raglineage 0.1.1__tar.gz

raglineage-0.1.1/CONTRIBUTING.md

@@ -0,0 +1,57 @@
+# Contributing to raglineage
+
+Thank you for your interest in contributing to raglineage! This document provides guidelines and instructions for contributing.
+
+## Development Setup
+
+1. Fork the repository
+2. Clone your fork:
+   ```bash
+   git clone https://github.com/YOUR_USERNAME/raglineage.git
+   cd raglineage
+   ```
+3. Install in development mode:
+   ```bash
+   pip install -e ".[dev]"
+   ```
+4. Run tests to ensure everything works:
+   ```bash
+   pytest
+   ```
+
+## Code Style
+
+- Use **type hints** everywhere (Python ≥ 3.10)
+- Follow **PEP 8** style guidelines
+- Use **ruff** for linting (configuration in `pyproject.toml`)
+- Use **pydantic** models for all data schemas
+- Write **docstrings** for all public functions and classes
+
+## Testing
+
+- Write tests for all new features
+- Aim for high test coverage
+- Tests should be in `tests/` directory
+- Run tests with: `pytest`
+
+## Pull Request Process
+
+1. Create a feature branch from `main`
+2. Make your changes
+3. Add tests for new functionality
+4. Ensure all tests pass: `pytest`
+5. Run linting: `ruff check .`
+6. Update documentation if needed
+7. Submit a pull request with a clear description
+
+## Commit Messages
+
+- Use clear, descriptive commit messages
+- Reference issue numbers if applicable
+- Follow conventional commit format when possible
+
+## Questions?
+
+Open an issue on GitHub for questions or discussions.
+
+Thank you for contributing!

raglineage-0.1.1/LICENSE

@@ -0,0 +1,17 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+Copyright 2026 Pranav Motarwar
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

raglineage-0.1.1/MANIFEST.in

@@ -0,0 +1,7 @@
+include README.md
+include LICENSE
+include CONTRIBUTING.md
+include pyproject.toml
+recursive-include examples *
+recursive-exclude * __pycache__
+recursive-exclude * *.py[co]

