feat: extend postgres vector store with paradedb BM25 support

llama-index-integrations/vector_stores/llama-index-vector-store-paradedb/.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-store-paradedb/LICENSE

@@ -0,0 +1,21 @@
+The MIT License
+
+Copyright (c) Jerry Liu
+
+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/vector_stores/llama-index-vector-store-paradedb/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-store-paradedb/README.md

@@ -0,0 +1,90 @@
+# LlamaIndex Vector Stores Integration: ParadeDB
+
+This module adds full ParadeDB integration enabling hybrid search with BM25 and vector similarity (HNSW) in PostgreSQL.
+
+---
+
+## Quick Setup
+
+---
+
+### 1. **Setup example**
+
+Run ParadeDB locally:
+
+```bash
+docker run --name paradedb \
+  -e POSTGRES_USER=postgres \
+  -e POSTGRES_PASSWORD=mark90 \ 
+  -e POSTGRES_DB=postgres \
+  -p 5432:5432 \
+  -d paradedb/paradedb:latest
+```
+
+---
+
+### 2. **Usage example**
+
+```python
+import os
+from dotenv import load_dotenv
+from sqlalchemy import make_url
+from llama_index.vector_stores.paradedb import ParadeDBVectorStore
+
+def get_vector_store(table_name: str = "pgvector") -> ParadeDBVectorStore:
+    """
+    Creates and returns a new ParadeDBVectorStore instance using environment variables.
+    """
+    load_dotenv()
+
+    host = os.getenv("DB_HOST")
+    port = os.getenv("DB_PORT")
+    user = os.getenv("DB_USER")
+    password = os.getenv("DB_PASSWORD")
+    database = os.getenv("DB_DATABASE")
+
+    connection_string = f"postgresql://{user}:{password}@{host}:{port}"
+    url = make_url(connection_string)
+
+    return ParadeDBVectorStore.from_params(
+        database=database,
+        host=url.host,
+        password=url.password,
+        port=url.port,
+        user=url.username,
+        table_name=table_name,
+        text_search_config="english",
+        hybrid_search=True,  # needed to use bm25
+        use_bm25=True,
+        embed_dim=int(os.getenv("EMBEDDING_DIM")),
+        hnsw_kwargs={
+            "hnsw_m": 16,
+            "hnsw_ef_construction": 64,
+            "hnsw_ef_search": 40,
+            "hnsw_dist_method": "vector_cosine_ops",
+        },
+    )
+```
+
+---
+
+### Notes
+
+* Set `hybrid_search=True` and `use_bm25=True` to enable **hybrid BM25 + vector** retrieval.
+* You **must** use the `paradedb/paradedb:latest` image — not `pgvector/pgvector`.
+* The default schema name is `paradedb` to enable BM25.
+* Fully compatible with **llama-index-core** and other vector store interfaces.
+
+---
+
+### Disclaimer
+
+This integration was based on the Postgres Vector Store implementation:
+
+**version = "0.5.5"**
+
+
+However, **`customize_query_fn`** and other Postgres-specific query customization features are **not supported** in this ParadeDB version, as the focus here is on BM25 and hybrid retrieval.
+
+Feel free to contribute and extend this module further.
+

llama-index-integrations/vector_stores/llama-index-vector-store-paradedb/llama_index/vector_stores/paradedb/__init__.py

@@ -0,0 +1,3 @@
+from llama_index.vector_stores.paradedb.base import ParadeDBVectorStore
+
+__all__ = ["ParadeDBVectorStore"]