
"source": [
"# Get an OpenAI token: https://platform.openai.com/account/api-keys\n",
"\n",
"# import os\n",
"# from getpass import getpass\n",
"\n",
"# OPENAI_API_KEY = getpass()\n",
"\n",
"# os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
]
},
{
"cell_type": "markdown",
"id": "8dbb6de2",
"metadata": {
"tags": []
},
"source": [
"# Using DocArrayHnswSearch"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b757afef-ef0a-465d-8e8a-9aadb9c32b88",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import DocArrayHnswSearch\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "605e200e-e711-486b-b36e-cbe5dd2512d7",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"documents = TextLoader('../../../state_of_the_union.txt').load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"\n",
"db = DocArrayHnswSearch.from_documents(docs, embeddings, work_dir='hnswlib_store/', n_dim=1536)"
]
},
{
"cell_type": "markdown",
"id": "ed6f905b-4853-4a44-9730-614aa8e22b78",
"metadata": {},
"source": [
"## Similarity search"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4d7e742f-2002-449d-a10e-16046890906c",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "0da9e26f-1fc2-48e6-95a7-f692c853bbd3",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "3febb987-e903-416f-af26-6897d84c8d61",
"metadata": {},
"source": [
"## Similarity search with score"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "40764fdd-357d-475a-8152-5f1979d61a45",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"docs = db.similarity_search_with_score(query)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "a479fc46-b299-4330-89b9-e9b5a218ea03",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={}),\n",
" 0.36962226)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4d3d4e97-5d2b-4571-8ff9-e3f6b6778714",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import shutil\n",
"# delete the dir\n",
"shutil.rmtree('hnswlib_store')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
docs/modules/indexes/vectorstores/examples/docarray_in_memory.ipynb
+210
View File
@@ -0,0 +1,210 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "a3afefb0-7e99-4912-a222-c6b186da11af",
"metadata": {},
"source": [
"# DocArrayInMemorySearch\n",
"\n",
">[DocArrayInMemorySearch](https://docs.docarray.org/user_guide/storing/index_in_memory/) is a document index provided by [Docarray](https://docs.docarray.org/) that stores documents in memory. It is a great starting point for small datasets, where you may not want to launch a database server.\n",
"\n",
"This notebook shows how to use functionality related to the `DocArrayInMemorySearch`."
]
},
{
"cell_type": "markdown",
"id": "5031a3ec",
"metadata": {},
"source": [
"# Setup\n",
"\n",
"Uncomment the below cells to install docarray and get/set your OpenAI api key if you haven't already done so."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7cd7391f-7759-4a21-952a-2ec972d818c6",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# !pip install \"docarray\""
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c6a40ad8-920e-4370-818d-3227e2f506ed",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Get an OpenAI token: https://platform.openai.com/account/api-keys\n",
"\n",
"# import os\n",
"# from getpass import getpass\n",
"\n",
"# OPENAI_API_KEY = getpass()\n",
"\n",
"# os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e49be085-ddf1-4028-8c0c-97836ce4a873",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import DocArrayInMemorySearch\n",
"from langchain.document_loaders import TextLoader"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "38222aee-adc5-44c2-913c-97977b394cf5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"documents = TextLoader('../../../state_of_the_union.txt').load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"\n",
"db = DocArrayInMemorySearch.from_documents(docs, embeddings)"
]
},
{
"cell_type": "markdown",
"id": "efbb6684-3846-4332-a624-ddd4d75844c1",
"metadata": {},
"source": [
"## Similarity search"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "aa28a7f8-41d0-4299-84eb-91d1576e8a63",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "1eb16d2a-b466-456a-b412-5e74bb8523dd",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
"\n",
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
"\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
]
}
],
"source": [
"print(docs[0].page_content)"
]
},
{
"cell_type": "markdown",
"id": "43896697-f99e-47b6-9117-47a25e9afa9c",
"metadata": {},
"source": [
"## Similarity search with score"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "8e9eef05-1516-469a-ad36-880c69aef7a9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"docs = db.similarity_search_with_score(query)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "bd5fb0e4-2a94-4bb4-af8a-27327ecb1a7f",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={}),\n",
" 0.8154190158347903)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs[0]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3e5da522-ef0e-4a59-91ea-89e563f7b825",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
langchain/vectorstores/__init__.py
+3
View File
@@ -5,6 +5,7 @@ from langchain.vectorstores.atlas import AtlasDB
from langchain.vectorstores.base import VectorStore
from langchain.vectorstores.chroma import Chroma
from langchain.vectorstores.deeplake import DeepLake
from langchain.vectorstores.docarray import DocArrayHnswSearch, DocArrayInMemorySearch
from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch
from langchain.vectorstores.faiss import FAISS
from langchain.vectorstores.lancedb import LanceDB
@@ -40,4 +41,6 @@ __all__ = [
"AnalyticDB",
"Tair",
"LanceDB",
"DocArrayHnswSearch",
"DocArrayInMemorySearch",
]
langchain/vectorstores/docarray/__init__.py
+7
View File
@@ -0,0 +1,7 @@
from langchain.vectorstores.docarray.hnsw import DocArrayHnswSearch
from langchain.vectorstores.docarray.in_memory import DocArrayInMemorySearch
__all__ = [
"DocArrayHnswSearch",
"DocArrayInMemorySearch",
]
langchain/vectorstores/docarray/base.py
+199
View File
@@ -0,0 +1,199 @@
from abc import ABC
from typing import TYPE_CHECKING, Any, Iterable, List, Optional, Tuple, Type
import numpy as np
from pydantic import Field
from langchain.embeddings.base import Embeddings
from langchain.schema import Document
from langchain.vectorstores import VectorStore
from langchain.vectorstores.utils import maximal_marginal_relevance
if TYPE_CHECKING:
from docarray import BaseDoc
from docarray.index.abstract import BaseDocIndex
def _check_docarray_import() -> None:
try:
import docarray
da_version = docarray.__version__.split(".")
if int(da_version[0]) == 0 and int(da_version[1]) <= 30:
raise ValueError(
f"To use the DocArrayHnswSearch VectorStore the docarray "
f"version >=0.31.0 is expected, received: {docarray.__version__}."
f"To upgrade, please run: `pip install -U docarray`."
)
except ImportError:
raise ImportError(
"Could not import docarray python package. "
'Please install it with `pip install "langchain[docarray]"`.'
)
class DocArrayIndex(VectorStore, ABC):
def __init__(
self,
doc_index: "BaseDocIndex",
embedding: Embeddings,
):
"""Initialize a vector store from DocArray's DocIndex."""
self.doc_index = doc_index
self.embedding = embedding
@staticmethod
def _get_doc_cls(**embeddings_params: Any) -> Type["BaseDoc"]:
"""Get docarray Document class describing the schema of DocIndex."""
from docarray import BaseDoc
from docarray.typing import NdArray
class DocArrayDoc(BaseDoc):
text: Optional[str]
embedding: Optional[NdArray] = Field(**embeddings_params)
metadata: Optional[dict]
return DocArrayDoc
@property
def doc_cls(self) -> Type["BaseDoc"]:
if self.doc_index._schema is None:
raise ValueError("doc_index expected to have non-null _schema attribute.")
return self.doc_index._schema
def add_texts(
self,
texts: Iterable[str],
metadatas: Optional[List[dict]] = None,
**kwargs: Any,
) -> List[str]:
"""Run more texts through the embeddings and add to the vectorstore.
Args:
texts: Iterable of strings to add to the vectorstore.
metadatas: Optional list of metadatas associated with the texts.
Returns:
List of ids from adding the texts into the vectorstore.
"""
ids: List[str] = []
embeddings = self.embedding.embed_documents(list(texts))
for i, (t, e) in enumerate(zip(texts, embeddings)):
m = metadatas[i] if metadatas else {}
doc = self.doc_cls(text=t, embedding=e, metadata=m)
self.doc_index.index([doc])
ids.append(str(doc.id))
return ids
def similarity_search_with_score(
self, query: str, k: int = 4, **kwargs: Any
) -> List[Tuple[Document, float]]:
"""Return docs most similar to query.
Args:
query: Text to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
Returns:
List of Documents most similar to the query and score for each.
"""
query_embedding = self.embedding.embed_query(query)
query_doc = self.doc_cls(embedding=query_embedding) # type: ignore
docs, scores = self.doc_index.find(query_doc, search_field="embedding", limit=k)
result = [
(Document(page_content=doc.text, metadata=doc.metadata), score)
for doc, score in zip(docs, scores)
]
return result
def similarity_search(
self, query: str, k: int = 4, **kwargs: Any
) -> List[Document]:
"""Return docs most similar to query.
Args:
query: Text to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
Returns:
List of Documents most similar to the query.
"""
results = self.similarity_search_with_score(query, k=k, **kwargs)
return [doc for doc, _ in results]
def _similarity_search_with_relevance_scores(
self,
query: str,
k: int = 4,
**kwargs: Any,
) -> List[Tuple[Document, float]]:
"""Return docs and relevance scores, normalized on a scale from 0 to 1.
0 is dissimilar, 1 is most similar.
"""
raise NotImplementedError
def similarity_search_by_vector(
self, embedding: List[float], k: int = 4, **kwargs: Any
) -> List[Document]:
"""Return docs most similar to embedding vector.
Args:
embedding: Embedding to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
Returns:
List of Documents most similar to the query vector.
"""
query_doc = self.doc_cls(embedding=embedding) # type: ignore
docs = self.doc_index.find(
query_doc, search_field="embedding", limit=k
).documents
result = [
Document(page_content=doc.text, metadata=doc.metadata) for doc in docs
]
return result
def max_marginal_relevance_search(
self,
query: str,
k: int = 4,
fetch_k: int = 20,
lambda_mult: float = 0.5,
**kwargs: Any,
) -> List[Document]:
"""Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Args:
query: Text to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
fetch_k: Number of Documents to fetch to pass to MMR algorithm.
lambda_mult: Number between 0 and 1 that determines the degree
of diversity among the results with 0 corresponding
to maximum diversity and 1 to minimum diversity.
Defaults to 0.5.
Returns:
List of Documents selected by maximal marginal relevance.
"""
query_embedding = self.embedding.embed_query(query)
query_doc = self.doc_cls(embedding=query_embedding) # type: ignore
docs = self.doc_index.find(
query_doc, search_field="embedding", limit=fetch_k
).documents
mmr_selected = maximal_marginal_relevance(
np.array(query_embedding), docs.embedding, k=k
)
results = [
Document(page_content=docs[idx].text, metadata=docs[idx].metadata)
for idx in mmr_selected
]
return results
langchain/vectorstores/docarray/hnsw.py
+109
View File
@@ -0,0 +1,109 @@
"""Wrapper around Hnswlib store."""
from __future__ import annotations
from typing import Any, List, Literal, Optional
from langchain.embeddings.base import Embeddings
from langchain.vectorstores.docarray.base import (
DocArrayIndex,
_check_docarray_import,
)
class DocArrayHnswSearch(DocArrayIndex):
"""Wrapper around HnswLib storage.
To use it, you should have the ``docarray[hnswlib]`` package with version >=0.31.0
installed. You can install it with `pip install "langchain[hnswlib]"`.
"""
@classmethod
def from_params(
cls,
embedding: Embeddings,
work_dir: str,
n_dim: int,
dist_metric: Literal["cosine", "ip", "l2"] = "cosine",
max_elements: int = 1024,
index: bool = True,
ef_construction: int = 200,
ef: int = 10,
M: int = 16,
allow_replace_deleted: bool = True,
num_threads: int = 1,
**kwargs: Any,
) -> DocArrayHnswSearch:
"""Initialize DocArrayHnswSearch store.
Args:
embedding (Embeddings): Embedding function.
work_dir (str): path to the location where all the data will be stored.
n_dim (int): dimension of an embedding.
dist_metric (str): Distance metric for DocArrayHnswSearch can be one of:
"cosine", "ip", and "l2". Defaults to "cosine".
max_elements (int): Maximum number of vectors that can be stored.
Defaults to 1024.
index (bool): Whether an index should be built for this field.
Defaults to True.
ef_construction (int): defines a construction time/accuracy trade-off.
Defaults to 200.
ef (int): parameter controlling query time/accuracy trade-off.
Defaults to 10.
M (int): parameter that defines the maximum number of outgoing
connections in the graph. Defaults to 16.
allow_replace_deleted (bool): Enables replacing of deleted elements
with new added ones. Defaults to True.
num_threads (int): Sets the number of cpu threads to use. Defaults to 1.
