harborrag 2.0.0a1__tar.gz

harborrag-2.0.0a1/.gitignore

@@ -0,0 +1,252 @@
+# 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
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+harborrag_control.db
+harborrag_control.db-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/*
+!.pixi/config.toml
+
+# 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/
+
+# HarborRAG local runtime state and ingested object data
+/.harborrag/
+/.local/
+# ...and the same, wherever a package nests its own local runtime state.
+**/.local/
+
+# 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
+
+.claude/**
+.agents/
+
+examples/
+
+# OS / editor noise
+.DS_Store
+.~lock.*#
+
+# Generated API contract artifact (exported by make openapi)
+openapi.json
+clients/typescript/src/schema.d.ts
+clients/typescript/dist/
+clients/typescript/node_modules/
+
+# Internal architecture working notes (kept out of the repo per team decision)
+docs/developers/architecture/http_backend/
+
+# Docling image output (config/parsers.yaml pdf-docling.image_output_dir)
+/data/docling-images/
+
+# Local macOS-compatible copy of dev.sh (bash 3.2 / BSD sed tweaks)
+scripts/deployment/dev-mac.sh

harborrag-2.0.0a1/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 [yyyy] [name of copyright owner]
+
+   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.

harborrag-2.0.0a1/PKG-INFO

@@ -0,0 +1,177 @@
+Metadata-Version: 2.5
+Name: harborrag
+Version: 2.0.0a1
+Summary: Meta-package public facade for HarborRAG.
+Project-URL: Homepage, https://github.com/cbtw-apac/HarborRAG
+Project-URL: Repository, https://github.com/cbtw-apac/HarborRAG
+Project-URL: Issues, https://github.com/cbtw-apac/HarborRAG/issues
+Author: HarborRAG Contributors
+License-Expression: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Requires-Dist: harborrag-core==2.0.0a1
+Requires-Dist: harborrag-runtime==2.0.0a1
+Provides-Extra: all
+Requires-Dist: harborrag-adapters[parsers-all]==2.0.0a1; extra == 'all'
+Requires-Dist: harborrag-app[api]==2.0.0a1; extra == 'all'
+Requires-Dist: harborrag-mcp-server[mcp]==2.0.0a1; extra == 'all'
+Requires-Dist: harborrag-memory==2.0.0a1; extra == 'all'
+Requires-Dist: harborrag-runtime[production,temporal]==2.0.0a1; extra == 'all'
+Provides-Extra: chat
+Requires-Dist: harborrag-adapters[llm]==2.0.0a1; extra == 'chat'
+Provides-Extra: cli
+Requires-Dist: harborrag-app==2.0.0a1; extra == 'cli'
+Provides-Extra: falkordb
+Requires-Dist: harborrag-adapters[falkordb]==2.0.0a1; extra == 'falkordb'
+Provides-Extra: local
+Requires-Dist: harborrag-adapters[chunking,control-plane,falkordb,llm,parsers,pdf-docling,qdrant,s3,tables]==2.0.0a1; extra == 'local'
+Provides-Extra: mcp
+Requires-Dist: harborrag-mcp-server[mcp]==2.0.0a1; extra == 'mcp'
+Provides-Extra: memory
+Requires-Dist: harborrag-memory==2.0.0a1; extra == 'memory'
+Provides-Extra: postgres
+Requires-Dist: harborrag-adapters[control-plane,postgres]==2.0.0a1; extra == 'postgres'
+Provides-Extra: qdrant
+Requires-Dist: harborrag-adapters[qdrant]==2.0.0a1; extra == 'qdrant'
+Provides-Extra: redis
+Requires-Dist: harborrag-adapters[redis]==2.0.0a1; extra == 'redis'
+Provides-Extra: s3
+Requires-Dist: harborrag-adapters[s3]==2.0.0a1; extra == 's3'
+Provides-Extra: server
+Requires-Dist: harborrag-app[api]==2.0.0a1; extra == 'server'
+Requires-Dist: harborrag-runtime[production,temporal]==2.0.0a1; extra == 'server'
+Provides-Extra: temporal
+Requires-Dist: harborrag-runtime[temporal]==2.0.0a1; extra == 'temporal'
+Description-Content-Type: text/markdown
+
+# harborrag
+
+`harborrag` is the public SDK facade and installation bundle for
+[HarborRAG](https://github.com/cbtw-apac/HarborRAG), a modular, provider-agnostic RAG
+framework for engineering knowledge. Importing it does not initialize provider clients or
+perform network I/O.
+
+- Documentation: <https://cbtw-apac.github.io/HarborRAG/>
+- Source: <https://github.com/cbtw-apac/HarborRAG>
+
+## Install
+
+```bash
+pip install "harborrag[all]"          # everything
+pip install "harborrag[local]"        # local end-to-end ingestion and retrieval
+pip install "harborrag[cli,qdrant]"   # or just what you need
+```
