post-graph-rag 0.1.0__tar.gz

post_graph_rag-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,65 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v[0-9]+.[0-9]+.[0-9]+*"
+      - "v*"
+
+jobs:
+  publish:
+    name: Build & Publish post-graph-rag to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write # Required for PyPI Trusted Publisher OIDC
+      contents: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Update module and package version from git tag
+        run: |
+          # Extract version (e.g. v1.2.3 -> 1.2.3)
+          TAG_NAME="${GITHUB_REF#refs/tags/}"
+          export VERSION="${TAG_NAME#v}"
+          echo "Release version: $VERSION"
+
+          # Update version in pyproject.toml and post_graph_rag/__init__.py
+          python -c "
+          import os, re
+          ver = os.environ['VERSION']
+
+          with open('pyproject.toml', 'r') as f:
+              content = f.read()
+          updated = re.sub(r'version\s*=\s*\"[^\"]+\"', 'version = \"' + ver + '\"', content, count=1)
+          with open('pyproject.toml', 'w') as f:
+              f.write(updated)
+
+          with open('post_graph_rag/__init__.py', 'r') as f:
+              content = f.read()
+          updated = re.sub(r'__version__\s*=\s*\"[^\"]+\"', '__version__ = \"' + ver + '\"', content, count=1)
+          with open('post_graph_rag/__init__.py', 'w') as f:
+              f.write(updated)
+          "
+
+          echo "Updated pyproject.toml and post_graph_rag/__init__.py to version ${VERSION}"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v3
+        with:
+          enable-cache: false
+
+      - name: Build package artifacts
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}
+          skip-existing: true

post_graph_rag-0.1.0/.gitignore

@@ -0,0 +1,222 @@
+# Secrets and keys
+**/*secret*
+**/*key*
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

post_graph_rag-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Chandan Rajah
+
+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.

