Metadata-Version: 2.4
Name: langchain-reindexer
Version: 0.1.3
Summary: Reindexer vector store integration for LangChain
Author: Parviz Mirzoev
Author-email: Parviz Mirzoev <parviz.mirzoev@restream.ru>
License: Apache-2.0
Project-URL: Homepage, https://github.com/Restream/reindexer-langchain-community
Project-URL: Repository, https://github.com/Restream/reindexer-langchain-community
Project-URL: Documentation, https://github.com/Restream/reindexer-langchain-community/blob/main/README.md
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: langchain-core>=0.1.0
Requires-Dist: pyreindexer>=0.5.0
Requires-Dist: numpy>=2.0.2
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Requires-Dist: mypy>=1.0.0; extra == "dev"
Dynamic: author
Dynamic: license-file
Dynamic: requires-python

[EN README](https://github.com/Restream/langchain-reindexer/blob/main/README_EN.md)
# Reindexer Vector Store for LangChain

Этот пакет предоставляет интеграцию векторного хранилища для базы данных [Reindexer](https://reindexer.io/) с фреймворком [LangChain](https://github.com/hwchase17/langchain).

## Установка

```bash
pip install langchain-reindexer
```

## Использование
Теперь вы можете использовать векторное хранилище в вашем приложении LangChain:

```python
from langchain_reindexer import ReindexerVectorStore
from langchain_openai import OpenAIEmbeddings

# Инициализация векторного хранилища
vector_store = ReindexerVectorStore(
    embedding=OpenAIEmbeddings(),
    rx_connector_config={"dsn": "builtin:///tmp/my_db"},
    rx_namespace="my_namespace",
)

# Добавление документов
from langchain_core.documents import Document

documents = [
    Document(page_content="foo", metadata={"baz": "bar"}),
    Document(page_content="thud", metadata={"bar": "baz"}),
]

ids = vector_store.add_documents(documents=documents)

# Поиск
results = vector_store.similarity_search(query="thud", k=1)
```
Больше примеров [здесь](https://github.com/Restream/langchain-reindexer/blob/main/examples/reindexer_ru.ipynb) 
## Возможности

- Добавление и удаление документов
- Поиск по сходству с оценкой и без
- Фильтрация по метаданным
- Поиск максимальной предельной релевантности (MMR)
- Асинхронная поддержка
- Сохранение и загрузка конфигурации векторного хранилища
