Pebblo-Llama PebbloSafeReader (#13128)

llama-index-integrations/readers/llama-index-readers-pebblo/.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/readers/llama-index-readers-pebblo/BUILD

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

llama-index-integrations/readers/llama-index-readers-pebblo/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/readers/llama-index-readers-pebblo/README.md

@@ -0,0 +1,49 @@
+# LlamaIndex Readers Integration: Pebblo
+
+## Pebblo Safe DocumentReader
+
+[Pebblo](https://github.com/daxa-ai/pebblo) enables developers to safely load data and promote their Gen AI app to deployment without worrying about the organization’s compliance and security requirements. The project identifies semantic topics and entities found in the loaded data and summarizes them on the UI or a PDF report.
+
+### Pebblo has two components.
+
+1. Pebblo Safe DocumentReader for Llama
+2. Pebblo Daemon
+
+This document describes how to augment your existing Llama DocumentReader with Pebblo Safe DocumentReader to get deep data visibility on the types of Topics and Entities ingested into the Gen-AI Llama application. For details on `Pebblo Daemon` see this [pebblo daemon](https://daxa-ai.github.io/pebblo-docs/daemon.html) document.
+
+Pebblo Safe DocumentReader enables safe data ingestion for Llama `DocumentReader`. This is done by wrapping the document reader call with `Pebblo Safe DocumentReader`
+
+#### How to Pebblo enable Document Reading?
+
+Assume a Llama RAG application snippet using `CSVReader` to read a CSV document for inference.
+
+Here is the snippet of Document loading using `CSVReader`
+
+```
+from pathlib import Path
+from llama_index.readers.file import CSVReader
+reader = CSVReader()
+documents = reader.load_data(file=Path('data/corp_sens_data.csv'))
+print(documents)
+```
+
+The Pebblo SafeReader can be installed and enabled with few lines of code change to the above snippet.
+
+##### Install PebbloSafeReader
+
+```
+pip install llama-index-readers-pebblo
+```
+
+##### Use PebbloSafeReader
+
+```
+from pathlib import Path
+from llama_index.readers.pebblo import PebbloSafeReader
+from llama_index.readers.file import CSVReader
+reader = CSVReader()
+pebblo_reader = PebbloSafeReader(reader, name="acme-corp-rag-1", # App name (Mandatory)
+owner="Joe Smith", # Owner (Optional)
+description="Support productivity RAG application")
+documents = pebblo_reader.load_data(file=Path('data/corp_sens_data.csv'))
+```

llama-index-integrations/readers/llama-index-readers-pebblo/llama_index/readers/pebblo/BUILD

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

llama-index-integrations/readers/llama-index-readers-pebblo/llama_index/readers/pebblo/__init__.py

@@ -0,0 +1,5 @@
+from llama_index.readers.pebblo.base import (
+    PebbloSafeReader,
+)
+
+__all__ = ["PebbloSafeReader"]