+
+A bare `pip install harborrag` installs the framework - contracts, engine, memory,
+adapters, and runtime - but deliberately **no third-party provider clients**. There is no
+vector store, no graph store, and no model client until you add an extra:
+
+| Extra | Adds |
+| --- | --- |
+| `local` | Qdrant, FalkorDB, S3, model client, chunking, control plane, parsers, Docling PDF, tables |
+| `chat` | the model client used by chat, embeddings, and reranking |
+| `cli` | the `harborrag` command |
+| `server` | the HTTP API plus the production and Temporal runtime |
+| `mcp` | the MCP transport |
+| `temporal` | the Temporal client for durable ingestion |
+| `qdrant`, `falkordb`, `postgres`, `s3`, `redis` | one provider each |
+| `all` | everything above; a superset of `local` |
+
+Conversation memory (`harborrag-memory`) is already a required dependency, so it is
+available in every install. The `harborrag[memory]` extra exists for explicitness and adds
+nothing new.
+
+See [Installation](https://cbtw-apac.github.io/HarborRAG/docs/getting-started/installation.html)
+for PDF/OCR backends, editable installs, and platform notes.
+
+## Ingest and retrieve
+
+`HarborRAG` exposes four async service facades - `ingestion`, `retrieval`, `graph`, and
+`chat` - behind one async context manager. Connectors are declared by name in your
+connector catalog, so credentials stay as environment references:
+
+```python
+import asyncio
+
+from harborrag import AccessContext, HarborRAG, IngestionRequest, RetrievalRequest
+
+
+async def main() -> None:
+    access = AccessContext(principal_id="user-1", tenant_id="tenant-1")
+
+    async with HarborRAG.from_config("config/harborrag.example.yaml") as harbor:
+        await harbor.ingestion.run(
+            IngestionRequest(access=access, connector_name="harborrag-workspace")
+        )
+        results = await harbor.retrieval.search(
+            RetrievalRequest(access=access, query="deployment requirements")
+        )
+        print(results)
+
+
+asyncio.run(main())
+```
+
+`config/harborrag.example.yaml` ships in the repository checkout. Copy it next to your
+application and point `from_config` at your own path.
+
+## Chat
+
+Chat needs a model provider, so install `harborrag[chat]` (or any extra that includes it,
+such as `local`, `server`, or `all`) and configure credentials first:
+
+```python
+from harborrag import ChatPrompt, HarborChatMessage, HarborChatRequest, HarborRAG
+
+async with HarborRAG.from_config("config/harborrag.example.yaml") as harbor:
+    response = await harbor.chat.complete(
+        HarborChatRequest(messages=(HarborChatMessage.user("Summarize the results"),)),
+        prompt=ChatPrompt.CONCISE,
+    )
+```
+
+## Direct versus durable execution
+
+Direct execution is the default: `ingestion.run` does the work inline.
+
+The durable controls - `submit`, `status`, `pause`, `resume`, and `cancel` - need
+`execution_mode: temporal` in your configuration **and** the `harborrag[temporal]` extra.
+Calling them without both raises `ExecutionCapabilityError`:
+
+```python
+task = await harbor.ingestion.submit(request)
+status = await harbor.ingestion.status(task.task_id)
+await harbor.ingestion.pause(task.task_id)
+await harbor.ingestion.resume(task.task_id)
+await harbor.ingestion.cancel(task.task_id)
+```
+
+## Related packages
+
+`harborrag` re-exports stable APIs from the workspace packages. Install one directly for a
+narrower dependency tree:
+
+| Package | Contains |
+| --- | --- |
+| `harborrag-core` | provider-neutral contracts and domain models |
+| `harborrag-adapters` | connectors, parsers, model clients, repositories |
+| `harborrag-engine` | ingestion and retrieval orchestration |
+| `harborrag-memory` | scope-aware conversation memory |
+| `harborrag-runtime` | production composition and Temporal orchestration |
+| `harborrag-app` | CLI and HTTP API |
+| `harborrag-mcp-server` | MCP tools and transport |
+
+## Development
+
+Tests for this package live in `packages/harborrag/tests/`. Run them from the repository
+root:
+
+```shell
+uv run pytest packages/harborrag/tests
+```
+
+Licensed under the Apache License 2.0.

