glassbox-rag 0.1.0__tar.gz

glassbox_rag-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Averoe
+
+   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.

glassbox_rag-0.1.0/PKG-INFO

@@ -0,0 +1,195 @@
+Metadata-Version: 2.4
+Name: glassbox-rag
+Version: 0.1.0
+Summary: An open-source, high-transparency modular RAG framework for AI/ML applications
+Author: averoe
+License-Expression: Apache-2.0
+Keywords: rag,retrieval,generation,onnx,ollama,vector-store,multimodal
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastapi>=0.104.0
+Requires-Dist: uvicorn[standard]>=0.24.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pydantic-settings>=2.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: python-multipart>=0.0.6
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: flake8>=6.0.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Provides-Extra: embeddings
+Requires-Dist: onnxruntime>=1.16.0; extra == "embeddings"
+Requires-Dist: ollama>=0.0.50; extra == "embeddings"
+Requires-Dist: openai>=1.3.0; extra == "embeddings"
+Provides-Extra: vector-stores
+Requires-Dist: qdrant-client>=2.4.0; extra == "vector-stores"
+Requires-Dist: chromadb>=0.4.0; extra == "vector-stores"
+Requires-Dist: psycopg2-binary>=2.9.0; extra == "vector-stores"
+Provides-Extra: multimodal
+Requires-Dist: pillow>=10.0.0; extra == "multimodal"
+Requires-Dist: pypdf>=3.17.0; extra == "multimodal"
+Requires-Dist: python-pptx>=0.6.21; extra == "multimodal"
+Dynamic: license-file
+
+# GlassBox
+
+An open-source, high-transparency modular RAG (Retrieval-Augmented Generation) framework for AI/ML applications.
+
+## Features
+
+- Modular architecture with pluggable components
+- Support for multiple vector stores (Qdrant, Chroma)
+- Multiple embedding providers (OpenAI, Ollama, ONNX)
+- Database support (PostgreSQL, SQLite)
+- Comprehensive tracing and monitoring
+- FastAPI-based REST API
+- Web dashboard for trace visualization
+- Async/await support with asyncio
+- Pydantic v2 for robust configuration management
+
+## Installation
+
+Install from PyPI:
+
+```bash
+pip install glassbox-rag
+```
+
+## Quick Start
+
+```python
+from glassbox_rag.core.engine import GlassBoxEngine
+from glassbox_rag.config import GlassBoxConfig
+
+# Initialize the engine
+config = GlassBoxConfig()
+engine = GlassBoxEngine(config)
+
+# Ingest documents
+documents = [
+    {"content": "Document 1", "metadata": {"source": "source1"}},
+    {"content": "Document 2", "metadata": {"source": "source2"}},
+]
+engine.ingest(documents)
+
+# Retrieve relevant documents
+results = engine.retrieve("query text", top_k=5)
+```
+
+## Configuration
+
+Configure via YAML file (config/default.yaml):
+
+```yaml
+server:
+  host: "0.0.0.0"
+  port: 8000
+
+vector_store:
+  type: "qdrant"
+  config:
+    url: "http://localhost:6333"
+
+encoder:
+  type: "openai"
+  config:
+    api_key: "${OPENAI_API_KEY}"
+    model: "text-embedding-3-small"
+
+database:
+  type: "postgresql"
+  config:
+    url: "postgresql://user:password@localhost/glassbox"
+```
+
+## API Endpoints
+
+- GET /health - Health check
+- POST /retrieve - Retrieve documents
+- POST /ingest - Ingest new documents
+- POST /update - Update existing documents
+- GET /traces/{id} - Get execution trace
+- GET /traces/{id}/visualize - Visualize trace
+
+## Running the Server
+
+Start the FastAPI server with Uvicorn:
+
+```bash
+python -m glassbox_rag
+```
+
+The server will be available at http://localhost:8000
+
+## Web Dashboard
+
+Access the web dashboard at http://localhost:8000/ to:
+
+- View recent execution traces
+- Visualize trace hierarchy and timing
+- Monitor system metrics
+- Track token usage and costs
+
+## Testing
+
+Run the test suite:
+
+```bash
+pytest tests/ -v
+```
+
+## Plugin Architecture
+
+Extend GlassBox with custom plugins:
+
+1. Create a plugin class inheriting from the appropriate base class
+2. Implement required abstract methods
+3. Register in the configuration
+
+Example custom embedder:
+
+```python
+from glassbox_rag.plugins.base import EmbedderBase
+
+class CustomEmbedder(EmbedderBase):
+    def encode(self, texts):
+        # Your embedding implementation
+        return embeddings
+```
+
+## Architecture
+
+GlassBox consists of several core components:
+
+- Engine: Orchestrates all operations
+- Encoder: Handles document and query encoding
+- Retriever: Implements retrieval strategies
+- Writeback: Manages document updates with protection
+- Metrics: Tracks token usage and costs
+- Trace: Records execution traces for debugging
+
+## License
+
+Licensed under the Apache License 2.0. See LICENSE file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit pull requests.
+
+## Support
+
+For issues, questions, or suggestions, please open an issue on GitHub.