**kwargs: Other keyword arguments to be passed to the get_doc_cls method.
"""
_check_docarray_import()
from docarray.index import HnswDocumentIndex
doc_cls = cls._get_doc_cls(
dim=n_dim,
space=dist_metric,
max_elements=max_elements,
index=index,
ef_construction=ef_construction,
ef=ef,
M=M,
allow_replace_deleted=allow_replace_deleted,
num_threads=num_threads,
**kwargs,
)
doc_index = HnswDocumentIndex[doc_cls](work_dir=work_dir) # type: ignore
return cls(doc_index, embedding)
@classmethod
def from_texts(
cls,
texts: List[str],
embedding: Embeddings,
metadatas: Optional[List[dict]] = None,
work_dir: Optional[str] = None,
n_dim: Optional[int] = None,
**kwargs: Any,
) -> DocArrayHnswSearch:
"""Create an DocArrayHnswSearch store and insert data.
Args:
texts (List[str]): Text data.
embedding (Embeddings): Embedding function.
metadatas (Optional[List[dict]]): Metadata for each text if it exists.
Defaults to None.
work_dir (str): path to the location where all the data will be stored.
n_dim (int): dimension of an embedding.
**kwargs: Other keyword arguments to be passed to the __init__ method.
Returns:
DocArrayHnswSearch Vector Store
"""
if work_dir is None:
raise ValueError("`work_dir` parameter has not been set.")
if n_dim is None:
raise ValueError("`n_dim` parameter has not been set.")
store = cls.from_params(embedding, work_dir, n_dim, **kwargs)
store.add_texts(texts=texts, metadatas=metadatas)
return store
langchain/vectorstores/docarray/in_memory.py
+69
View File
@@ -0,0 +1,69 @@
"""Wrapper around in-memory storage."""
from __future__ import annotations
from typing import Any, Dict, List, Literal, Optional
from langchain.embeddings.base import Embeddings
from langchain.vectorstores.docarray.base import (
DocArrayIndex,
_check_docarray_import,
)
class DocArrayInMemorySearch(DocArrayIndex):
"""Wrapper around in-memory storage for exact search.
To use it, you should have the ``docarray`` package with version >=0.31.0 installed.
You can install it with `pip install "langchain[in_memory_store]"`.
"""
@classmethod
def from_params(
cls,
embedding: Embeddings,
metric: Literal[
"cosine_sim", "euclidian_dist", "sgeuclidean_dist"
] = "cosine_sim",
**kwargs: Any,
) -> DocArrayInMemorySearch:
"""Initialize DocArrayInMemorySearch store.
Args:
embedding (Embeddings): Embedding function.
metric (str): metric for exact nearest-neighbor search.
Can be one of: "cosine_sim", "euclidean_dist" and "sqeuclidean_dist".
Defaults to "cosine_sim".
**kwargs: Other keyword arguments to be passed to the get_doc_cls method.
"""
_check_docarray_import()
from docarray.index import InMemoryExactNNIndex
doc_cls = cls._get_doc_cls(space=metric, **kwargs)
doc_index = InMemoryExactNNIndex[doc_cls]() # type: ignore
return cls(doc_index, embedding)
@classmethod
def from_texts(
cls,
texts: List[str],
embedding: Embeddings,
metadatas: Optional[List[Dict[Any, Any]]] = None,
**kwargs: Any,
) -> DocArrayInMemorySearch:
"""Create an DocArrayInMemorySearch store and insert data.
Args:
texts (List[str]): Text data.
embedding (Embeddings): Embedding function.
metadatas (Optional[List[Dict[Any, Any]]]): Metadata for each text
if it exists. Defaults to None.
metric (str): metric for exact nearest-neighbor search.
Can be one of: "cosine_sim", "euclidean_dist" and "sqeuclidean_dist".
Defaults to "cosine_sim".
Returns:
DocArrayInMemorySearch Vector Store
"""
store = cls.from_params(embedding, **kwargs)
store.add_texts(texts=texts, metadatas=metadatas)
return store
poetry.lock
Generated
+260 -197
View File
@@ -883,14 +883,14 @@ files = [
[[package]]
name = "certifi"
version = "2022.12.7"
version = "2023.5.7"
description = "Python package for providing Mozilla's CA Bundle."
category = "main"
optional = false
python-versions = ">=3.6"
files = [
{file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
{file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
{file = "certifi-2023.5.7-py3-none-any.whl", hash = "sha256:c6c2e98f5c7869efca1f8916fed228dd91539f9f1b444c314c06eef02980c716"},
{file = "certifi-2023.5.7.tar.gz", hash = "sha256:0f0d56dc5a6ad56fd4ba36484d6cc34451e1c6548c61daad8c320169f91eddc7"},
]
[[package]]
@@ -1560,43 +1560,51 @@ wmi = ["wmi (>=1.5.1,<2.0.0)"]
[[package]]
name = "docarray"
version = "0.21.0"
description = "The data structure for unstructured data"
version = "0.31.0"
description = "The data structure for multimodal data"
category = "main"
optional = true
python-versions = "*"
python-versions = ">=3.7,<4.0"
files = [
{file = "docarray-0.21.0.tar.gz", hash = "sha256:3c9f605123800c1b0cdf8c458be3fb19c05e9a81f723e51200ef531b02e689ee"},
{file = "docarray-0.31.0-py3-none-any.whl", hash = "sha256:3783e9bdcf0d59b17499660e54577f4e3d202545998afca9306ebcc09cf0e14e"},
{file = "docarray-0.31.0.tar.gz", hash = "sha256:a79d1ed70bd143b3e2a53ff90a62e4b3ce7231d5d237a2fab9b8311d7ae7d245"},
]
[package.dependencies]
jina-hubble-sdk = ">=0.24.0"
numpy = "*"
rich = ">=12.0.0"
numpy = ">=1.17.3"
orjson = ">=3.8.2"
pydantic = ">=1.10.2"
rich = ">=13.1.0"
types-requests = ">=2.28.11.6"
typing-inspect = ">=0.8.0"
[package.extras]
annlite = ["annlite"]
benchmark = ["h5py", "matplotlib", "pandas", "seaborn"]
common = ["Pillow", "fastapi", "lz4", "matplotlib", "protobuf (>=3.13.0)", "pydantic (>=1.9.0)", "requests", "uvicorn"]
elasticsearch = ["elasticsearch (>=8.2.0)"]
full = ["Pillow", "av", "fastapi", "grpcio (>=1.46.0,<1.48.1)", "grpcio-health-checking (>=1.46.0,<1.48.1)", "grpcio-reflection (>=1.46.0,<1.48.1)", "ipython", "lz4", "matplotlib", "protobuf (>=3.13.0)", "pydantic (>=1.9.0)", "requests", "scipy", "strawberry-graphql", "trimesh[easy]", "uvicorn"]
milvus = ["pymilvus (>=2.1.0,<2.2.0)"]
opensearch = ["opensearch-py (==2.0.1)"]
qdrant = ["qdrant-client (>=0.10.3,<0.11.0)"]
redis = ["redis (>=4.3.0)"]
test = ["annlite", "black (==22.3.0)", "datasets", "elasticsearch (>=8.2.0)", "jina", "jupyterlab", "mock", "onnx", "onnxruntime", "opensearch-py (==2.0.1)", "paddlepaddle", "protobuf (>=3.13.0,<=3.20.0)", "pymilvus (==2.1.3)", "pytest", "pytest-cov (==3.0.0)", "pytest-custom_exit_code", "pytest-mock", "pytest-mock", "pytest-repeat", "pytest-reraise", "pytest-timeout", "redis (>=4.3.0)", "tensorflow (==2.7.0)", "torch (==1.9.0)", "torchvision (==0.10.0)", "transformers (>=4.16.2)", "weaviate-client (>=3.9.0,<3.10.0)"]
weaviate = ["weaviate-client (>=3.9.0,<3.10.0)"]
audio = ["pydub (>=0.25.1,<0.26.0)"]
aws = ["smart-open[s3] (>=6.3.0)"]
elasticsearch = ["elastic-transport (>=8.4.0,<9.0.0)", "elasticsearch (>=7.10.1)"]
full = ["av (>=10.0.0)", "lz4 (>=1.0.0)", "pandas (>=1.1.0)", "pillow (>=9.3.0)", "protobuf (>=3.19.0)", "pydub (>=0.25.1,<0.26.0)", "trimesh[easy] (>=3.17.1)", "types-pillow (>=9.3.0.1)"]
hnswlib = ["hnswlib (>=0.6.2)"]
image = ["pillow (>=9.3.0)", "types-pillow (>=9.3.0.1)"]
jac = ["jina-hubble-sdk (>=0.34.0)"]
mesh = ["trimesh[easy] (>=3.17.1)"]
pandas = ["pandas (>=1.1.0)"]
proto = ["lz4 (>=1.0.0)", "protobuf (>=3.19.0)"]
qdrant = ["qdrant-client (>=1.1.4)"]
torch = ["torch (>=1.0.0)"]
video = ["av (>=10.0.0)"]
weaviate = ["weaviate-client (>=3.15)"]
web = ["fastapi (>=0.87.0)"]
[[package]]
name = "docker"
version = "6.0.1"
version = "6.1.1"
description = "A Python library for the Docker Engine API."
category = "main"
optional = true
python-versions = ">=3.7"
files = [
{file = "docker-6.0.1-py3-none-any.whl", hash = "sha256:dbcb3bd2fa80dca0788ed908218bf43972772009b881ed1e20dfc29a65e49782"},
{file = "docker-6.0.1.tar.gz", hash = "sha256:896c4282e5c7af5c45e8b683b0b0c33932974fe6e50fc6906a0a83616ab3da97"},
{file = "docker-6.1.1-py3-none-any.whl", hash = "sha256:8308b23d3d0982c74f7aa0a3abd774898c0c4fba006e9c3bde4f68354e470fe2"},
{file = "docker-6.1.1.tar.gz", hash = "sha256:5ec18b9c49d48ee145a5b5824bb126dc32fc77931e18444783fc07a7724badc0"},
]
[package.dependencies]
@@ -2039,14 +2047,14 @@ files = [
[[package]]
name = "fsspec"
version = "2023.4.0"
version = "2023.5.0"
description = "File-system specification"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "fsspec-2023.4.0-py3-none-any.whl", hash = "sha256:f398de9b49b14e9d84d2c2d11b7b67121bc072fe97b930c4e5668ac3917d8307"},
{file = "fsspec-2023.4.0.tar.gz", hash = "sha256:bf064186cd8808f0b2f6517273339ba0a0c8fb1b7048991c28bc67f58b8b67cd"},
{file = "fsspec-2023.5.0-py3-none-any.whl", hash = "sha256:51a4ad01a5bb66fcc58036e288c0d53d3975a0df2a5dc59a93b59bade0391f2a"},
{file = "fsspec-2023.5.0.tar.gz", hash = "sha256:b3b56e00fb93ea321bc9e5d9cf6f8522a0198b20eb24e02774d329e9c6fb84ce"},
]
[package.extras]
@@ -2099,26 +2107,24 @@ files = [
[[package]]
name = "google-api-core"
version = "2.11.0"
version = "2.8.2"
description = "Google API client core library"
category = "main"
optional = true
python-versions = ">=3.7"
python-versions = ">=3.6"
files = [
{file = "google-api-core-2.11.0.tar.gz", hash = "sha256:4b9bb5d5a380a0befa0573b302651b8a9a89262c1730e37bf423cec511804c22"},
{file = "google_api_core-2.11.0-py3-none-any.whl", hash = "sha256:ce222e27b0de0d7bc63eb043b956996d6dccab14cc3b690aaea91c9cc99dc16e"},
{file = "google-api-core-2.8.2.tar.gz", hash = "sha256:06f7244c640322b508b125903bb5701bebabce8832f85aba9335ec00b3d02edc"},
{file = "google_api_core-2.8.2-py3-none-any.whl", hash = "sha256:93c6a91ccac79079ac6bbf8b74ee75db970cc899278b97d53bc012f35908cf50"},
]
[package.dependencies]
google-auth = ">=2.14.1,<3.0dev"
google-auth = ">=1.25.0,<3.0dev"
googleapis-common-protos = ">=1.56.2,<2.0dev"
protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0dev"
protobuf = ">=3.15.0,<5.0.0dev"
requests = ">=2.18.0,<3.0.0dev"
[package.extras]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio (>=1.49.1,<2.0dev)", "grpcio-status (>=1.33.2,<2.0dev)", "grpcio-status (>=1.49.1,<2.0dev)"]
grpcgcp = ["grpcio-gcp (>=0.2.2,<1.0dev)"]
grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0dev)"]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio-status (>=1.33.2,<2.0dev)"]
[[package]]
name = "google-api-python-client"
@@ -2232,32 +2238,32 @@ requests = "*"
[[package]]
name = "googleapis-common-protos"
version = "1.59.0"
version = "1.56.4"
description = "Common protobufs used in Google APIs"
category = "main"
optional = true
python-versions = ">=3.7"
files = [
{file = "googleapis-common-protos-1.59.0.tar.gz", hash = "sha256:4168fcb568a826a52f23510412da405abd93f4d23ba544bb68d943b14ba3cb44"},
{file = "googleapis_common_protos-1.59.0-py2.py3-none-any.whl", hash = "sha256:b287dc48449d1d41af0c69f4ea26242b5ae4c3d7249a38b0984c86a4caffff1f"},
{file = "googleapis-common-protos-1.56.4.tar.gz", hash = "sha256:c25873c47279387cfdcbdafa36149887901d36202cb645a0e4f29686bf6e4417"},
{file = "googleapis_common_protos-1.56.4-py2.py3-none-any.whl", hash = "sha256:8eb2cbc91b69feaf23e32452a7ae60e791e09967d81d4fcc7fc388182d1bd394"},
]
[package.dependencies]
protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0dev"
protobuf = ">=3.15.0,<5.0.0dev"
[package.extras]
grpc = ["grpcio (>=1.44.0,<2.0.0dev)"]
grpc = ["grpcio (>=1.0.0,<2.0.0dev)"]
[[package]]
name = "gptcache"
version = "0.1.21"
version = "0.1.22"
description = "GPTCache, a powerful caching library that can be used to speed up and lower the cost of chat applications that rely on the LLM service. GPTCache works as a memcache for AIGC applications, similar to how Redis works for traditional applications."