post_graph_rag-0.1.0/PKG-INFO

@@ -0,0 +1,245 @@
+Metadata-Version: 2.4
+Name: post-graph-rag
+Version: 0.1.0
+Summary: Graph RAG library leveraging post-graph and pgvector on PostgreSQL with OpenAI-compatible LLMs.
+Project-URL: Homepage, https://github.com/crajah/post-graph-rag
+Project-URL: Repository, https://github.com/crajah/post-graph-rag
+Author-email: Chandan Rajah <chandan.rajah@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: graph-rag,knowledge-graph,llm,openai,pgvector,post-graph,rag
+Requires-Python: >=3.9
+Requires-Dist: openai>=1.0.0
+Requires-Dist: post-graph>=0.1.4
+Requires-Dist: pydantic>=2.0.0
+Description-Content-Type: text/markdown
+
+# post-graph-rag
+
+[![PyPI version](https://img.shields.io/pypi/v/post-graph-rag.svg)](https://pypi.org/project/post-graph-rag/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
+
+**Production-Grade, High-Performance Knowledge Graph RAG Engine Native to PostgreSQL.**
+
+`post-graph-rag` seamlessly combines **automated LLM-based entity & triple extraction**, **vector similarity search via `pgvector`**, and **graph relationship traversal** directly on PostgreSQL using the [`post-graph`](https://pypi.org/project/post-graph/) graph database library.
+
+It connects to **any OpenAI-compatible API** (LiteLLM, vLLM, Ollama, DeepSeek, OpenAI) for zero-shot domain-agnostic knowledge extraction, structured document metadata tracking, and context-aware answer synthesis.
+
+---
+
+## 🌟 Why `post-graph-rag`?
+
+Traditional Vector RAG systems suffer from **"chunk isolation"**—they retrieve isolated text passages based purely on semantic similarity, missing higher-level relationships and cross-document entity connections. 
+
+`post-graph-rag` solves this by building a **dual representation** inside PostgreSQL:
+1. **Unstructured Vector Passages**: Full document chunks indexed with `pgvector` HNSW embeddings.
+2. **Knowledge Graph Triples**: Extracted Subject-Predicate-Object entities connected by graph edges.
+3. **Structured Document Metadata**: Rich metadata tracking (`source`, `category`, `collection`, `document`, `page`, `paragraph`).
+
+---
+
+## 🏗️ Architecture Workflow
+
+```mermaid
+graph TD
+    subgraph INDEXING ["1. Knowledge Graph & Vector Indexing"]
+        A[Document Text + Metadata] --> B[Embedding Service]
+        A --> C[LLM GraphExtractor]
+        
+        B -->|Vectors| D[post-graph Store]
+        C -->|Entities & Triples| D
+        
+        D --> E[(PostgreSQL + pgvector)]
+        E -->|Tables| E1[documents]
+        E -->|Tables| E2[entities]
+        E -->|Edges| E3[relations]
+        E -->|Edges| E4[doc_mentions]
+    end
+
+    subgraph RETRIEVAL ["2. Hybrid Retrieval & Synthesis"]
+        Q[User Question] --> R[GraphRAG Query Engine]
+        R -->|Embedding| S[pgvector Similarity Search]
+        E1 & E2 -->|Top-K Passages & Entities| S
+        S --> T[1-Hop Graph Relationship Traversal]
+        E3 -->|Subject-Predicate-Object| T
+        
+        S & T --> U[LLM Answer Synthesis]
+        U --> V[Final Answer + Citations + Graph Triples]
+    end
+```
+
+---
+
+## 📦 Installation
+
+Install `post-graph-rag` via `pip` or `uv`:
+
+```bash
+pip install post-graph-rag
+```
+
+Or using `uv`:
+
+```bash
+uv add post-graph-rag
+```
+
+### PostgreSQL Requirements
+Ensure PostgreSQL is running with the `pgvector` extension installed:
+
+```sql
+CREATE EXTENSION IF NOT EXISTS vector;
+```
+
+---
+
+## 🚀 Quick Start
+
+### 1. Basic Indexing & Querying
+
+```python
+import asyncio
+from post_graph_rag import GraphRAG, RAGConfig, DocumentMetadata
+
+async def main():
+    # 1. Configure GraphRAG engine
+    config = RAGConfig(
+        api_base="http://localhost:4000/v1",       # OpenAI-compatible router endpoint
+        api_key="BEVZ-6L81-OZ8Y",                 # Master or OpenAI API Key
+        model="DeepSeek-V3.2",                    # LLM model for extraction & synthesis
+        embedding_model="text-embedding-3-small", # Embedding model
+        embedding_dim=1536,                       # Vector dimensionality
+        db_uri="postgresql://user:password@localhost:5432/postgres",
+        realm="enterprise_kb"
+    )
+
+    rag = GraphRAG(config)
+    
+    # 2. Connect & initialize PostgreSQL graph schema
+    await rag.initialize()
+
+    # 3. Index unstructured documents
+    doc_text = (
+        "Zeus is the king of the Olympian gods, ruling sky and thunder from Mount Olympus. "
+        "He is the son of Cronus and Rhea, and married to Hera. "
+        "Zeus defeated the Titans in the Titanomachy to establish his rule."
+    )
+    
+    result = await rag.index_document(doc_text, metadata={"source": "greek_mythology.txt"})
+    print(f"Indexed document {result['document_id']}: Extracted {result['entities_extracted']} entities.")
+
+    # 4. Perform Hybrid RAG Query
+    response = await rag.query("Who are the parents of Zeus and what did he defeat?")
+    
+    print("\n=== SYNTHESIZED ANSWER ===")
+    print(response["answer"])
+
+    print("\n=== RETRIEVED GRAPH TRIPLES ===")
+    for triple in response["retrieved_graph_triples"]:
+        print(f"  - {triple}")
+
+    # 5. Clean up
+    await rag.close()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+---
+
+## 📋 Document Metadata (`DocumentMetadata`)
+
