Add llama-index-retriever integration for HPE AlletraMP X10000 (#19798)

Author: madhur-singh-hpe

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/.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/retrievers/llama-index-retrievers-alletra-x10000/LICENSE

@@ -0,0 +1,19 @@
+(C) Copyright [2025] Hewlett Packard Enterprise Development LP
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the "Software"),
+to deal in the Software without restriction, including without limitation
+the rights to use, copy, modify, merge, publish, distribute, sublicense,
+and/or sell copies of the Software, and to permit persons to whom the
+Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/Makefile

@@ -0,0 +1,19 @@
+# Copyright Hewlett Packard Enterprise Development LP.
+
+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/retrievers/llama-index-retrievers-alletra-x10000/README.md

@@ -0,0 +1,43 @@
+# LlamaIndex Retrievers Integration: AlletraX10000Retriever
+
+This llama-index retriever will provide interfaces for the user applications to do semantic similarity search on the embeddings for Data Intelligence solution of HPE AlletraMP X10000
+
+## How to use SDK
+
+### Install llama-index-retrievers-alletra-x10000-retriever
+
+```sh
+pip install llama-index-retrievers-alletra-x10000-retriever
+```
+
+### Driver code
+
+```python
+from llama_index.core.chat_engine import CondensePlusContextChatEngine
+from llama_index.core.memory import ChatMemoryBuffer
+from llama_index.retrievers.alletra_x10000_retriever import (
+    AlletraX10000Retriever,
+)
+
+
+# Configure the llm settings before using the retriever
+
+retriever = AlletraX10000Retriever(
+    uri="https://example.com",
+    s3_access_key="",
+    s3_secret_key="",
+    collection_name="testcollection",
+    top_k=50,
+    search_config={"radius": 0.75},
+)
+
+memory = ChatMemoryBuffer.from_defaults(token_limit=1000)
+chatbot = CondensePlusContextChatEngine.from_defaults(
+    retriever=retriever, memory=memory
+)
+
+res = chatbot.chat(
+    "Who was the eldest daughter of the steward of the old Lord de Versely?"
+)
+print(res)
+```

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/llama_index/retrievers/alletra_x10000_retriever/__init__.py

@@ -0,0 +1,5 @@
+# Copyright Hewlett Packard Enterprise Development LP.
+
+from llama_index.retrievers.alletra_x10000_retriever.base import AlletraX10000Retriever
+
+__all__ = ["AlletraX10000Retriever"]

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/llama_index/retrievers/alletra_x10000_retriever/base.py

@@ -0,0 +1,50 @@
+# Copyright Hewlett Packard Enterprise Development LP.
+
+from pydi_client import DIClient
+from typing import Any, Dict, Union
+
+from llama_index.core.retrievers import BaseRetriever
+from llama_index.core.schema import QueryBundle, NodeWithScore, TextNode
+
+
+class AlletraX10000Retriever(BaseRetriever):
+    def __init__(
+        self,
+        uri: str,
+        s3_access_key: str,
+        s3_secret_key: str,
+        collection_name: str,
+        search_config: Union[Any, Dict[str, Any]] = None,
+        top_k: int = 5,
+    ):
+        self.uri = uri
+        self.top_k = top_k
+        self.collection_name = collection_name
+        self.access_key = s3_access_key
+        self.secret_key = s3_secret_key
+        self.search_config = search_config
+
+    def _retrieve(self, query_bundle: QueryBundle) -> list[NodeWithScore]:
+        query = query_bundle.query_str
+
+        client = DIClient(uri=self.uri)
+        data = client.similarity_search(
+            collection_name=self.collection_name,
+            query=query,
+            top_k=self.top_k,
+            access_key=self.access_key,
+            secret_key=self.secret_key,
+            search_parameters=self.search_config,
+        )
+
+        nodes = []
+        for item in data:
+            nodes.append(
+                NodeWithScore(
+                    node=TextNode(
+                        text=item["dataChunk"], metadata=item["chunkMetadata"]
+                    ),
+                    score=item["score"],
+                )
+            )
+        return nodes

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/pyproject.toml

@@ -0,0 +1,47 @@
+[build-system]
+build-backend = "hatchling.build"
+requires = ["hatchling"]
+
+[dependency-groups]
+dev = [
+    "pytest==7.2.1",
+    "pytest-mock==3.11.1",
+    "pre-commit==3.2.0",
+    "pytest-cov>=6.1.1",
+]
+
+[project]
+name = "llama-index-retrievers-alletra-x10000-retriever"
+version = "0.1.0"
+description = "llama-index retriever for AlletraMP X10000"
+readme = "README.md"
+requires-python = ">=3.11.2,<4.0"
+authors = [{name = "HPE"}]
+dependencies = [
+    "pydi-client>=1.0.0",
+    "llama-index-core>=0.12.35",
+]
+
+[tool.codespell]
+check-filenames = true
+check-hidden = true
+skip = "*.csv,*.html,*.json,*.jsonl,*.pdf,*.txt,*.ipynb"
+
+[tool.hatch.build.targets.sdist]
+include = ["llama_index/"]
+
+[tool.hatch.build.targets.wheel]
+include = ["llama_index/"]
+
+[tool.llamahub]
+contains_example = false
+import_path = "llama_index.retrievers.alletra_x10000_retriever"
+
+[tool.llamahub.class_authors]
+AlletraX10000Retriever = "HPE"
+
+[tool.mypy]
+disallow_untyped_defs = true
+exclude = ["_static", "build", "examples", "notebooks", "venv"]
+ignore_missing_imports = true
+python_version = "3.11.2"

llama-index-integrations/retrievers/llama-index-retrievers-alletra-x10000/tests/__init__.py

@@ -0,0 +1 @@
+# Copyright Hewlett Packard Enterprise Development LP.