category = "main"
optional = false
python-versions = ">=3.8.1"
files = [
{file = "gptcache-0.1.21-py3-none-any.whl", hash = "sha256:76322a19f96fe0576857072c62a7b29bc680dfde719d551d5bc1aedd0d8a5f34"},
{file = "gptcache-0.1.21.tar.gz", hash = "sha256:4c3eb750b972cc95681233358a7bbfd61233827e76ae81be47668552132a9002"},
{file = "gptcache-0.1.22-py3-none-any.whl", hash = "sha256:081fada6f4f2f57ef2955ee1ce1224eb4f3511546d7efd483648f1ff8d257fdb"},
{file = "gptcache-0.1.22.tar.gz", hash = "sha256:5fb7b7eb7ae774f2ec6c9b9dbcd7829da4a83925776d5edc98181811d8f71a0f"},
]
[package.dependencies]
@@ -2565,7 +2571,7 @@ numpy = ">=1.14.5"
name = "hnswlib"
version = "0.7.0"
description = "hnswlib"
category = "dev"
category = "main"
optional = false
python-versions = "*"
files = [
@@ -2856,14 +2862,14 @@ files = [
[[package]]
name = "ipykernel"
version = "6.22.0"
version = "6.23.0"
description = "IPython Kernel for Jupyter"
category = "dev"
optional = false
python-versions = ">=3.8"
files = [
{file = "ipykernel-6.22.0-py3-none-any.whl", hash = "sha256:1ae6047c1277508933078163721bbb479c3e7292778a04b4bacf0874550977d6"},
{file = "ipykernel-6.22.0.tar.gz", hash = "sha256:302558b81f1bc22dc259fb2a0c5c7cf2f4c0bdb21b50484348f7bafe7fb71421"},
{file = "ipykernel-6.23.0-py3-none-any.whl", hash = "sha256:fc886f1dcdc0ec17f277e4d21fd071c857d381adcb04f3f3735d25325ca323c6"},
{file = "ipykernel-6.23.0.tar.gz", hash = "sha256:bd6f487d9e2744c84f6e667d46462d7647a4c862e70e08282f05a52b9d4b705f"},
]
[package.dependencies]
@@ -2890,14 +2896,14 @@ test = ["flaky", "ipyparallel", "pre-commit", "pytest (>=7.0)", "pytest-asyncio"
[[package]]
name = "ipython"
version = "8.12.1"
version = "8.12.2"
description = "IPython: Productive Interactive Computing"
category = "dev"
optional = false
python-versions = ">=3.8"
files = [
{file = "ipython-8.12.1-py3-none-any.whl", hash = "sha256:e3015a1a4aa09b3984fb81b9cef4f0772af5a549878b81efb094cda8bb121993"},
{file = "ipython-8.12.1.tar.gz", hash = "sha256:2442915417763b62181009259782975fa50bb5eedb97ae97fb614204bf6ecc21"},
{file = "ipython-8.12.2-py3-none-any.whl", hash = "sha256:ea8801f15dfe4ffb76dea1b09b847430ffd70d827b41735c64a0638a04103bfc"},
{file = "ipython-8.12.2.tar.gz", hash = "sha256:c7b80eb7f5a855a88efc971fda506ff7a91c280b42cdae26643e0f601ea281ea"},
]
[package.dependencies]
@@ -3038,20 +3044,20 @@ testing = ["Django (<3.1)", "attrs", "colorama", "docopt", "pytest (<7.0.0)"]
[[package]]
name = "jina"
version = "3.15.0"
version = "3.14.1"
description = "Build multimodal AI services via cloud native technologies · Neural Search · Generative AI · MLOps"
category = "main"
optional = true
python-versions = "*"
files = [
{file = "jina-3.15.0.tar.gz", hash = "sha256:18a3be8ddca14ed66a554d8480a277bcb7620ebc6ae11352a9835c91865f9d1e"},
{file = "jina-3.14.1.tar.gz", hash = "sha256:00b1f5995b13c9a49a2287bd534bd32eb8c05706064752035d569e616a15b411"},
]
[package.dependencies]
aiofiles = "*"
aiohttp = "*"
aiostream = "*"
docarray = ">=0.16.4,<0.30.0"
docarray = ">=0.16.4"
docker = "*"
fastapi = ">=0.76.0"
filelock = "*"
@@ -3085,14 +3091,14 @@ websockets = "*"
aiofiles = ["aiofiles"]
aiohttp = ["aiohttp"]
aiostream = ["aiostream"]
all = ["Pillow", "aiofiles", "aiohttp", "aiostream", "black (==22.3.0)", "bs4", "coverage (==6.2)", "docarray (>=0.16.4,<0.30.0)", "docker", "fastapi (>=0.76.0)", "filelock", "flaky", "grpcio (>=1.46.0,<1.48.1)", "grpcio-health-checking (>=1.46.0,<1.48.1)", "grpcio-reflection (>=1.46.0,<1.48.1)", "jcloud (>=0.0.35)", "jina-hubble-sdk (>=0.30.4)", "jsonschema", "kubernetes (>=18.20.0)", "mock", "numpy", "opentelemetry-api (>=1.12.0)", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-instrumentation-grpc (>=0.35b0)", "opentelemetry-sdk (>=1.14.0)", "opentelemetry-test-utils (>=0.33b0)", "packaging (>=20.0)", "pathspec", "portforward (>=0.2.4,<0.4.3)", "prometheus-api-client (>=0.5.1)", "prometheus_client (>=0.12.0)", "protobuf (>=3.19.0)", "psutil", "pydantic", "pytest", "pytest-asyncio", "pytest-cov (==3.0.0)", "pytest-custom_exit_code", "pytest-kind (==22.11.1)", "pytest-lazy-fixture", "pytest-mock", "pytest-repeat", "pytest-reraise", "pytest-timeout", "python-multipart", "pyyaml (>=5.3.1)", "requests", "requests-mock", "scipy (>=1.6.1)", "sgqlc", "strawberry-graphql (>=0.96.0)", "tensorflow (>=2.0)", "torch", "uvicorn[standard]", "uvloop", "watchfiles (>=0.18.0)", "websockets"]
all = ["Pillow", "aiofiles", "aiohttp", "aiostream", "black (==22.3.0)", "bs4", "coverage (==6.2)", "docarray (>=0.16.4)", "docker", "fastapi (>=0.76.0)", "filelock", "flaky", "grpcio (>=1.46.0,<1.48.1)", "grpcio-health-checking (>=1.46.0,<1.48.1)", "grpcio-reflection (>=1.46.0,<1.48.1)", "jcloud (>=0.0.35)", "jina-hubble-sdk (>=0.30.4)", "jsonschema", "kubernetes (>=18.20.0)", "mock", "numpy", "opentelemetry-api (>=1.12.0)", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-instrumentation-grpc (>=0.35b0)", "opentelemetry-sdk (>=1.14.0)", "opentelemetry-test-utils (>=0.33b0)", "packaging (>=20.0)", "pathspec", "portforward (>=0.2.4)", "prometheus-api-client (>=0.5.1)", "prometheus_client (>=0.12.0)", "protobuf (>=3.19.0)", "psutil", "pydantic", "pytest", "pytest-asyncio", "pytest-cov (==3.0.0)", "pytest-custom_exit_code", "pytest-kind (==22.11.1)", "pytest-lazy-fixture", "pytest-mock", "pytest-repeat", "pytest-reraise", "pytest-timeout", "python-multipart", "pyyaml (>=5.3.1)", "requests", "requests-mock", "scipy (>=1.6.1)", "sgqlc", "strawberry-graphql (>=0.96.0)", "tensorflow (>=2.0)", "torch", "uvicorn[standard]", "uvloop", "watchfiles (>=0.18.0)", "websockets"]
black = ["black (==22.3.0)"]
bs4 = ["bs4"]
cicd = ["bs4", "jsonschema", "portforward (>=0.2.4,<0.4.3)", "sgqlc", "strawberry-graphql (>=0.96.0)", "tensorflow (>=2.0)", "torch"]
core = ["aiostream", "docarray (>=0.16.4,<0.30.0)", "grpcio (>=1.46.0,<1.48.1)", "grpcio-health-checking (>=1.46.0,<1.48.1)", "grpcio-reflection (>=1.46.0,<1.48.1)", "jcloud (>=0.0.35)", "jina-hubble-sdk (>=0.30.4)", "numpy", "opentelemetry-api (>=1.12.0)", "opentelemetry-instrumentation-grpc (>=0.35b0)", "packaging (>=20.0)", "protobuf (>=3.19.0)", "pyyaml (>=5.3.1)"]
cicd = ["bs4", "jsonschema", "portforward (>=0.2.4)", "sgqlc", "strawberry-graphql (>=0.96.0)", "tensorflow (>=2.0)", "torch"]
core = ["docarray (>=0.16.4)", "grpcio (>=1.46.0,<1.48.1)", "grpcio-health-checking (>=1.46.0,<1.48.1)", "grpcio-reflection (>=1.46.0,<1.48.1)", "jcloud (>=0.0.35)", "jina-hubble-sdk (>=0.30.4)", "numpy", "opentelemetry-api (>=1.12.0)", "opentelemetry-instrumentation-grpc (>=0.35b0)", "packaging (>=20.0)", "protobuf (>=3.19.0)", "pyyaml (>=5.3.1)"]
coverage = ["coverage (==6.2)"]
devel = ["aiofiles", "aiohttp", "docker", "fastapi (>=0.76.0)", "filelock", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-sdk (>=1.14.0)", "pathspec", "prometheus_client (>=0.12.0)", "pydantic", "python-multipart", "requests", "sgqlc", "strawberry-graphql (>=0.96.0)", "uvicorn[standard]", "uvloop", "watchfiles (>=0.18.0)", "websockets"]
docarray = ["docarray (>=0.16.4,<0.30.0)"]
devel = ["aiofiles", "aiohttp", "aiostream", "docker", "fastapi (>=0.76.0)", "filelock", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-sdk (>=1.14.0)", "pathspec", "prometheus_client (>=0.12.0)", "pydantic", "python-multipart", "requests", "sgqlc", "strawberry-graphql (>=0.96.0)", "uvicorn[standard]", "uvloop", "watchfiles (>=0.18.0)", "websockets"]
docarray = ["docarray (>=0.16.4)"]
docker = ["docker"]
fastapi = ["fastapi (>=0.76.0)"]
filelock = ["filelock"]
@@ -3119,7 +3125,7 @@ packaging = ["packaging (>=20.0)"]
pathspec = ["pathspec"]
perf = ["opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-sdk (>=1.14.0)", "prometheus_client (>=0.12.0)", "uvloop"]
pillow = ["Pillow"]
portforward = ["portforward (>=0.2.4,<0.4.3)"]
portforward = ["portforward (>=0.2.4)"]
prometheus-api-client = ["prometheus-api-client (>=0.5.1)"]
prometheus-client = ["prometheus_client (>=0.12.0)"]
protobuf = ["protobuf (>=3.19.0)"]
@@ -3141,7 +3147,7 @@ requests = ["requests"]
requests-mock = ["requests-mock"]
scipy = ["scipy (>=1.6.1)"]
sgqlc = ["sgqlc"]
standard = ["aiofiles", "aiohttp", "docker", "fastapi (>=0.76.0)", "filelock", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-sdk (>=1.14.0)", "pathspec", "prometheus_client (>=0.12.0)", "pydantic", "python-multipart", "requests", "uvicorn[standard]", "uvloop", "websockets"]
standard = ["aiofiles", "aiohttp", "aiostream", "docker", "fastapi (>=0.76.0)", "filelock", "opentelemetry-exporter-otlp (>=1.12.0)", "opentelemetry-exporter-prometheus (>=1.12.0rc1)", "opentelemetry-instrumentation-aiohttp-client (>=0.33b0)", "opentelemetry-instrumentation-fastapi (>=0.33b0)", "opentelemetry-sdk (>=1.14.0)", "pathspec", "prometheus_client (>=0.12.0)", "pydantic", "python-multipart", "requests", "uvicorn[standard]", "uvloop", "websockets"]
standrad = ["opentelemetry-exporter-otlp-proto-grpc (>=1.13.0)"]
strawberry-graphql = ["strawberry-graphql (>=0.96.0)"]
tensorflow = ["tensorflow (>=2.0)"]
@@ -3579,18 +3585,18 @@ files = [
[[package]]
name = "lancedb"
version = "0.1.1"
version = "0.1.2"
description = "lancedb"
category = "main"
optional = true
python-versions = ">=3.8"
files = [
{file = "lancedb-0.1.1-py3-none-any.whl", hash = "sha256:f98c993194f48a4adc1d11123382f47af16dd0c6254b8d2e84ddf20453727ea6"},
{file = "lancedb-0.1.1.tar.gz", hash = "sha256:7a6443a8244a370ce43e16f6f424856e275e02e67fe8ee03d7280d67dae0b056"},
{file = "lancedb-0.1.2-py3-none-any.whl", hash = "sha256:aa2baea7d16caeaa4c720c25ab46b5c5d88d8833486724e5a132e5b6cf392663"},
{file = "lancedb-0.1.2.tar.gz", hash = "sha256:d561568dacaa4fcdf5aac262bdb807004bb0dde550a44d43f7cdb4f95956b2bf"},
]
[package.dependencies]
pylance = ">=0.4.4"
pylance = ">=0.4.6"
ratelimiter = "*"
retry = "*"
tqdm = "*"
@@ -4349,14 +4355,14 @@ testing = ["beautifulsoup4", "coverage[toml]", "pytest (>=6,<7)", "pytest-cov",
[[package]]
name = "nbclassic"
version = "0.5.6"
version = "1.0.0"
description = "Jupyter Notebook as a Jupyter Server extension."