+`post-graph-rag` includes structured document metadata tracking via the `DocumentMetadata` model:
+
+```python
+from post_graph_rag import DocumentMetadata
+
+metadata = DocumentMetadata(
+    source="https://mythology.org/zeus.html",  # Document origin (URL, filepath, API)
+    category="greek_mythology",               # Document category/topic
+    collection="olympian_deities",             # Collection namespace
+    document="zeus_overview.pdf",              # Title or filename
+    page=1,                                    # 1-based page number
+    paragraph=2,                               # 1-based paragraph index
+    extra={"author": "Homer", "year": -700}    # Custom metadata key-value pairs
+)
+
+await rag.index_document(chunk_text, metadata=metadata)
+```
+
+### Design Rationale: Optional vs. Required
+- **All metadata fields are optional** with default `None`. This allows seamless indexing of raw strings, short code snippets, webhooks, or unformatted text, while offering rich structural provenance tracking when indexing multi-page PDFs or categorized enterprise documents.
+
+---
+
+## ⚙️ Configuration Reference (`RAGConfig`)
+
+`RAGConfig` can be configured explicitly or automatically loaded from environment variables:
+
+| Option | Environment Variable | Default Value | Description |
+| :--- | :--- | :--- | :--- |
+| `api_base` | `OPENAI_API_BASE` | `http://localhost:4000/v1` | Base URL for OpenAI-compatible LLM endpoint |
+| `api_key` | `OPENAI_API_KEY` | `BEVZ-6L81-OZ8Y` | API Key for authorization |
+| `model` | `RAG_MODEL` | `DeepSeek-V3.2` | Primary LLM model for triple extraction & synthesis |
+| `embedding_model` | `RAG_EMBEDDING_MODEL` | `text-embedding-3-small` | Model for vector embedding generation |
+| `embedding_dim` | `RAG_EMBEDDING_DIM` | `1536` | Dimensionality of embedding vectors |
+| `db_uri` | `POSTGRES_URI` | `postgresql://crajah@localhost:5432/postgres` | PostgreSQL connection DSN |
+| `realm` | `RAG_REALM` | `default` | Multi-tenant graph namespace |
+
+---
+
+## 📖 API Reference
+
+### `GraphRAG`
+The main orchestrator class for indexing and querying.
+
+- `await initialize()`: Connects to PostgreSQL and creates necessary graph tables (`documents`, `entities`, `relations`, `doc_mentions`).
+- `await index_document(text: str, metadata: Optional[Union[Dict[str, Any], DocumentMetadata]] = None) -> Dict[str, Any]`: Computes document embeddings, extracts entity/triple structures via LLM, and persists graph nodes/edges into PostgreSQL.
+- `await query(question: str, top_k: int = 5) -> Dict[str, Any]`: Executes hybrid vector similarity search over documents and entities, traverses 1-hop graph relationship edges, and synthesizes a comprehensive answer. Returns dictionary with `question`, `answer`, `retrieved_documents`, `retrieved_entities`, and `retrieved_graph_triples`.
+- `await close()`: Closes database connection pools.
+
+### `DocumentMetadata`
+Data container for structured document metadata.
+
+- `source: Optional[str]`: Document URL, path, or origin.
+- `category: Optional[str]`: Document category or domain.
+- `collection: Optional[str]`: Document collection or folder.
+- `document: Optional[str]`: File title or filename.
+- `page: Optional[int]`: 1-based page number.
+- `paragraph: Optional[int]`: 1-based paragraph index.
+- `extra: Dict[str, Any]`: Custom user metadata.
+- `to_dict() -> Dict[str, Any]`: Serializes non-None fields to dictionary representation.
+- `from_dict(data: Dict[str, Any]) -> DocumentMetadata`: Deserializes dictionary data.
+
+### `RAGGraphStore`
+Database layer wrapping `post-graph`.
+
+- `add_document(text, embedding, metadata)`: Inserts a document vertex into the `documents` table.
+- `upsert_entity(name, entity_type, description, embedding)`: Upserts an entity vertex into the `entities` table.
+- `add_relation(from_entity, to_entity, relation_type, description)`: Connects entity vertices with a directed relation edge.
+- `search_similar_entities(query_vec, top_k)`: Executes `pgvector` HNSW similarity search over `entities`.
+- `search_similar_documents(query_vec, top_k)`: Executes `pgvector` HNSW similarity search over `documents`.
+
+---
+
+## 🗄️ PostgreSQL Database Schema
+
+`post-graph-rag` automatically provisions and manages the following graph schema in PostgreSQL powered by `post-graph`:
+
+| Table Name | Type | Key Columns | Description |
+| :--- | :--- | :--- | :--- |
+| `{realm}_documents` | Vertex Table | `id`, `payload`, `embedding` (`vector`) | Stores raw text chunks and `DocumentMetadata` payloads |
+| `{realm}_entities` | Vertex Table | `id`, `payload`, `embedding` (`vector`) | Canonical entity nodes (`name`, `type`, `description`) |
+| `{realm}_relations` | Edge Table | `from_id`, `to_id`, `relation_type`, `payload` | Directed edges representing entity-to-entity triples |
+| `{realm}_doc_mentions` | Edge Table | `from_id`, `to_id`, `relation_type` | Directed edges connecting document chunks to mentioned entities |
+| `{table}_audit` | Audit Table | `audit_id`, `action`, `changed_by`, `changed_at` | Automatic shadow audit logging for all graph mutations |
+| `{table}_data` | History Table | `data_id`, `payload`, `timestamp`, `embedding` | Append-only historical records for vertices and edges |
+
+---
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+Developed by **Chandan Rajah** (<chandan.rajah@gmail.com>).