Reindexer Vector Store for LangChain
Этот пакет предоставляет интеграцию векторного хранилища для базы данных Reindexer с фреймворком LangChain.
Установка
pip install langchain-reindexer
Использование
Теперь вы можете использовать векторное хранилище в вашем приложении LangChain:
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
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
Metadata
Release files for langchain-reindexer 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| langchain_reindexer-0.1.5.tar.gz | 17.8 kB | Without provenance | Details for langchain_reindexer-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_reindexer-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for langchain_reindexer-0.1.5-py3-none-any.whl |
Total release size: 31.9 kB
Release files / langchain_reindexer-0.1.5.tar.gz
| Download URL | langchain_reindexer-0.1.5.tar.gz |
|---|---|
| Size | 17.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
83d8a4ed4a8de6e80e7951368a57241b6bcec824c4a191ec10454dd86030da09
|
|
BLAKE2b-256 checksum How to use checksums |
f5050d9d4a99e59d8edf8e8517b5c2d311f12424f358b7259a6d5188806dd78c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / langchain_reindexer-0.1.5-py3-none-any.whl
| Download URL | langchain_reindexer-0.1.5-py3-none-any.whl |
|---|---|
| Size | 14.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3a194b6537737522c5d5f2f7ceec2be7aae9d15874ca8b1063b377d9ad29d38e
|
|
BLAKE2b-256 checksum How to use checksums |
1e1163ff8348b9919f90b98157680d285ae67c7d51bfe05b7d2a1eb6298cdd67
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Security for langchain-reindexer 0.1.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.