category = "dev"
optional = false
python-versions = ">=3.7"
files = [
{file = "nbclassic-0.5.6-py3-none-any.whl", hash = "sha256:e3c8b7de80046c4a36a74662a5e325386d345289906c618366d8154e03dc2322"},
{file = "nbclassic-0.5.6.tar.gz", hash = "sha256:aab53fa1bea084fb6ade5c538b011a4f070c69f88d72878a8e8fb356f152509f"},
{file = "nbclassic-1.0.0-py3-none-any.whl", hash = "sha256:f99e4769b4750076cd4235c044b61232110733322384a94a63791d2e7beacc66"},
{file = "nbclassic-1.0.0.tar.gz", hash = "sha256:0ae11eb2319455d805596bf320336cda9554b41d99ab9a3c31bf8180bffa30e3"},
]
[package.dependencies]
@@ -4408,14 +4414,14 @@ test = ["flaky", "ipykernel", "ipython", "ipywidgets", "nbconvert (>=7.0.0)", "p
[[package]]
name = "nbconvert"
version = "7.3.1"
version = "7.4.0"
description = "Converting Jupyter Notebooks"
category = "dev"
optional = false
python-versions = ">=3.7"
files = [
{file = "nbconvert-7.3.1-py3-none-any.whl", hash = "sha256:d2e95904666f1ff77d36105b9de4e0801726f93b862d5b28f69e93d99ad3b19c"},
{file = "nbconvert-7.3.1.tar.gz", hash = "sha256:78685362b11d2e8058e70196fe83b09abed8df22d3e599cf271f4d39fdc48b9e"},
{file = "nbconvert-7.4.0-py3-none-any.whl", hash = "sha256:af5064a9db524f9f12f4e8be7f0799524bd5b14c1adea37e34e83c95127cc818"},
{file = "nbconvert-7.4.0.tar.gz", hash = "sha256:51b6c77b507b177b73f6729dba15676e42c4e92bcb00edc8cc982ee72e7d89d7"},
]
[package.dependencies]
@@ -5201,6 +5207,62 @@ numpy = ">=1.7"
docs = ["numpydoc", "sphinx (==1.2.3)", "sphinx-rtd-theme", "sphinxcontrib-napoleon"]
tests = ["pytest", "pytest-cov", "pytest-pep8"]
[[package]]
name = "orjson"
version = "3.8.12"
description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
category = "main"
optional = true
python-versions = ">=3.7"
files = [
{file = "orjson-3.8.12-cp310-cp310-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:c84046e890e13a119404a83f2e09e622509ed4692846ff94c4ca03654fbc7fb5"},
{file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29706dd8189835bcf1781faed286e99ae54fd6165437d364dfdbf0276bf39b19"},
{file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f4e22b0aa70c963ac01fcd620de15be21a5027711b0e5d4b96debcdeea43e3ae"},
{file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6d1acf52d3a4b9384af09a5c2658c3a7a472a4d62a0ad1fe2c8fab8ef460c9b4"},
{file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a72b50719bdd6bb0acfca3d4d1c841aa4b191f3ff37268e7aba04e5d6be44ccd"},
{file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83e8c740a718fa6d511a82e463adc7ab17631c6eea81a716b723e127a9c51d57"},
{file = "orjson-3.8.12-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:ebb03e4c7648f7bb299872002a6120082da018f41ba7a9ebf4ceae8d765443d2"},
{file = "orjson-3.8.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:44f7bb4c995652106276442de1147c9993716d1e2d79b7fd435afa154ff236b9"},
{file = "orjson-3.8.12-cp310-none-win_amd64.whl", hash = "sha256:06e528f9a84fbb4000fd0eee573b5db543ee70ae586fdbc53e740b0ac981701c"},
{file = "orjson-3.8.12-cp311-cp311-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:9a6c1594d5a9ff56e5babc4a87ac372af38d37adef9e06744e9f158431e33f43"},
{file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6390ce0bce24c107fc275736aa8a4f768ef7eb5df935d7dca0cc99815eb5d99"},
{file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:efb3a10030462a22c731682434df5c137a67632a8339f821cd501920b169007e"},
{file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7e405d54c84c30d9b1c918c290bcf4ef484a45c69d5583a95db81ffffba40b44"},
{file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd6fbd1413559572e81b5ac64c45388147c3ba85cc3df2eaa11002945e0dbd1f"},
{file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f480ae7b84369b1860d8867f0baf8d885fede400fda390ce088bfa8edf97ffdc"},
{file = "orjson-3.8.12-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:355055e0977c43b0e5325b9312b7208c696fe20cd54eed1d6fc80b0a4d6721f5"},
{file = "orjson-3.8.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d937503e4dfba5edc8d5e0426d3cc97ed55716e93212b2e12a198664487b9965"},
{file = "orjson-3.8.12-cp311-none-win_amd64.whl", hash = "sha256:eb16e0195febd24b44f4db1ab3be85ecf6038f92fd511370cebc004b3d422294"},
{file = "orjson-3.8.12-cp37-cp37m-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:dc27a8ec13f28e92dc1ea89bf1232d77e7d3ebfd5c1ccf4f3729a70561cb63bd"},
{file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77710774faed337ac4ad919dadc5f3b655b0cd40518e5386e6f1f116de9c6c25"},
{file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7e549468867991f6f9cfbd9c5bbc977330173bd8f6ceb79973bbd4634e13e1b9"},
{file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:96fb1eb82b578eb6c0e53e3cf950839fe98ea210626f87c8204bd4fc2cc6ba02"},
{file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d153b228b6e24f8bccf732a51e01e8e938eef59efed9030c5c257778fbe0804"},
{file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:becbd5af6d035a7ec2ee3239d4700929d52d8517806b97dd04efcc37289403f7"},
{file = "orjson-3.8.12-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7d63f524048825e05950db3b6998c756d5377a5e8c469b2e3bdb9f3217523d74"},
{file = "orjson-3.8.12-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ec4f0130d9a27cb400423e09e0f9e46480e9e977f05fdcf663a7a2c68735513e"},
{file = "orjson-3.8.12-cp37-none-win_amd64.whl", hash = "sha256:6f1b01f641f5e87168b819ac1cbd81aa6278e7572c326f3d27e92dea442a2c0d"},
{file = "orjson-3.8.12-cp38-cp38-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:062e67108c218fdb9475edd5272b1629c05b56c66416fa915de5656adde30e73"},
{file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ba645c92801417933fa74448622ba614a275ea82df05e888095c7742d913bb4"},
{file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7d50d9b1ae409ea15534365fec0ce8a5a5f7dc94aa790aacfb8cfec87ab51aa4"},
{file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8f00038bf5d07439d13c0c2c5cd6ad48eb86df7dbd7a484013ce6a113c421b14"},
{file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:397670665f94cf5cff779054781d80395084ba97191d82f7b3a86f0a20e6102b"},
{file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f568205519bb0197ca91915c5da6058cfbb59993e557b02dfc3b2718b34770a"},
{file = "orjson-3.8.12-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:4fd240e736ce52cd757d74142d9933fd35a3184396be887c435f0574e0388654"},
{file = "orjson-3.8.12-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6cae2ff288a80e81ce30313e735c5436495ab58cf8d4fbe84900e616d0ee7a78"},
{file = "orjson-3.8.12-cp38-none-win_amd64.whl", hash = "sha256:710c40c214b753392e46f9275fd795e9630dd737a5ab4ac6e4ee1a02fe83cc0d"},
{file = "orjson-3.8.12-cp39-cp39-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:aff761de5ed5543a0a51e9f703668624749aa2239de5d7d37d9c9693daeaf5dc"},
{file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:135f29cf936283a0cd1b8bce86540ca181108f2a4d4483eedad6b8026865d2a9"},
{file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:62f999798f2fa55e567d483864ebfc30120fb055c2696a255979439323a5b15c"},
{file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3fa58ca064c640fa9d823f98fbbc8e71940ecb78cea3ac2507da1cbf49d60b51"},
{file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8682f752c19f6a7d9fc727fd98588b4c8b0dce791b5794bb814c7379ccd64a79"},
{file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de3d096dde3e46d01841abc1982b906694ab3c92f338d37a2e6184739dc8a958"},
{file = "orjson-3.8.12-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:834b50df79f1fe89bbaced3a1c1d8c8c92cc99e84cdcd374d8da4974b3560d2a"},
{file = "orjson-3.8.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:2ad149ed76dce2bbdfbadd61c35959305e77141badf364a158beb4ef3d88ec37"},
{file = "orjson-3.8.12-cp39-none-win_amd64.whl", hash = "sha256:82d65e478a21f98107b4eb8390104746bb3024c27084b57edab7d427385f1f70"},
{file = "orjson-3.8.12.tar.gz", hash = "sha256:9f0f042cf002a474a6aea006dd9f8d7a5497e35e5fb190ec78eb4d232ec19955"},
]
[[package]]
name = "packaging"
version = "23.1"
@@ -5777,37 +5839,36 @@ requests = "*"
[[package]]
name = "protobuf"
version = "3.19.6"
version = "3.19.0"
description = "Protocol Buffers"
category = "main"
optional = true
python-versions = ">=3.5"
files = [
{file = "protobuf-3.19.6-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:010be24d5a44be7b0613750ab40bc8b8cedc796db468eae6c779b395f50d1fa1"},
{file = "protobuf-3.19.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11478547958c2dfea921920617eb457bc26867b0d1aa065ab05f35080c5d9eb6"},
{file = "protobuf-3.19.6-cp310-cp310-win32.whl", hash = "sha256:559670e006e3173308c9254d63facb2c03865818f22204037ab76f7a0ff70b5f"},
{file = "protobuf-3.19.6-cp310-cp310-win_amd64.whl", hash = "sha256:347b393d4dd06fb93a77620781e11c058b3b0a5289262f094379ada2920a3730"},
{file = "protobuf-3.19.6-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:a8ce5ae0de28b51dff886fb922012dad885e66176663950cb2344c0439ecb473"},
{file = "protobuf-3.19.6-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90b0d02163c4e67279ddb6dc25e063db0130fc299aefabb5d481053509fae5c8"},
{file = "protobuf-3.19.6-cp36-cp36m-win32.whl", hash = "sha256:30f5370d50295b246eaa0296533403961f7e64b03ea12265d6dfce3a391d8992"},