raglineage-0.1.1/PKG-INFO

@@ -0,0 +1,315 @@
+Metadata-Version: 2.4
+Name: raglineage
+Version: 0.1.1
+Summary: Lineage-aware RAG engine for auditable, reproducible, versioned retrieval and answers
+Author-email: Pranav Motarwar <pranav.motarwar@example.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/PranavMotarwar/raglineage
+Project-URL: Documentation, https://github.com/PranavMotarwar/raglineage
+Project-URL: Repository, https://github.com/PranavMotarwar/raglineage
+Project-URL: Issues, https://github.com/PranavMotarwar/raglineage/issues
+Keywords: rag,lineage,provenance,vector-search,nlp,llm
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: networkx>=3.0
+Requires-Dist: faiss-cpu>=1.7.4
+Requires-Dist: sentence-transformers>=2.2.0
+Requires-Dist: typer>=0.9.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: mypy>=1.5.0; extra == "dev"
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
+Dynamic: license-file
+
+# raglineage
+
+**Lineage-aware RAG engine for auditable, reproducible, versioned retrieval and answers**
+
+[![PyPI version](https://badge.fury.io/py/raglineage.svg)](https://badge.fury.io/py/raglineage)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
+[![PyPI downloads](https://img.shields.io/pypi/dm/raglineage.svg)](https://pypi.org/project/raglineage/)
+
+## The Unique Idea
+
+Most RAG tools store text chunks and embeddings. They lose provenance and cannot explain answer drift.
+
+**raglineage** treats RAG as a data lineage and provenance problem, not just vector search. Every retrievable unit is a **Lineage Node (LN)** with:
+
+- Immutable ID and dataset version
+- Precise source reference (file path, page, row, URL, etc.)
+- Full transform chain (ordered list of transforms applied)
+- Content hash for integrity
+- Timestamps for auditing
+
+The system maintains a **Lineage Graph (DAG)** linking nodes through structural and semantic relationships, enabling:
+
+- Dataset versioning and diffing
+- Incremental rebuilds (only recompute what changed)
+- Answer auditing (reconstruct provenance of any answer)
+- Version consistency checks
+- Staleness detection
+
+This is **not** a LangChain/LlamaIndex wrapper—it's a first-class lineage system.
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                      Data Sources                            │
+│  (PDFs, CSVs, JSON, APIs, Text Files)                       │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│                    Ingestion Layer                           │
+│  AutoIngestor → FileIngestor → TabularIngestor              │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│                   Transform Layer                            │
+│  Chunkers → Dedupe → Normalize                              │
+│  (Each transform recorded in transform_chain)               │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Lineage Node Creation                           │
+│  ln_id, source, transform_chain, content_hash, version      │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Lineage Graph (DAG)                             │
+│  networkx DAG: nodes=LN, edges=relationships                │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Embedding + Vector Store                        │
+│  Embeddings → FAISS Store → LN ID Mapping                   │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Retrieval + Audit                               │
+│  Query → Top-K → Graph Walk → Answer + Lineage             │
+│  Audit → Version Check → Staleness → Risk Flags             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Lineage Node Example
+
+Every retrievable chunk is a Lineage Node with complete provenance:
+
+```json
+{
+  "ln_id": "ln_92af",
+  "content": "Revenue declined due to supply constraints",
+  "source": {
+    "type": "pdf",
+    "uri": "data/10Q_Q3_2023.pdf",
+    "page": 14,
+    "section": "Management Discussion"
+  },
+  "dataset_version": "v3.1",
+  "transform_chain": [
+    "pdf_parse",
+    "section_split",
+    "semantic_chunk",
+    "deduplicate"
+  ],
+  "content_hash": "sha256:a3f5b8c9d2e1f4a6b7c8d9e0f1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0",
+  "created_at": "2026-01-20T00:00:00Z"
+}
+```
+
+## Audited Answer Example
+
+Every answer includes full lineage and audit metadata:
+
+```json
+{
+  "question": "Why did revenue fall in Q3?",
+  "answer": "Revenue declined primarily due to supply constraints affecting shipments.",
+  "lineage": [
+    {
+      "ln_id": "ln_92af",
+      "score": 0.91,
+      "source": {
+        "uri": "data/10Q_Q3_2023.pdf",
+        "page": 14
+      },
+      "dataset_version": "v3.1",
+      "transform_chain": ["pdf_parse","section_split","semantic_chunk","deduplicate"]
+    }
+  ],
+  "audit": {
+    "staleness_check": "pass",
+    "version_consistency": "single_version",
+    "transform_risk_flags": []
+  }
+}
+```
+
+## Quickstart
+
+### Installation
+
+```bash
+pip install raglineage
+```
+
+### Basic Usage
+
+```python
+from raglineage import RagLineage
+
+rag = RagLineage(
+    source="examples/data",
+    store_backend="faiss",
+    embed_backend="local"
+)
+
+# Build initial version
+rag.build(version="v1.0")
+
+# Query with lineage
+ans = rag.query("What is the refund policy?", k=5)
+print(ans.model_dump_json(indent=2))
+
+# Audit the answer
+report = rag.audit(ans)
+print(report.model_dump_json(indent=2))
+```
+
+### CLI Usage
+
+```bash
+# Initialize a project
+raglineage init ./my_project
+
+# Build from source
+raglineage build --source ./data --version v1.0
+
+# Update incrementally
+raglineage update --source ./data --version v1.1 --changed-only
+
+# Query
+raglineage query "What is the refund policy?" --k 5
+
+# Diff versions
+raglineage diff v1.0 v1.1
+```
+
+## Comparison with Other RAG Tools
+
+| Feature | raglineage | LangChain | LlamaIndex |
+|---------|-----------|-----------|------------|
+| **Lineage Tracking** | First-class | Not built-in | Not built-in |
+| **Dataset Versioning** | Native | Manual | Manual |
+| **Incremental Updates** | Automatic | Full rebuild | Full rebuild |
+| **Answer Auditing** | Built-in | Manual | Manual |
+| **Transform Chain Tracking** | Every LN | Not tracked | Not tracked |
+| **Version Diffing** | Structured | Not available | Not available |
+| **Graph Relationships** | DAG-based | Optional | Optional |
+| **Source Provenance** | Complete | Basic | Basic |
+
+**Key Difference**: raglineage treats lineage as a core requirement, not an afterthought. Every operation preserves and tracks provenance.
+
+## Core Concepts
+
+### Lineage Nodes (LN)
+
+A Lineage Node is the atomic unit of retrieval. Each LN has:
+- **ln_id**: Stable, deterministic identifier
+- **content**: The actual text content
+- **source**: Precise reference to origin (file, page, row, etc.)
+- **dataset_version**: Version tag for the dataset
+- **transform_chain**: Ordered list of transforms applied
+- **content_hash**: SHA-256 hash for integrity
+- **timestamps**: Created/updated timestamps
+
+### Lineage Graph
+
+A directed acyclic graph (DAG) where:
+- **Nodes**: Lineage Node IDs
+- **Edges**: Typed relationships (adjacent, semantic, references, same_entity, etc.)
+
+Enables graph-walk retrieval and relationship exploration.
+
+### Dataset Versioning
+
+Each dataset build produces a versioned manifest:
+- Tracks all source files and their hashes
+- Enables diffing between versions
+- Supports incremental updates (only recompute changed files)
+
+### Answer Auditing
+
+Every answer includes:
+- **Lineage**: List of LNs used with scores and metadata
+- **Audit Report**: 
+  - Version consistency check
+  - Staleness detection
+  - Transform risk flags
+
+## Requirements
+
+- Python ≥ 3.10
+- Strict type hints throughout
+- Pydantic models for schemas
+- NetworkX for graph operations
+- FAISS for vector storage
+- Sentence-transformers for local embeddings
+
+## Development
+
+```bash
+# Clone repository
+git clone https://github.com/PranavMotarwar/raglineage.git
+cd raglineage
+
+# Install in development mode
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Run linting
+ruff check .
+```
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+## License
+
+Apache-2.0 License. See [LICENSE](LICENSE) for details.
+
+## Author
+
+Pranav Motarwar - [GitHub](https://github.com/PranavMotarwar)
+
+---
+
+**raglineage** - Where every answer has a traceable origin.

