Add vector store integration of lindorm, including knn search, … (#14623

)

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/.gitignore

@@ -0,0 +1,153 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.ruff_cache
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/BUILD

@@ -0,0 +1,3 @@
+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/Makefile

@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help:	## Show all Makefile targets.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format:	## Run code autoformatters (black).
+	pre-commit install
+	git ls-files | xargs pre-commit run black --files
+
+lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
+	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test:	## Run tests via pytest.
+	pytest tests
+
+watch-docs:	## Build and watch documentation.
+	sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/README.md

@@ -0,0 +1,60 @@
+# LlamaIndex Vector_Stores Integration: Lindorm
+
+- LindormVectorStore support pure vector search, search with metadata filtering, hybrid search, async, etc.
+- Please refer to the [notebook](../../../docs/docs/examples/vector_stores/LindormDemo.ipynb) for usage of Lindorm as vector store in LlamaIndex.
+
+# Example Usage
+
+```sh
+pip install llama-index
+pip install opensearch-py
+pip install llama-index-vector-stores-lindorm
+```
+
+```python
+from llama_index.vector_stores.lindorm import (
+    LindormVectorStore,
+    LindormVectorClient,
+)
+
+# how to obtain an lindorm search instance:
+# https://alibabacloud.com/help/en/lindorm/latest/create-an-instance
+
+# how to access your lindorm search instance:
+# https://www.alibabacloud.com/help/en/lindorm/latest/view-endpoints
+
+# run curl commands to connect to and use LindormSearch:
+# https://www.alibabacloud.com/help/en/lindorm/latest/connect-and-use-the-search-engine-with-the-curl-command
+
+# lindorm instance info
+host = "ld-bp******jm*******-proxy-search-pub.lindorm.aliyuncs.com"
+port = 30070
+username = "your_username"
+password = "your_password"
+
+# index to demonstrate the VectorStore impl
+index_name = "lindorm_test_index"
+
+# extension param of lindorm search, number of cluster units to query; between 1 and method.parameters.nlist.
+nprobe = "a number(string type)"
+
+# extension param of lindorm search, usually used to improve recall accuracy, but it increases performance overhead;
+#   between 1 and 200; default: 10.
+reorder_factor = "a number(string type)"
+
+# LindormVectorClient encapsulates logic for a single index with vector search enabled
+client = LindormVectorClient(
+    host=host,
+    port=port,
+    username=username,
+    password=password,
+    index=index_name,
+    dimension=1536,  # match with your embedding model
+    nprobe=nprobe,
+    reorder_factor=reorder_factor,
+    # filter_type="pre_filter/post_filter(default)"
+)
+
+# initialize vector store
+vector_store = LindormVectorStore(client)
+```

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/llama_index/vector_stores/lindorm/BUILD

@@ -0,0 +1 @@
+python_sources()

llama-index-integrations/vector_stores/llama-index-vector-stores-lindorm/llama_index/vector_stores/lindorm/__init__.py

@@ -0,0 +1,6 @@
+from llama_index.vector_stores.lindorm.base import (
+    LindormVectorStore,
+    LindormVectorClient,
+)
+
+__all__ = ["LindormVectorStore", "LindormVectorClient"]