{file = "protobuf-3.19.6-cp36-cp36m-win_amd64.whl", hash = "sha256:0c0714b025ec057b5a7600cb66ce7c693815f897cfda6d6efb58201c472e3437"},
{file = "protobuf-3.19.6-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:5057c64052a1f1dd7d4450e9aac25af6bf36cfbfb3a1cd89d16393a036c49157"},
{file = "protobuf-3.19.6-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:bb6776bd18f01ffe9920e78e03a8676530a5d6c5911934c6a1ac6eb78973ecb6"},
{file = "protobuf-3.19.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:84a04134866861b11556a82dd91ea6daf1f4925746b992f277b84013a7cc1229"},
{file = "protobuf-3.19.6-cp37-cp37m-win32.whl", hash = "sha256:4bc98de3cdccfb5cd769620d5785b92c662b6bfad03a202b83799b6ed3fa1fa7"},
{file = "protobuf-3.19.6-cp37-cp37m-win_amd64.whl", hash = "sha256:aa3b82ca1f24ab5326dcf4ea00fcbda703e986b22f3d27541654f749564d778b"},
{file = "protobuf-3.19.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2b2d2913bcda0e0ec9a784d194bc490f5dc3d9d71d322d070b11a0ade32ff6ba"},
{file = "protobuf-3.19.6-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:d0b635cefebd7a8a0f92020562dead912f81f401af7e71f16bf9506ff3bdbb38"},
{file = "protobuf-3.19.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7a552af4dc34793803f4e735aabe97ffc45962dfd3a237bdde242bff5a3de684"},
{file = "protobuf-3.19.6-cp38-cp38-win32.whl", hash = "sha256:0469bc66160180165e4e29de7f445e57a34ab68f49357392c5b2f54c656ab25e"},
{file = "protobuf-3.19.6-cp38-cp38-win_amd64.whl", hash = "sha256:91d5f1e139ff92c37e0ff07f391101df77e55ebb97f46bbc1535298d72019462"},
{file = "protobuf-3.19.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c0ccd3f940fe7f3b35a261b1dd1b4fc850c8fde9f74207015431f174be5976b3"},
{file = "protobuf-3.19.6-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:30a15015d86b9c3b8d6bf78d5b8c7749f2512c29f168ca259c9d7727604d0e39"},
{file = "protobuf-3.19.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:878b4cd080a21ddda6ac6d1e163403ec6eea2e206cf225982ae04567d39be7b0"},
{file = "protobuf-3.19.6-cp39-cp39-win32.whl", hash = "sha256:5a0d7539a1b1fb7e76bf5faa0b44b30f812758e989e59c40f77a7dab320e79b9"},
{file = "protobuf-3.19.6-cp39-cp39-win_amd64.whl", hash = "sha256:bbf5cea5048272e1c60d235c7bd12ce1b14b8a16e76917f371c718bd3005f045"},
{file = "protobuf-3.19.6-py2.py3-none-any.whl", hash = "sha256:14082457dc02be946f60b15aad35e9f5c69e738f80ebbc0900a19bc83734a5a4"},
{file = "protobuf-3.19.6.tar.gz", hash = "sha256:5f5540d57a43042389e87661c6eaa50f47c19c6176e8cf1c4f287aeefeccb5c4"},
{file = "protobuf-3.19.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:01a0645ef3acddfbc90237e1cdfae1086130fc7cb480b5874656193afd657083"},
{file = "protobuf-3.19.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:d3861c9721a90ba83ee0936a9cfcc4fa1c4b4144ac9658fb6f6343b38558e9b4"},
{file = "protobuf-3.19.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b64be5d7270cf5e76375bac049846e8a9543a2d4368b69afe78ab725380a7487"},
{file = "protobuf-3.19.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:2f6046b9e2feee0dce994493186e8715b4392ed5f50f356280ad9c2f9f93080a"},
{file = "protobuf-3.19.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac2f8ec942d414609aba0331952ae12bb823e8f424bbb6b8c422f1cef32dc842"},
{file = "protobuf-3.19.0-cp36-cp36m-win32.whl", hash = "sha256:3fea09aa04ef2f8b01fcc9bb87f19509934f8a35d177c865b8f9ee5c32b60c1b"},
{file = "protobuf-3.19.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d1f4277d321f60456845ca9b882c4845736f1f5c1c69eb778eba22a97977d8af"},
{file = "protobuf-3.19.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8488c2276f14f294e890cc1260ab342a13e90cd20dcc03319d2eea258f1fd321"},
{file = "protobuf-3.19.0-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:36bf292f44966c67080e535321501717f4f1eba30faef8f2cd4b0c745a027211"},
{file = "protobuf-3.19.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c99af73ae34c93e0e2ace57ea2e70243f34fc015c8c23fd39ee93652e726f7e7"},
{file = "protobuf-3.19.0-cp37-cp37m-win32.whl", hash = "sha256:f7a031cf8e2fc14acc0ba694f6dff0a01e06b70d817eba6edc72ee6cc20517ac"},
{file = "protobuf-3.19.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d4ca5f0c7bc8d2e6966ca3bbd85e9ebe7191b6e21f067896d4af6b28ecff29fe"},
{file = "protobuf-3.19.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9a8a880593015ef2c83f7af797fa4fbf583b2c98b4bd94e46c5b61fee319d84b"},
{file = "protobuf-3.19.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:6f16925f5c977dd7787973a50c242e60c22b1d1182aba6bec7bd02862579c10f"},
{file = "protobuf-3.19.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9097327d277b0aa4a3224e61cd6850aef3269172397715299bcffc9f90293c9"},
{file = "protobuf-3.19.0-cp38-cp38-win32.whl", hash = "sha256:708d04394a63ee9bdc797938b6e15ed5bf24a1cb37743eb3886fd74a5a67a234"},
{file = "protobuf-3.19.0-cp38-cp38-win_amd64.whl", hash = "sha256:ee4d07d596357f51316b6ecf1cc1927660e9d5e418385bb1c51fd2496cd9bee7"},
{file = "protobuf-3.19.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:34a77b8fafdeb8f89fee2b7108ae60d8958d72e33478680cc1e05517892ecc46"},
{file = "protobuf-3.19.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:4f93e0f6af796ddd1502225ff8ea25340ced186ca05b601c44d5c88b45ba80a0"},
{file = "protobuf-3.19.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:942dd6bc8bd2a3c6a156d8ab0f80bd45313f22b78e1176283270054dcc8ca4c2"},
{file = "protobuf-3.19.0-cp39-cp39-win32.whl", hash = "sha256:7b3867795708ac88fde8d6f34f0d9a50af56087e41f624bdb2e9ff808ea5dda7"},
{file = "protobuf-3.19.0-cp39-cp39-win_amd64.whl", hash = "sha256:a74432e9d28a6072a2359a0f49f81eb14dd718e7dbbfb6c0789b456c49e1f130"},
{file = "protobuf-3.19.0-py2.py3-none-any.whl", hash = "sha256:c96e94d3e523a82caa3e5f74b35dd1c4884199358d01c950d95c341255ff48bc"},
{file = "protobuf-3.19.0.tar.gz", hash = "sha256:6a1dc6584d24ef86f5b104bcad64fa0fe06ed36e5687f426e0445d363a041d18"},
]
[[package]]
@@ -6223,16 +6284,16 @@ tests = ["coverage[toml] (==5.0.4)", "pytest (>=6.0.0,<7.0.0)"]
[[package]]
name = "pylance"
version = "0.4.4"
version = "0.4.6"
description = "python wrapper for lance-rs"
category = "main"
optional = true
python-versions = ">=3.8"
files = [
{file = "pylance-0.4.4-cp38-abi3-macosx_10_15_x86_64.whl", hash = "sha256:bd6a0e62bb49db2abba05183e1eea18da20ecde7653cd111a9c814e9323d5c6a"},
{file = "pylance-0.4.4-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:eb432fe63c89059185f28b1a24e3f2d711258231ef770f5ac1cb9bd18ce4b627"},
{file = "pylance-0.4.4-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87024b00e816cfce16a6693ec85112314e5dd3613dbf9eafa858c82e8a72a570"},
{file = "pylance-0.4.4-cp38-abi3-win_amd64.whl", hash = "sha256:f5f6642540ad4cecb6afc421bd7480ebce56ab61971d0adb69944613d9b7ed27"},
{file = "pylance-0.4.6-cp38-abi3-macosx_10_15_x86_64.whl", hash = "sha256:ca295089231dfd982dc1ab24ce92765ac70ab06d7e1567de7a2262b2c785d466"},
{file = "pylance-0.4.6-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:2c6f6b427bccf2c6870922f6a7f80156d9d3668c7f6f0f8192385c32dacefd24"},
{file = "pylance-0.4.6-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d7432c8b918a751121ecdb0e211c586e47c59721f5f0116d44204192ec35ccc"},
{file = "pylance-0.4.6-cp38-abi3-win_amd64.whl", hash = "sha256:cc654a35d4b92bdf69f4456719ca4002ac236762f5b335d76b820afe955389fa"},
]
[package.dependencies]
@@ -6923,14 +6984,14 @@ urllib3 = ">=1.26.14,<2.0.0"
[[package]]
name = "qtconsole"
version = "5.4.2"
version = "5.4.3"
description = "Jupyter Qt console"
category = "dev"
optional = false
python-versions = ">= 3.7"
files = [
{file = "qtconsole-5.4.2-py3-none-any.whl", hash = "sha256:30975c6a7d7941dd646d00a23e5982db49beaa60c3920bb243727d43da805f12"},
{file = "qtconsole-5.4.2.tar.gz", hash = "sha256:dc935780da276a2ab31a7a08a8cf327a2ea47fa27e21d485073251a7eeb16167"},
{file = "qtconsole-5.4.3-py3-none-any.whl", hash = "sha256:35fd6e87b1f6d1fd41801b07e69339f8982e76afd4fa8ef35595bc6036717189"},
{file = "qtconsole-5.4.3.tar.gz", hash = "sha256:5e4082a86a201796b2a5cfd4298352d22b158b51b57736531824715fc2a979dd"},
]
[package.dependencies]
@@ -7268,14 +7329,14 @@ files = [
[[package]]
name = "s3transfer"
version = "0.6.0"
version = "0.6.1"
description = "An Amazon S3 Transfer Manager"
category = "main"
optional = false
python-versions = ">= 3.7"
files = [
{file = "s3transfer-0.6.0-py3-none-any.whl", hash = "sha256:06176b74f3a15f61f1b4f25a1fc29a4429040b7647133a463da8fa5bd28d5ecd"},
{file = "s3transfer-0.6.0.tar.gz", hash = "sha256:2ed07d3866f523cc561bf4a00fc5535827981b117dd7876f036b0c1aca42c947"},
{file = "s3transfer-0.6.1-py3-none-any.whl", hash = "sha256:3c0da2d074bf35d6870ef157158641178a4204a6e689e82546083e31e0311346"},
{file = "s3transfer-0.6.1.tar.gz", hash = "sha256:640bb492711f4c0c0905e1f62b6aaeb771881935ad27884852411f8e9cacbca9"},
]
[package.dependencies]
@@ -8267,18 +8328,18 @@ files = [
[[package]]
name = "tensorflow-hub"
version = "0.13.0"
version = "0.12.0"
description = "TensorFlow Hub is a library to foster the publication, discovery, and consumption of reusable parts of machine learning models."