glassbox_rag-0.1.0/README.md

@@ -0,0 +1,148 @@
+# GlassBox
+
+An open-source, high-transparency modular RAG (Retrieval-Augmented Generation) framework for AI/ML applications.
+
+## Features
+
+- Modular architecture with pluggable components
+- Support for multiple vector stores (Qdrant, Chroma)
+- Multiple embedding providers (OpenAI, Ollama, ONNX)
+- Database support (PostgreSQL, SQLite)
+- Comprehensive tracing and monitoring
+- FastAPI-based REST API
+- Web dashboard for trace visualization
+- Async/await support with asyncio
+- Pydantic v2 for robust configuration management
+
+## Installation
+
+Install from PyPI:
+
+```bash
+pip install glassbox-rag
+```
+
+## Quick Start
+
+```python
+from glassbox_rag.core.engine import GlassBoxEngine
+from glassbox_rag.config import GlassBoxConfig
+
+# Initialize the engine
+config = GlassBoxConfig()
+engine = GlassBoxEngine(config)
+
+# Ingest documents
+documents = [
+    {"content": "Document 1", "metadata": {"source": "source1"}},
+    {"content": "Document 2", "metadata": {"source": "source2"}},
+]
+engine.ingest(documents)
+
+# Retrieve relevant documents
+results = engine.retrieve("query text", top_k=5)
+```
+
+## Configuration
+
+Configure via YAML file (config/default.yaml):
+
+```yaml
+server:
+  host: "0.0.0.0"
+  port: 8000
+
+vector_store:
+  type: "qdrant"
+  config:
+    url: "http://localhost:6333"
+
+encoder:
+  type: "openai"
+  config:
+    api_key: "${OPENAI_API_KEY}"
+    model: "text-embedding-3-small"
+
+database:
+  type: "postgresql"
+  config:
+    url: "postgresql://user:password@localhost/glassbox"
+```
+
+## API Endpoints
+
+- GET /health - Health check
+- POST /retrieve - Retrieve documents
+- POST /ingest - Ingest new documents
+- POST /update - Update existing documents
+- GET /traces/{id} - Get execution trace
+- GET /traces/{id}/visualize - Visualize trace
+
+## Running the Server
+
+Start the FastAPI server with Uvicorn:
+
+```bash
+python -m glassbox_rag
+```
+
+The server will be available at http://localhost:8000
+
+## Web Dashboard
+
+Access the web dashboard at http://localhost:8000/ to:
+
+- View recent execution traces
+- Visualize trace hierarchy and timing
+- Monitor system metrics
+- Track token usage and costs
+
+## Testing
+
+Run the test suite:
+
+```bash
+pytest tests/ -v
+```
+
+## Plugin Architecture
+
+Extend GlassBox with custom plugins:
+
+1. Create a plugin class inheriting from the appropriate base class
+2. Implement required abstract methods
+3. Register in the configuration
+
+Example custom embedder:
+
+```python
+from glassbox_rag.plugins.base import EmbedderBase
+
+class CustomEmbedder(EmbedderBase):
+    def encode(self, texts):
+        # Your embedding implementation
+        return embeddings
+```
+
+## Architecture
+
+GlassBox consists of several core components:
+
+- Engine: Orchestrates all operations
+- Encoder: Handles document and query encoding
+- Retriever: Implements retrieval strategies
+- Writeback: Manages document updates with protection
+- Metrics: Tracks token usage and costs
+- Trace: Records execution traces for debugging
+
+## License
+
+Licensed under the Apache License 2.0. See LICENSE file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit pull requests.
+
+## Support
+
+For issues, questions, or suggestions, please open an issue on GitHub.

glassbox_rag-0.1.0/pyproject.toml

@@ -0,0 +1,91 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "glassbox-rag"
+version = "0.1.0"
+description = "An open-source, high-transparency modular RAG framework for AI/ML applications"
+requires-python = ">=3.9"
+readme = "README.md"
+license = "Apache-2.0"
+authors = [
+    {name = "averoe"}
+]
+keywords = ["rag", "retrieval", "generation", "onnx", "ollama", "vector-store", "multimodal"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+
+dependencies = [
+    "fastapi>=0.104.0",
+    "uvicorn[standard]>=0.24.0",
+    "pydantic>=2.0.0",
+    "pydantic-settings>=2.0.0",
+    "pyyaml>=6.0",
+    "numpy>=1.24.0",
+    "requests>=2.31.0",
+    "python-multipart>=0.0.6",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "black>=23.0.0",
+    "isort>=5.12.0",
+    "flake8>=6.0.0",
+    "mypy>=1.0.0",
+    "ruff>=0.1.0",
+]
+
+embeddings = [
+    "onnxruntime>=1.16.0",
+    "ollama>=0.0.50",
+    "openai>=1.3.0",
+]
+
+vector-stores = [
+    "qdrant-client>=2.4.0",
+    "chromadb>=0.4.0",
+    "psycopg2-binary>=2.9.0",
+]
+
+multimodal = [
+    "pillow>=10.0.0",
+    "pypdf>=3.17.0",
+    "python-pptx>=0.6.21",
+]
+
+[project.scripts]
+glassbox-rag = "glassbox_rag.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["glassbox_rag*"]
+
+[tool.black]
+line-length = 100
+target-version = ['py39']
+
+[tool.isort]
+profile = "black"
+line_length = 100
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.mypy]
+python_version = "3.9"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false

glassbox_rag-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

glassbox_rag-0.1.0/src/glassbox_rag/__init__.py

@@ -0,0 +1,16 @@
+"""
+GlassBox RAG - A transparent, modular RAG framework for AI/ML applications.
+
+High-level API for working with the GlassBox engine.
+"""
+
+__version__ = "0.1.0"
+__author__ = "GlassBox Team"
+
+from glassbox_rag.core.engine import GlassBoxEngine
+from glassbox_rag.trace.tracker import TraceTracker
+
+__all__ = [
+    "GlassBoxEngine",
+    "TraceTracker",
+]

glassbox_rag-0.1.0/src/glassbox_rag/__main__.py

@@ -0,0 +1,6 @@
+"""Entry point for running GlassBox RAG as a module."""
+
+from glassbox_rag.cli import main
+
+if __name__ == "__main__":
+    main()