raglineage-0.1.1/README.md

@@ -0,0 +1,275 @@
+# raglineage
+
+**Lineage-aware RAG engine for auditable, reproducible, versioned retrieval and answers**
+
+[![PyPI version](https://badge.fury.io/py/raglineage.svg)](https://badge.fury.io/py/raglineage)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
+[![PyPI downloads](https://img.shields.io/pypi/dm/raglineage.svg)](https://pypi.org/project/raglineage/)
+
+## The Unique Idea
+
+Most RAG tools store text chunks and embeddings. They lose provenance and cannot explain answer drift.
+
+**raglineage** treats RAG as a data lineage and provenance problem, not just vector search. Every retrievable unit is a **Lineage Node (LN)** with:
+
+- Immutable ID and dataset version
+- Precise source reference (file path, page, row, URL, etc.)
+- Full transform chain (ordered list of transforms applied)
+- Content hash for integrity
+- Timestamps for auditing
+
+The system maintains a **Lineage Graph (DAG)** linking nodes through structural and semantic relationships, enabling:
+
+- Dataset versioning and diffing
+- Incremental rebuilds (only recompute what changed)
+- Answer auditing (reconstruct provenance of any answer)
+- Version consistency checks
+- Staleness detection
+
+This is **not** a LangChain/LlamaIndex wrapper—it's a first-class lineage system.
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                      Data Sources                            │
+│  (PDFs, CSVs, JSON, APIs, Text Files)                       │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│                    Ingestion Layer                           │
+│  AutoIngestor → FileIngestor → TabularIngestor              │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│                   Transform Layer                            │
+│  Chunkers → Dedupe → Normalize                              │
+│  (Each transform recorded in transform_chain)               │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Lineage Node Creation                           │
+│  ln_id, source, transform_chain, content_hash, version      │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Lineage Graph (DAG)                             │
+│  networkx DAG: nodes=LN, edges=relationships                │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Embedding + Vector Store                        │
+│  Embeddings → FAISS Store → LN ID Mapping                   │
+└──────────────────────┬──────────────────────────────────────┘
+                       │
+                       ▼
+┌─────────────────────────────────────────────────────────────┐
+│              Retrieval + Audit                               │
+│  Query → Top-K → Graph Walk → Answer + Lineage             │
+│  Audit → Version Check → Staleness → Risk Flags             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Lineage Node Example
+
+Every retrievable chunk is a Lineage Node with complete provenance:
+
+```json
+{
+  "ln_id": "ln_92af",
+  "content": "Revenue declined due to supply constraints",
+  "source": {
+    "type": "pdf",
+    "uri": "data/10Q_Q3_2023.pdf",
+    "page": 14,
+    "section": "Management Discussion"
+  },
+  "dataset_version": "v3.1",
+  "transform_chain": [
+    "pdf_parse",
+    "section_split",
+    "semantic_chunk",
+    "deduplicate"
+  ],
+  "content_hash": "sha256:a3f5b8c9d2e1f4a6b7c8d9e0f1a2b3c4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0",
+  "created_at": "2026-01-20T00:00:00Z"
+}
+```
+
+## Audited Answer Example
+
+Every answer includes full lineage and audit metadata:
+
+```json
+{
+  "question": "Why did revenue fall in Q3?",
+  "answer": "Revenue declined primarily due to supply constraints affecting shipments.",
+  "lineage": [
+    {
+      "ln_id": "ln_92af",
+      "score": 0.91,
+      "source": {
+        "uri": "data/10Q_Q3_2023.pdf",
+        "page": 14
+      },
+      "dataset_version": "v3.1",
+      "transform_chain": ["pdf_parse","section_split","semantic_chunk","deduplicate"]
+    }
+  ],
+  "audit": {
+    "staleness_check": "pass",
+    "version_consistency": "single_version",
+    "transform_risk_flags": []
+  }
+}
+```
+
+## Quickstart
+
+### Installation
+
+```bash
+pip install raglineage
+```
+
+### Basic Usage
+
+```python
+from raglineage import RagLineage
+
+rag = RagLineage(