category = "main"
optional = true
python-versions = "*"
files = [
{file = "tensorflow_hub-0.13.0-py2.py3-none-any.whl", hash = "sha256:3544f4fd9fd99e4eeb6da1b5b5320e4a2dbdef7f9bb778f66f76d6790f32dd65"},
{file = "tensorflow_hub-0.12.0-py2.py3-none-any.whl", hash = "sha256:822fe5f7338c95efcc3a534011c6689e4309ba2459def87194179c4de8a6e1fc"},
]
[package.dependencies]
numpy = ">=1.12.0"
protobuf = ">=3.19.6"
protobuf = ">=3.8.0"
[package.extras]
make-image-classifier = ["keras-preprocessing[image]"]
@@ -8904,14 +8965,14 @@ files = [
[[package]]
name = "types-redis"
version = "4.5.4.1"
version = "4.5.4.2"
description = "Typing stubs for redis"
category = "dev"
optional = false
python-versions = "*"
files = [
{file = "types-redis-4.5.4.1.tar.gz", hash = "sha256:bf04192f415b2b42ecefd70bb4b91eb0352e48f2716a213e038e35c096a639c2"},
{file = "types_redis-4.5.4.1-py3-none-any.whl", hash = "sha256:2db530f54facec3149147bfe61d5ac24f5fe4e871823d95a601cd2c1d775d8a0"},
{file = "types-redis-4.5.4.2.tar.gz", hash = "sha256:7979ce406cd7b4a0093b10a377e5060c5c890e8463cd1ef50423c1669efbc075"},
{file = "types_redis-4.5.4.2-py3-none-any.whl", hash = "sha256:b6f7e44aae1a79732f694cb6df6093e38361382d2be03780460684ef59745d62"},
]
[package.dependencies]
@@ -8920,18 +8981,18 @@ types-pyOpenSSL = "*"
[[package]]
name = "types-requests"
version = "2.29.0.0"
version = "2.30.0.0"
description = "Typing stubs for requests"
category = "dev"
category = "main"
optional = false
python-versions = "*"
files = [
{file = "types-requests-2.29.0.0.tar.gz", hash = "sha256:c86f4a955d943d2457120dbe719df24ef0924e11177164d10a0373cf311d7b4d"},
{file = "types_requests-2.29.0.0-py3-none-any.whl", hash = "sha256:4cf6e323e856c779fbe8815bb977a5bf5d6c5034713e4c17ff2a9a20610f5b27"},
{file = "types-requests-2.30.0.0.tar.gz", hash = "sha256:dec781054324a70ba64430ae9e62e7e9c8e4618c185a5cb3f87a6738251b5a31"},
{file = "types_requests-2.30.0.0-py3-none-any.whl", hash = "sha256:c6cf08e120ca9f0dc4fa4e32c3f953c3fba222bcc1db6b97695bce8da1ba9864"},
]
[package.dependencies]
types-urllib3 = "<1.27"
types-urllib3 = "*"
[[package]]
name = "types-toml"
@@ -8949,7 +9010,7 @@ files = [
name = "types-urllib3"
version = "1.26.25.12"
description = "Typing stubs for urllib3"
category = "dev"
category = "main"
optional = false
python-versions = "*"
files = [
@@ -9271,14 +9332,14 @@ files = [
[[package]]
name = "weaviate-client"
version = "3.16.2"
version = "3.17.1"
description = "A python native weaviate client"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "weaviate-client-3.16.2.tar.gz", hash = "sha256:709066d122a9d28b55e8558b02c24a296d922c77dfb72cc3a5401fd10540e138"},
{file = "weaviate_client-3.16.2-py3-none-any.whl", hash = "sha256:dae0b6f923ad4a82de7b26819a397743db3da5a2ffcb872ae98a50b92bdbf2b9"},
{file = "weaviate-client-3.17.1.tar.gz", hash = "sha256:04277030396a0e63e73b994a185c705f07f948254d27c0a3774c60b4795c37ab"},
{file = "weaviate_client-3.17.1-py3-none-any.whl", hash = "sha256:0c86f4d5fcb155efd0888515c8caa20364241c0df01dead361ce0c023dbc5da9"},
]
[package.dependencies]
@@ -9337,82 +9398,82 @@ test = ["websockets"]
[[package]]
name = "websockets"
version = "11.0.2"
version = "11.0.3"
description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "websockets-11.0.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:580cc95c58118f8c39106be71e24d0b7e1ad11a155f40a2ee687f99b3e5e432e"},
{file = "websockets-11.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:143782041e95b63083b02107f31cda999f392903ae331de1307441f3a4557d51"},
{file = "websockets-11.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8df63dcd955eb6b2e371d95aacf8b7c535e482192cff1b6ce927d8f43fb4f552"},
{file = "websockets-11.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca9b2dced5cbbc5094678cc1ec62160f7b0fe4defd601cd28a36fde7ee71bbb5"},
{file = "websockets-11.0.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e0eeeea3b01c97fd3b5049a46c908823f68b59bf0e18d79b231d8d6764bc81ee"},
{file = "websockets-11.0.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:502683c5dedfc94b9f0f6790efb26aa0591526e8403ad443dce922cd6c0ec83b"},
{file = "websockets-11.0.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d3cc3e48b6c9f7df8c3798004b9c4b92abca09eeea5e1b0a39698f05b7a33b9d"},
{file = "websockets-11.0.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:808b8a33c961bbd6d33c55908f7c137569b09ea7dd024bce969969aa04ecf07c"},
{file = "websockets-11.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:34a6f8996964ccaa40da42ee36aa1572adcb1e213665e24aa2f1037da6080909"},
{file = "websockets-11.0.2-cp310-cp310-win32.whl", hash = "sha256:8f24cd758cbe1607a91b720537685b64e4d39415649cac9177cd1257317cf30c"},
{file = "websockets-11.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:3b87cd302f08ea9e74fdc080470eddbed1e165113c1823fb3ee6328bc40ca1d3"},
{file = "websockets-11.0.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3565a8f8c7bdde7c29ebe46146bd191290413ee6f8e94cf350609720c075b0a1"},
{file = "websockets-11.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f97e03d4d5a4f0dca739ea274be9092822f7430b77d25aa02da6775e490f6846"},
{file = "websockets-11.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8f392587eb2767afa8a34e909f2fec779f90b630622adc95d8b5e26ea8823cb8"},
{file = "websockets-11.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7742cd4524622cc7aa71734b51294644492a961243c4fe67874971c4d3045982"},
{file = "websockets-11.0.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:46dda4bc2030c335abe192b94e98686615f9274f6b56f32f2dd661fb303d9d12"},
{file = "websockets-11.0.2-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d6b2bfa1d884c254b841b0ff79373b6b80779088df6704f034858e4d705a4802"},
{file = "websockets-11.0.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1df2413266bf48430ef2a752c49b93086c6bf192d708e4a9920544c74cd2baa6"},
{file = "websockets-11.0.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cf45d273202b0c1cec0f03a7972c655b93611f2e996669667414557230a87b88"},
{file = "websockets-11.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a09cce3dacb6ad638fdfa3154d9e54a98efe7c8f68f000e55ca9c716496ca67"},
{file = "websockets-11.0.2-cp311-cp311-win32.whl", hash = "sha256:2174a75d579d811279855df5824676d851a69f52852edb0e7551e0eeac6f59a4"},
{file = "websockets-11.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:c78ca3037a954a4209b9f900e0eabbc471fb4ebe96914016281df2c974a93e3e"},
{file = "websockets-11.0.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3a2100b02d1aaf66dc48ff1b2a72f34f6ebc575a02bc0350cc8e9fbb35940166"},
{file = "websockets-11.0.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dca9708eea9f9ed300394d4775beb2667288e998eb6f542cdb6c02027430c599"},
{file = "websockets-11.0.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:320ddceefd2364d4afe6576195201a3632a6f2e6d207b0c01333e965b22dbc84"},
{file = "websockets-11.0.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2a573c8d71b7af937852b61e7ccb37151d719974146b5dc734aad350ef55a02"},
{file = "websockets-11.0.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:13bd5bebcd16a4b5e403061b8b9dcc5c77e7a71e3c57e072d8dff23e33f70fba"},
{file = "websockets-11.0.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:95c09427c1c57206fe04277bf871b396476d5a8857fa1b99703283ee497c7a5d"},
{file = "websockets-11.0.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2eb042734e710d39e9bc58deab23a65bd2750e161436101488f8af92f183c239"},
{file = "websockets-11.0.2-cp37-cp37m-win32.whl", hash = "sha256:5875f623a10b9ba154cb61967f940ab469039f0b5e61c80dd153a65f024d9fb7"},
{file = "websockets-11.0.2-cp37-cp37m-win_amd64.whl", hash = "sha256:634239bc844131863762865b75211a913c536817c0da27f691400d49d256df1d"},
{file = "websockets-11.0.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:3178d965ec204773ab67985a09f5696ca6c3869afeed0bb51703ea404a24e975"},
{file = "websockets-11.0.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:955fcdb304833df2e172ce2492b7b47b4aab5dcc035a10e093d911a1916f2c87"},
{file = "websockets-11.0.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cb46d2c7631b2e6f10f7c8bac7854f7c5e5288f024f1c137d4633c79ead1e3c0"},
{file = "websockets-11.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25aae96c1060e85836552a113495db6d857400288161299d77b7b20f2ac569f2"},
{file = "websockets-11.0.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2abeeae63154b7f63d9f764685b2d299e9141171b8b896688bd8baec6b3e2303"},
{file = "websockets-11.0.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:daa1e8ea47507555ed7a34f8b49398d33dff5b8548eae3de1dc0ef0607273a33"},
{file = "websockets-11.0.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:954eb789c960fa5daaed3cfe336abc066941a5d456ff6be8f0e03dd89886bb4c"},
{file = "websockets-11.0.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:3ffe251a31f37e65b9b9aca5d2d67fd091c234e530f13d9dce4a67959d5a3fba"},
{file = "websockets-11.0.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:adf6385f677ed2e0b021845b36f55c43f171dab3a9ee0ace94da67302f1bc364"},
{file = "websockets-11.0.2-cp38-cp38-win32.whl", hash = "sha256:aa7b33c1fb2f7b7b9820f93a5d61ffd47f5a91711bc5fa4583bbe0c0601ec0b2"},
{file = "websockets-11.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:220d5b93764dd70d7617f1663da64256df7e7ea31fc66bc52c0e3750ee134ae3"},
{file = "websockets-11.0.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:0fb4480556825e4e6bf2eebdbeb130d9474c62705100c90e59f2f56459ddab42"},
{file = "websockets-11.0.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ec00401846569aaf018700249996143f567d50050c5b7b650148989f956547af"},
{file = "websockets-11.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:87c69f50281126dcdaccd64d951fb57fbce272578d24efc59bce72cf264725d0"},
{file = "websockets-11.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:232b6ba974f5d09b1b747ac232f3a3d8f86de401d7b565e837cc86988edf37ac"},
{file = "websockets-11.0.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:392d409178db1e46d1055e51cc850136d302434e12d412a555e5291ab810f622"},
{file = "websockets-11.0.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a4fe2442091ff71dee0769a10449420fd5d3b606c590f78dd2b97d94b7455640"},
{file = "websockets-11.0.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ede13a6998ba2568b21825809d96e69a38dc43184bdeebbde3699c8baa21d015"},
{file = "websockets-11.0.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:4c54086b2d2aec3c3cb887ad97e9c02c6be9f1d48381c7419a4aa932d31661e4"},
{file = "websockets-11.0.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e37a76ccd483a6457580077d43bc3dfe1fd784ecb2151fcb9d1c73f424deaeba"},
{file = "websockets-11.0.2-cp39-cp39-win32.whl", hash = "sha256:d1881518b488a920434a271a6e8a5c9481a67c4f6352ebbdd249b789c0467ddc"},
{file = "websockets-11.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:25e265686ea385f22a00cc2b719b880797cd1bb53b46dbde969e554fb458bfde"},
{file = "websockets-11.0.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ce69f5c742eefd039dce8622e99d811ef2135b69d10f9aa79fbf2fdcc1e56cd7"},
{file = "websockets-11.0.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b985ba2b9e972cf99ddffc07df1a314b893095f62c75bc7c5354a9c4647c6503"},
{file = "websockets-11.0.2-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1b52def56d2a26e0e9c464f90cadb7e628e04f67b0ff3a76a4d9a18dfc35e3dd"},
{file = "websockets-11.0.2-pp37-pypy37_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d70a438ef2a22a581d65ad7648e949d4ccd20e3c8ed7a90bbc46df4e60320891"},
{file = "websockets-11.0.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:752fbf420c71416fb1472fec1b4cb8631c1aa2be7149e0a5ba7e5771d75d2bb9"},
{file = "websockets-11.0.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:dd906b0cdc417ea7a5f13bb3c6ca3b5fd563338dc596996cb0fdd7872d691c0a"},
