document store and index store for elasticsearch (#12218)

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/.gitignore

+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/storage/docstore/llama-index-storage-docstore-elasticsearch/BUILD

+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/Makefile

+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/storage/docstore/llama-index-storage-docstore-elasticsearch/README.md

+# LlamaIndex Docstore Integration: Elasticsearch

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/llama_index/storage/docstore/elasticsearch/BUILD

+python_sources()

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/llama_index/storage/docstore/elasticsearch/__init__.py

+from llama_index.storage.docstore.elasticsearch.base import ElasticsearchDocumentStore
+
+__all__ = ["ElasticsearchDocumentStore"]

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/llama_index/storage/docstore/elasticsearch/base.py

+from typing import Optional
+
+from llama_index.core.storage.docstore.keyval_docstore import KVDocumentStore
+from llama_index.core.storage.docstore.types import DEFAULT_BATCH_SIZE
+from llama_index.storage.kvstore.elasticsearch import ElasticsearchKVStore
+
+
+class ElasticsearchDocumentStore(KVDocumentStore):
+    """Elasticsearch Document (Node) store.
+
+    An Elasticsearch store for Document and Node objects.
+
+    Args:
+        elasticsearch_kvstore (ElasticsearchKVStore): Elasticsearch key-value store
+        namespace (str): namespace for the docstore
+
+    """
+
+    def __init__(
+        self,
+        elasticsearch_kvstore: ElasticsearchKVStore,
+        namespace: Optional[str] = None,
+        node_collection_index: str = None,
+        ref_doc_collection_index: str = None,
+        metadata_collection_index: str = None,
+        batch_size: int = DEFAULT_BATCH_SIZE,
+    ) -> None:
+        """Init a ElasticsearchDocumentStore."""
+        super().__init__(
+            elasticsearch_kvstore, namespace=namespace, batch_size=batch_size
+        )
+        if node_collection_index:
+            self._node_collection = node_collection_index
+        else:
+            self._node_collection = f"llama_index-docstore.data-{self._namespace}"
+
+        if ref_doc_collection_index:
+            self._ref_doc_collection = ref_doc_collection_index
+        else:
+            self._ref_doc_collection = (
+                f"llama_index-docstore.ref_doc_info-{self._namespace}"
+            )
+
+        if metadata_collection_index:
+            self._metadata_collection = metadata_collection_index
+        else:
+            self._metadata_collection = (
+                f"llama_index-docstore.metadata-{self._namespace}"
+            )

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/pyproject.toml

+[build-system]
+build-backend = "poetry.core.masonry.api"
+requires = ["poetry-core"]
+
+[tool.codespell]
+check-filenames = true
+check-hidden = true
+skip = "*.csv,*.html,*.json,*.jsonl,*.pdf,*.txt,*.ipynb"
+
+[tool.llamahub]
+contains_example = false
+import_path = "llama_index.storage.docstore.elasticsearch"
+
+[tool.llamahub.class_authors]
+ElasticsearchDocumentStore = "llama-index"
+
+[tool.mypy]
+disallow_untyped_defs = true
+exclude = ["_static", "build", "examples", "notebooks", "venv"]
+ignore_missing_imports = true
+python_version = "3.8"
+
+[tool.poetry]
+authors = ["Your Name <you@example.com>"]
+description = "llama-index docstore elasticsearch integration"
+exclude = ["**/BUILD"]
+license = "MIT"
+name = "llama-index-storage-docstore-elasticsearch"
+readme = "README.md"
+version = "0.1.2"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+llama-index-core = "^0.10.1"
+llama-index-storage-kvstore-elasticsearch = "^0.1.1"
+
+[tool.poetry.group.dev.dependencies]
+ipython = "8.10.0"
+jupyter = "^1.0.0"
+mypy = "0.991"
+pre-commit = "3.2.0"
+pylint = "2.15.10"
+pytest = "7.2.1"
+pytest-mock = "3.11.1"
+ruff = "0.0.292"
+tree-sitter-languages = "^1.8.0"
+types-Deprecated = ">=0.1.0"
+types-PyYAML = "^6.0.12.12"
+types-protobuf = "^4.24.0.4"
+types-redis = "4.5.5.0"
+types-requests = "2.28.11.8"
+types-setuptools = "67.1.0.0"
+
+[tool.poetry.group.dev.dependencies.black]
+extras = ["jupyter"]
+version = "<=23.9.1,>=23.7.0"
+
+[tool.poetry.group.dev.dependencies.codespell]
+extras = ["toml"]
+version = ">=v2.2.6"
+
+[[tool.poetry.packages]]
+include = "llama_index/"

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/tests/BUILD

+python_tests()

llama-index-integrations/storage/docstore/llama-index-storage-docstore-elasticsearch/tests/test_storage_docstore_elasticsearch.py

+from llama_index.core.storage.docstore.keyval_docstore import KVDocumentStore
+from llama_index.storage.docstore.elasticsearch import ElasticsearchDocumentStore
+
+
+def test_class():
+    names_of_base_classes = [b.__name__ for b in ElasticsearchDocumentStore.__mro__]
+    assert KVDocumentStore.__name__ in names_of_base_classes

llama-index-integrations/storage/index_store/llama-index-storage-index-store-elasticsearch/.gitignore

+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/storage/index_store/llama-index-storage-index-store-elasticsearch/BUILD

+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/storage/index_store/llama-index-storage-index-store-elasticsearch/Makefile

+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/storage/index_store/llama-index-storage-index-store-elasticsearch/README.md

+# LlamaIndex Index_Store Integration: Elasticsearch Index Store

llama-index-integrations/storage/index_store/llama-index-storage-index-store-elasticsearch/llama_index/storage/index_store/elasticsearch/BUILD

+python_sources()

llama-index-integrations/storage/index_store/llama-index-storage-index-store-elasticsearch/llama_index/storage/index_store/elasticsearch/__init__.py

+from llama_index.storage.index_store.elasticsearch.base import ElasticsearchIndexStore
+
+__all__ = ["ElasticsearchIndexStore"]

llama-index-integrations/storage/index_store/llama-index-storage-index-store-elasticsearch/llama_index/storage/index_store/elasticsearch/base.py

+from typing import Optional
+
+from llama_index.core.storage.index_store.keyval_index_store import KVIndexStore
+from llama_index.storage.kvstore.elasticsearch import ElasticsearchKVStore
+
+
+class ElasticsearchIndexStore(KVIndexStore):
+    """Elasticsearch Index store.
+
+    Args:
+        elasticsearch_kvstore (ElasticsearchKVStore): Elasticsearch key-value store
+        namespace (str): namespace for the index store
+
+    """
+
+    def __init__(
+        self,
+        elasticsearch_kvstore: ElasticsearchKVStore,
+        namespace: Optional[str] = None,
+    ) -> None:
+        """Init a ElasticsearchIndexStore."""
+        super().__init__(elasticsearch_kvstore, namespace=namespace)