+    source="examples/data",
+    store_backend="faiss",
+    embed_backend="local"
+)
+
+# Build initial version
+rag.build(version="v1.0")
+
+# Query with lineage
+ans = rag.query("What is the refund policy?", k=5)
+print(ans.model_dump_json(indent=2))
+
+# Audit the answer
+report = rag.audit(ans)
+print(report.model_dump_json(indent=2))
+```
+
+### CLI Usage
+
+```bash
+# Initialize a project
+raglineage init ./my_project
+
+# Build from source
+raglineage build --source ./data --version v1.0
+
+# Update incrementally
+raglineage update --source ./data --version v1.1 --changed-only
+
+# Query
+raglineage query "What is the refund policy?" --k 5
+
+# Diff versions
+raglineage diff v1.0 v1.1
+```
+
+## Comparison with Other RAG Tools
+
+| Feature | raglineage | LangChain | LlamaIndex |
+|---------|-----------|-----------|------------|
+| **Lineage Tracking** | First-class | Not built-in | Not built-in |
+| **Dataset Versioning** | Native | Manual | Manual |
+| **Incremental Updates** | Automatic | Full rebuild | Full rebuild |
+| **Answer Auditing** | Built-in | Manual | Manual |
+| **Transform Chain Tracking** | Every LN | Not tracked | Not tracked |
+| **Version Diffing** | Structured | Not available | Not available |
+| **Graph Relationships** | DAG-based | Optional | Optional |
+| **Source Provenance** | Complete | Basic | Basic |
+
+**Key Difference**: raglineage treats lineage as a core requirement, not an afterthought. Every operation preserves and tracks provenance.
+
+## Core Concepts
+
+### Lineage Nodes (LN)
+
+A Lineage Node is the atomic unit of retrieval. Each LN has:
+- **ln_id**: Stable, deterministic identifier
+- **content**: The actual text content
+- **source**: Precise reference to origin (file, page, row, etc.)
+- **dataset_version**: Version tag for the dataset
+- **transform_chain**: Ordered list of transforms applied
+- **content_hash**: SHA-256 hash for integrity
+- **timestamps**: Created/updated timestamps
+
+### Lineage Graph
+
+A directed acyclic graph (DAG) where:
+- **Nodes**: Lineage Node IDs
+- **Edges**: Typed relationships (adjacent, semantic, references, same_entity, etc.)
+
+Enables graph-walk retrieval and relationship exploration.
+
+### Dataset Versioning
+
+Each dataset build produces a versioned manifest:
+- Tracks all source files and their hashes
+- Enables diffing between versions
+- Supports incremental updates (only recompute changed files)
+
+### Answer Auditing
+
+Every answer includes:
+- **Lineage**: List of LNs used with scores and metadata
+- **Audit Report**: 
+  - Version consistency check
+  - Staleness detection
+  - Transform risk flags
+
+## Requirements
+
+- Python ≥ 3.10
+- Strict type hints throughout
+- Pydantic models for schemas
+- NetworkX for graph operations
+- FAISS for vector storage
+- Sentence-transformers for local embeddings
+
+## Development
+
+```bash
+# Clone repository
+git clone https://github.com/PranavMotarwar/raglineage.git
+cd raglineage
+
+# Install in development mode
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Run linting
+ruff check .
+```
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+## License
+
+Apache-2.0 License. See [LICENSE](LICENSE) for details.
+
+## Author
+
+Pranav Motarwar - [GitHub](https://github.com/PranavMotarwar)
+
+---
+
+**raglineage** - Where every answer has a traceable origin.

raglineage-0.1.1/examples/data/products.csv

@@ -0,0 +1,6 @@
+product_id,name,price,category
+1,Widget A,29.99,Electronics
+2,Widget B,49.99,Electronics
+3,Gadget X,19.99,Accessories
+4,Gadget Y,39.99,Accessories
+5,Tool Z,59.99,Tools

raglineage-0.1.1/examples/data/sample.txt

@@ -0,0 +1,15 @@
+Refund Policy
+
+Our refund policy is straightforward. Customers can request a refund within 30 days of purchase. 
+Refunds are processed within 5-7 business days. To request a refund, please contact our support team 
+with your order number and reason for the refund.
+
+Shipping Policy
+
+We offer free shipping on orders over $50. Standard shipping takes 5-7 business days. 
+Express shipping is available for an additional fee and takes 2-3 business days.
+
+Privacy Policy
+
+We respect your privacy. We do not sell your personal information to third parties. 
+Your data is encrypted and stored securely. You can request deletion of your data at any time.