{file = "websockets-11.0.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e79065ff6549dd3c765e7916067e12a9c91df2affea0ac51bcd302aaf7ad207"},
{file = "websockets-11.0.2-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:46388a050d9e40316e58a3f0838c63caacb72f94129eb621a659a6e49bad27ce"},
{file = "websockets-11.0.2-pp38-pypy38_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c7de298371d913824f71b30f7685bb07ad13969c79679cca5b1f7f94fec012f"},
{file = "websockets-11.0.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:6d872c972c87c393e6a49c1afbdc596432df8c06d0ff7cd05aa18e885e7cfb7c"},
{file = "websockets-11.0.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b444366b605d2885f0034dd889faf91b4b47668dd125591e2c64bfde611ac7e1"},
{file = "websockets-11.0.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8b967a4849db6b567dec3f7dd5d97b15ce653e3497b8ce0814e470d5e074750"},
{file = "websockets-11.0.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2acdc82099999e44fa7bd8c886f03c70a22b1d53ae74252f389be30d64fd6004"},
{file = "websockets-11.0.2-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:518ed6782d9916c5721ebd61bb7651d244178b74399028302c8617d0620af291"},
{file = "websockets-11.0.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:58477b041099bb504e1a5ddd8aa86302ed1d5c6995bdd3db2b3084ef0135d277"},
{file = "websockets-11.0.2-py3-none-any.whl", hash = "sha256:5004c087d17251938a52cce21b3dbdabeecbbe432ce3f5bbbf15d8692c36eac9"},
{file = "websockets-11.0.2.tar.gz", hash = "sha256:b1a69701eb98ed83dd099de4a686dc892c413d974fa31602bc00aca7cb988ac9"},
{file = "websockets-11.0.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3ccc8a0c387629aec40f2fc9fdcb4b9d5431954f934da3eaf16cdc94f67dbfac"},
{file = "websockets-11.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d67ac60a307f760c6e65dad586f556dde58e683fab03323221a4e530ead6f74d"},
{file = "websockets-11.0.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:84d27a4832cc1a0ee07cdcf2b0629a8a72db73f4cf6de6f0904f6661227f256f"},
{file = "websockets-11.0.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffd7dcaf744f25f82190856bc26ed81721508fc5cbf2a330751e135ff1283564"},
{file = "websockets-11.0.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7622a89d696fc87af8e8d280d9b421db5133ef5b29d3f7a1ce9f1a7bf7fcfa11"},
{file = "websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bceab846bac555aff6427d060f2fcfff71042dba6f5fca7dc4f75cac815e57ca"},
{file = "websockets-11.0.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:54c6e5b3d3a8936a4ab6870d46bdd6ec500ad62bde9e44462c32d18f1e9a8e54"},
{file = "websockets-11.0.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:41f696ba95cd92dc047e46b41b26dd24518384749ed0d99bea0a941ca87404c4"},
{file = "websockets-11.0.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:86d2a77fd490ae3ff6fae1c6ceaecad063d3cc2320b44377efdde79880e11526"},
{file = "websockets-11.0.3-cp310-cp310-win32.whl", hash = "sha256:2d903ad4419f5b472de90cd2d40384573b25da71e33519a67797de17ef849b69"},
{file = "websockets-11.0.3-cp310-cp310-win_amd64.whl", hash = "sha256:1d2256283fa4b7f4c7d7d3e84dc2ece74d341bce57d5b9bf385df109c2a1a82f"},
{file = "websockets-11.0.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e848f46a58b9fcf3d06061d17be388caf70ea5b8cc3466251963c8345e13f7eb"},
{file = "websockets-11.0.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:aa5003845cdd21ac0dc6c9bf661c5beddd01116f6eb9eb3c8e272353d45b3288"},
{file = "websockets-11.0.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b58cbf0697721120866820b89f93659abc31c1e876bf20d0b3d03cef14faf84d"},
{file = "websockets-11.0.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:660e2d9068d2bedc0912af508f30bbeb505bbbf9774d98def45f68278cea20d3"},
{file = "websockets-11.0.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c1f0524f203e3bd35149f12157438f406eff2e4fb30f71221c8a5eceb3617b6b"},
{file = "websockets-11.0.3-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:def07915168ac8f7853812cc593c71185a16216e9e4fa886358a17ed0fd9fcf6"},
{file = "websockets-11.0.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:b30c6590146e53149f04e85a6e4fcae068df4289e31e4aee1fdf56a0dead8f97"},
{file = "websockets-11.0.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:619d9f06372b3a42bc29d0cd0354c9bb9fb39c2cbc1a9c5025b4538738dbffaf"},
{file = "websockets-11.0.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:01f5567d9cf6f502d655151645d4e8b72b453413d3819d2b6f1185abc23e82dd"},
{file = "websockets-11.0.3-cp311-cp311-win32.whl", hash = "sha256:e1459677e5d12be8bbc7584c35b992eea142911a6236a3278b9b5ce3326f282c"},
{file = "websockets-11.0.3-cp311-cp311-win_amd64.whl", hash = "sha256:e7837cb169eca3b3ae94cc5787c4fed99eef74c0ab9506756eea335e0d6f3ed8"},
{file = "websockets-11.0.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:9f59a3c656fef341a99e3d63189852be7084c0e54b75734cde571182c087b152"},
{file = "websockets-11.0.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2529338a6ff0eb0b50c7be33dc3d0e456381157a31eefc561771ee431134a97f"},
{file = "websockets-11.0.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:34fd59a4ac42dff6d4681d8843217137f6bc85ed29722f2f7222bd619d15e95b"},
{file = "websockets-11.0.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:332d126167ddddec94597c2365537baf9ff62dfcc9db4266f263d455f2f031cb"},
{file = "websockets-11.0.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:6505c1b31274723ccaf5f515c1824a4ad2f0d191cec942666b3d0f3aa4cb4007"},
{file = "websockets-11.0.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:f467ba0050b7de85016b43f5a22b46383ef004c4f672148a8abf32bc999a87f0"},
{file = "websockets-11.0.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:9d9acd80072abcc98bd2c86c3c9cd4ac2347b5a5a0cae7ed5c0ee5675f86d9af"},
{file = "websockets-11.0.3-cp37-cp37m-win32.whl", hash = "sha256:e590228200fcfc7e9109509e4d9125eace2042fd52b595dd22bbc34bb282307f"},
{file = "websockets-11.0.3-cp37-cp37m-win_amd64.whl", hash = "sha256:b16fff62b45eccb9c7abb18e60e7e446998093cdcb50fed33134b9b6878836de"},
{file = "websockets-11.0.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fb06eea71a00a7af0ae6aefbb932fb8a7df3cb390cc217d51a9ad7343de1b8d0"},
{file = "websockets-11.0.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:8a34e13a62a59c871064dfd8ffb150867e54291e46d4a7cf11d02c94a5275bae"},
{file = "websockets-11.0.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4841ed00f1026dfbced6fca7d963c4e7043aa832648671b5138008dc5a8f6d99"},
{file = "websockets-11.0.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a073fc9ab1c8aff37c99f11f1641e16da517770e31a37265d2755282a5d28aa"},
{file = "websockets-11.0.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:68b977f21ce443d6d378dbd5ca38621755f2063d6fdb3335bda981d552cfff86"},
{file = "websockets-11.0.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e1a99a7a71631f0efe727c10edfba09ea6bee4166a6f9c19aafb6c0b5917d09c"},
{file = "websockets-11.0.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:bee9fcb41db2a23bed96c6b6ead6489702c12334ea20a297aa095ce6d31370d0"},
{file = "websockets-11.0.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4b253869ea05a5a073ebfdcb5cb3b0266a57c3764cf6fe114e4cd90f4bfa5f5e"},
{file = "websockets-11.0.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1553cb82942b2a74dd9b15a018dce645d4e68674de2ca31ff13ebc2d9f283788"},
{file = "websockets-11.0.3-cp38-cp38-win32.whl", hash = "sha256:f61bdb1df43dc9c131791fbc2355535f9024b9a04398d3bd0684fc16ab07df74"},
{file = "websockets-11.0.3-cp38-cp38-win_amd64.whl", hash = "sha256:03aae4edc0b1c68498f41a6772d80ac7c1e33c06c6ffa2ac1c27a07653e79d6f"},
{file = "websockets-11.0.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:777354ee16f02f643a4c7f2b3eff8027a33c9861edc691a2003531f5da4f6bc8"},
{file = "websockets-11.0.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8c82f11964f010053e13daafdc7154ce7385ecc538989a354ccc7067fd7028fd"},
{file = "websockets-11.0.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3580dd9c1ad0701169e4d6fc41e878ffe05e6bdcaf3c412f9d559389d0c9e016"},
{file = "websockets-11.0.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f1a3f10f836fab6ca6efa97bb952300b20ae56b409414ca85bff2ad241d2a61"},
{file = "websockets-11.0.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:df41b9bc27c2c25b486bae7cf42fccdc52ff181c8c387bfd026624a491c2671b"},
{file = "websockets-11.0.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:279e5de4671e79a9ac877427f4ac4ce93751b8823f276b681d04b2156713b9dd"},
{file = "websockets-11.0.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:1fdf26fa8a6a592f8f9235285b8affa72748dc12e964a5518c6c5e8f916716f7"},
{file = "websockets-11.0.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:69269f3a0b472e91125b503d3c0b3566bda26da0a3261c49f0027eb6075086d1"},
{file = "websockets-11.0.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:97b52894d948d2f6ea480171a27122d77af14ced35f62e5c892ca2fae9344311"},
{file = "websockets-11.0.3-cp39-cp39-win32.whl", hash = "sha256:c7f3cb904cce8e1be667c7e6fef4516b98d1a6a0635a58a57528d577ac18a128"},
{file = "websockets-11.0.3-cp39-cp39-win_amd64.whl", hash = "sha256:c792ea4eabc0159535608fc5658a74d1a81020eb35195dd63214dcf07556f67e"},
{file = "websockets-11.0.3-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:f2e58f2c36cc52d41f2659e4c0cbf7353e28c8c9e63e30d8c6d3494dc9fdedcf"},
{file = "websockets-11.0.3-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de36fe9c02995c7e6ae6efe2e205816f5f00c22fd1fbf343d4d18c3d5ceac2f5"},
{file = "websockets-11.0.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0ac56b661e60edd453585f4bd68eb6a29ae25b5184fd5ba51e97652580458998"},
{file = "websockets-11.0.3-pp37-pypy37_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e052b8467dd07d4943936009f46ae5ce7b908ddcac3fda581656b1b19c083d9b"},
{file = "websockets-11.0.3-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:42cc5452a54a8e46a032521d7365da775823e21bfba2895fb7b77633cce031bb"},
{file = "websockets-11.0.3-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:e6316827e3e79b7b8e7d8e3b08f4e331af91a48e794d5d8b099928b6f0b85f20"},
{file = "websockets-11.0.3-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8531fdcad636d82c517b26a448dcfe62f720e1922b33c81ce695d0edb91eb931"},
{file = "websockets-11.0.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c114e8da9b475739dde229fd3bc6b05a6537a88a578358bc8eb29b4030fac9c9"},
{file = "websockets-11.0.3-pp38-pypy38_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e063b1865974611313a3849d43f2c3f5368093691349cf3c7c8f8f75ad7cb280"},
{file = "websockets-11.0.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:92b2065d642bf8c0a82d59e59053dd2fdde64d4ed44efe4870fa816c1232647b"},
{file = "websockets-11.0.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0ee68fe502f9031f19d495dae2c268830df2760c0524cbac5d759921ba8c8e82"},
{file = "websockets-11.0.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dcacf2c7a6c3a84e720d1bb2b543c675bf6c40e460300b628bab1b1efc7c034c"},
{file = "websockets-11.0.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b67c6f5e5a401fc56394f191f00f9b3811fe843ee93f4a70df3c389d1adf857d"},
{file = "websockets-11.0.3-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d5023a4b6a5b183dc838808087033ec5df77580485fc533e7dab2567851b0a4"},
{file = "websockets-11.0.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:ed058398f55163a79bb9f06a90ef9ccc063b204bb346c4de78efc5d15abfe602"},
{file = "websockets-11.0.3-py3-none-any.whl", hash = "sha256:6681ba9e7f8f3b19440921e99efbb40fc89f26cd71bf539e45d8c8a25c976dc6"},
{file = "websockets-11.0.3.tar.gz", hash = "sha256:88fc51d9a26b10fc331be344f1781224a375b78488fc343620184e95a4b27016"},
]
[[package]]
@@ -9476,7 +9537,7 @@ name = "wikipedia"
version = "1.4.0"
description = "Wikipedia API for Python"
category = "main"
optional = true
optional = false
python-versions = "*"
files = [
{file = "wikipedia-1.4.0.tar.gz", hash = "sha256:db0fad1829fdd441b1852306e9856398204dc0786d2996dd2e0c8bb8e26133b2"},
@@ -9798,11 +9859,13 @@ cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\
cffi = ["cffi (>=1.11)"]
[extras]
all = ["O365", "aleph-alpha-client", "anthropic", "arxiv", "atlassian-python-api", "azure-cosmos", "azure-identity", "beautifulsoup4", "clickhouse-connect", "cohere", "deeplake", "duckduckgo-search", "elasticsearch", "faiss-cpu", "google-api-python-client", "google-search-results", "gptcache", "html2text", "huggingface_hub", "jina", "jinja2", "jq", "lancedb", "lark", "manifest-ml", "networkx", "nlpcloud", "nltk", "nomic", "openai", "opensearch-py", "pexpect", "pgvector", "pinecone-client", "pinecone-text", "psycopg2-binary", "pyowm", "pypdf", "pytesseract", "pyvespa", "qdrant-client", "redis", "sentence-transformers", "spacy", "tensorflow-text", "tiktoken", "torch", "transformers", "weaviate-client", "wikipedia", "wolframalpha"]
all = ["O365", "aleph-alpha-client", "anthropic", "arxiv", "atlassian-python-api", "azure-cosmos", "azure-identity", "beautifulsoup4", "clickhouse-connect", "cohere", "deeplake", "docarray", "duckduckgo-search", "elasticsearch", "faiss-cpu", "google-api-python-client", "google-search-results", "gptcache", "hnswlib", "html2text", "huggingface_hub", "jina", "jinja2", "jq", "lancedb", "lark", "manifest-ml", "networkx", "nlpcloud", "nltk", "nomic", "openai", "opensearch-py", "pexpect", "pgvector", "pinecone-client", "pinecone-text", "protobuf", "psycopg2-binary", "pyowm", "pypdf", "pytesseract", "pyvespa", "qdrant-client", "redis", "sentence-transformers", "spacy", "tensorflow-text", "tiktoken", "torch", "transformers", "weaviate-client", "wikipedia", "wolframalpha"]
azure = ["azure-core", "azure-cosmos", "azure-identity", "openai"]
cohere = ["cohere"]
embeddings = ["sentence-transformers"]
extended-testing = ["pdfminer-six", "pypdf"]
hnswlib = ["docarray", "hnswlib", "protobuf"]
in-memory-store = ["docarray"]
llms = ["anthropic", "cohere", "huggingface_hub", "manifest-ml", "nlpcloud", "openai", "torch", "transformers"]
openai = ["openai"]
qdrant = ["qdrant-client"]
@@ -9810,4 +9873,4 @@ qdrant = ["qdrant-client"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.8.1,<4.0"
content-hash = "63324f95fc04b48b631353c5e1a1a2ecc1b9dc757441181d4920e9d77cd8951f"
content-hash = "302163050738bb858c34c066dbf684aab5940a430756999940dc9ba66a4f24a6"
pyproject.toml
+6 -1
View File
@@ -78,6 +78,9 @@ pyvespa = {version = "^0.33.0", optional = true}
O365 = {version = "^2.0.26", optional = true}
jq = {version = "^1.4.1", optional = true}
pdfminer-six = {version = "^20221105", optional = true}
docarray = {version="^0.31.0", optional=true}
protobuf = {version="3.19", optional=true}
hnswlib = {version="^0.7.0", optional=true}
[tool.poetry.group.docs.dependencies]
@@ -159,9 +162,11 @@ llms = ["anthropic", "cohere", "openai", "nlpcloud", "huggingface_hub", "manifes
qdrant = ["qdrant-client"]
openai = ["openai"]
cohere = ["cohere"]
in_memory_store = ["docarray"]
hnswlib = ["docarray", "protobuf", "hnswlib"]
embeddings = ["sentence-transformers"]
azure = ["azure-identity", "azure-cosmos", "openai", "azure-core"]
all = ["anthropic", "cohere", "openai", "nlpcloud", "huggingface_hub", "jina", "manifest-ml", "elasticsearch", "opensearch-py", "google-search-results", "faiss-cpu", "sentence-transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "pinecone-text", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text", "pypdf", "networkx", "nomic", "aleph-alpha-client", "deeplake", "pgvector", "psycopg2-binary", "boto3", "pyowm", "pytesseract", "html2text", "atlassian-python-api", "gptcache", "duckduckgo-search", "arxiv", "azure-identity", "clickhouse-connect", "azure-cosmos", "lancedb", "lark", "pexpect", "pyvespa", "O365", "jq"]
all = ["anthropic", "cohere", "openai", "nlpcloud", "huggingface_hub", "jina", "manifest-ml", "elasticsearch", "opensearch-py", "google-search-results", "faiss-cpu", "sentence-transformers", "transformers", "spacy", "nltk", "wikipedia", "beautifulsoup4", "tiktoken", "torch", "jinja2", "pinecone-client", "pinecone-text", "weaviate-client", "redis", "google-api-python-client", "wolframalpha", "qdrant-client", "tensorflow-text", "pypdf", "networkx", "nomic", "aleph-alpha-client", "deeplake", "pgvector", "psycopg2-binary", "boto3", "pyowm", "pytesseract", "html2text", "atlassian-python-api", "gptcache", "duckduckgo-search", "arxiv", "azure-identity", "clickhouse-connect", "azure-cosmos", "lancedb", "lark", "pexpect", "pyvespa", "O365", "jq", "docarray", "protobuf", "hnswlib"]
# An extra used to be able to add extended testing.
extended_testing = ["pypdf", "pdfminer.six"]
tests/integration_tests/vectorstores/docarray/__init__.py
View File
tests/integration_tests/vectorstores/docarray/test_hnsw.py
+148
View File
@@ -0,0 +1,148 @@
from pathlib import Path
from typing import List
import numpy as np
import pytest
from langchain.schema import Document
from langchain.vectorstores.docarray import DocArrayHnswSearch
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
@pytest.fixture
def texts() -> List[str]:
return ["foo", "bar", "baz"]
def test_from_texts(texts: List[str], tmp_path: Path) -> None:
"""Test end to end construction and simple similarity search."""
docsearch = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
n_dim=10,
)
assert docsearch.doc_index.num_docs() == 3
def test_add_texts(texts: List[str], tmp_path: Path) -> None:
"""Test end to end construction and simple similarity search."""
docsearch = DocArrayHnswSearch.from_params(
work_dir=str(tmp_path),
n_dim=10,
embedding=FakeEmbeddings(),
)
docsearch.add_texts(texts=texts)
assert docsearch.doc_index.num_docs() == 3
@pytest.mark.parametrize("metric", ["cosine", "l2"])
def test_sim_search(metric: str, texts: List[str], tmp_path: Path) -> None:
"""Test end to end construction and simple similarity search."""
hnsw_vec_store = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
n_dim=10,
dist_metric=metric,
index=True,
)
output = hnsw_vec_store.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
@pytest.mark.parametrize("metric", ["cosine", "l2"])
def test_sim_search_all_configurations(
metric: str, texts: List[str], tmp_path: Path
) -> None:
"""Test end to end construction and simple similarity search."""
hnsw_vec_store = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
dist_metric=metric,
n_dim=10,
max_elements=8,
ef_construction=300,
ef=20,
M=8,
allow_replace_deleted=False,
num_threads=2,
)
output = hnsw_vec_store.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
@pytest.mark.parametrize("metric", ["cosine", "l2"])
def test_sim_search_by_vector(metric: str, texts: List[str], tmp_path: Path) -> None:
"""Test end to end construction and similarity search by vector."""
hnsw_vec_store = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
n_dim=10,
dist_metric=metric,
)
embedding = [1.0] * 10
output = hnsw_vec_store.similarity_search_by_vector(embedding, k=1)
assert output == [Document(page_content="bar")]
@pytest.mark.parametrize("metric", ["cosine", "l2"])
def test_sim_search_with_score(metric: str, tmp_path: Path) -> None:
"""Test end to end construction and similarity search with score."""
texts = ["foo", "bar", "baz"]
hnsw_vec_store = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
n_dim=10,
dist_metric=metric,
)
output = hnsw_vec_store.similarity_search_with_score("foo", k=1)
assert len(output) == 1
out_doc, out_score = output[0]
assert out_doc == Document(page_content="foo")
assert np.isclose(out_score, 0.0, atol=1.0e-6)
def test_sim_search_with_score_for_ip_metric(texts: List[str], tmp_path: Path) -> None:
"""
Test end to end construction and similarity search with score for ip
(inner-product) metric.
"""
hnsw_vec_store = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
work_dir=str(tmp_path),
n_dim=10,
dist_metric="ip",
)
output = hnsw_vec_store.similarity_search_with_score("foo", k=3)
assert len(output) == 3
for result in output:
assert result[1] == -8.0
@pytest.mark.parametrize("metric", ["cosine", "l2"])
def test_max_marginal_relevance_search(
metric: str, texts: List[str], tmp_path: Path
) -> None:
"""Test MRR search."""
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = DocArrayHnswSearch.from_texts(
texts,
FakeEmbeddings(),
metadatas=metadatas,
dist_metric=metric,
work_dir=str(tmp_path),
n_dim=10,
)
output = docsearch.max_marginal_relevance_search("foo", k=2, fetch_k=3)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="bar", metadata={"page": 1}),
]
tests/integration_tests/vectorstores/docarray/test_in_memory.py
+95
View File
@@ -0,0 +1,95 @@
from pathlib import Path
from typing import List
import numpy as np
import pytest
from langchain.schema import Document
from langchain.vectorstores.docarray import DocArrayInMemorySearch
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
@pytest.fixture
def texts() -> List[str]:
return ["foo", "bar", "baz"]
def test_from_texts(texts: List[str]) -> None:
"""Test end to end construction and simple similarity search."""
docsearch = DocArrayInMemorySearch.from_texts(
texts,
FakeEmbeddings(),
)
assert isinstance(docsearch, DocArrayInMemorySearch)
assert docsearch.doc_index.num_docs() == 3
def test_add_texts(texts: List[str], tmp_path: Path) -> None:
"""Test end to end construction and simple similarity search."""
docsearch = DocArrayInMemorySearch.from_params(FakeEmbeddings())
assert isinstance(docsearch, DocArrayInMemorySearch)
assert docsearch.doc_index.num_docs() == 0
docsearch.add_texts(texts=texts)
assert docsearch.doc_index.num_docs() == 3
@pytest.mark.parametrize("metric", ["cosine_sim", "euclidean_dist", "sqeuclidean_dist"])
def test_sim_search(metric: str, texts: List[str]) -> None:
"""Test end to end construction and simple similarity search."""
texts = ["foo", "bar", "baz"]
in_memory_vec_store = DocArrayInMemorySearch.from_texts(
texts=texts,
embedding=FakeEmbeddings(),
metric=metric,
)
output = in_memory_vec_store.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
@pytest.mark.parametrize("metric", ["cosine_sim", "euclidean_dist", "sqeuclidean_dist"])
def test_sim_search_with_score(metric: str, texts: List[str]) -> None:
"""Test end to end construction and similarity search with score."""
in_memory_vec_store = DocArrayInMemorySearch.from_texts(
texts=texts,
embedding=FakeEmbeddings(),
metric=metric,
)
output = in_memory_vec_store.similarity_search_with_score("foo", k=1)
out_doc, out_score = output[0]
assert out_doc == Document(page_content="foo")
expected_score = 0.0 if "dist" in metric else 1.0
assert np.isclose(out_score, expected_score, atol=1.0e-6)
@pytest.mark.parametrize("metric", ["cosine_sim", "euclidean_dist", "sqeuclidean_dist"])
def test_sim_search_by_vector(metric: str, texts: List[str]) -> None:
"""Test end to end construction and similarity search by vector."""
in_memory_vec_store = DocArrayInMemorySearch.from_texts(
texts=texts,
embedding=FakeEmbeddings(),
metric=metric,
)
embedding = [1.0] * 10
output = in_memory_vec_store.similarity_search_by_vector(embedding, k=1)
assert output == [Document(page_content="bar")]
@pytest.mark.parametrize("metric", ["cosine_sim", "euclidean_dist", "sqeuclidean_dist"])
def test_max_marginal_relevance_search(metric: str, texts: List[str]) -> None:
"""Test MRR search."""
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = DocArrayInMemorySearch.from_texts(
texts, FakeEmbeddings(), metadatas=metadatas, metric=metric
)
output = docsearch.max_marginal_relevance_search("foo", k=2, fetch_k=3)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="bar", metadata={"page": 1}),
]