harborrag-2.0.0a1/README.md

@@ -0,0 +1,127 @@
+# harborrag
+
+`harborrag` is the public SDK facade and installation bundle for
+[HarborRAG](https://github.com/cbtw-apac/HarborRAG), a modular, provider-agnostic RAG
+framework for engineering knowledge. Importing it does not initialize provider clients or
+perform network I/O.
+
+- Documentation: <https://cbtw-apac.github.io/HarborRAG/>
+- Source: <https://github.com/cbtw-apac/HarborRAG>
+
+## Install
+
+```bash
+pip install "harborrag[all]"          # everything
+pip install "harborrag[local]"        # local end-to-end ingestion and retrieval
+pip install "harborrag[cli,qdrant]"   # or just what you need
+```
+
+A bare `pip install harborrag` installs the framework - contracts, engine, memory,
+adapters, and runtime - but deliberately **no third-party provider clients**. There is no
+vector store, no graph store, and no model client until you add an extra:
+
+| Extra | Adds |
+| --- | --- |
+| `local` | Qdrant, FalkorDB, S3, model client, chunking, control plane, parsers, Docling PDF, tables |
+| `chat` | the model client used by chat, embeddings, and reranking |
+| `cli` | the `harborrag` command |
+| `server` | the HTTP API plus the production and Temporal runtime |
+| `mcp` | the MCP transport |
+| `temporal` | the Temporal client for durable ingestion |
+| `qdrant`, `falkordb`, `postgres`, `s3`, `redis` | one provider each |
+| `all` | everything above; a superset of `local` |
+
+Conversation memory (`harborrag-memory`) is already a required dependency, so it is
+available in every install. The `harborrag[memory]` extra exists for explicitness and adds
+nothing new.
+
+See [Installation](https://cbtw-apac.github.io/HarborRAG/docs/getting-started/installation.html)
+for PDF/OCR backends, editable installs, and platform notes.
+
+## Ingest and retrieve
+
+`HarborRAG` exposes four async service facades - `ingestion`, `retrieval`, `graph`, and
+`chat` - behind one async context manager. Connectors are declared by name in your
+connector catalog, so credentials stay as environment references:
+
+```python
+import asyncio
+
+from harborrag import AccessContext, HarborRAG, IngestionRequest, RetrievalRequest
+
+
+async def main() -> None:
+    access = AccessContext(principal_id="user-1", tenant_id="tenant-1")
+
+    async with HarborRAG.from_config("config/harborrag.example.yaml") as harbor:
+        await harbor.ingestion.run(
+            IngestionRequest(access=access, connector_name="harborrag-workspace")
+        )
+        results = await harbor.retrieval.search(
+            RetrievalRequest(access=access, query="deployment requirements")
+        )
+        print(results)
+
+
+asyncio.run(main())
+```
+
+`config/harborrag.example.yaml` ships in the repository checkout. Copy it next to your
+application and point `from_config` at your own path.
+
+## Chat
+
+Chat needs a model provider, so install `harborrag[chat]` (or any extra that includes it,
+such as `local`, `server`, or `all`) and configure credentials first:
+
+```python
+from harborrag import ChatPrompt, HarborChatMessage, HarborChatRequest, HarborRAG
+
+async with HarborRAG.from_config("config/harborrag.example.yaml") as harbor:
+    response = await harbor.chat.complete(
+        HarborChatRequest(messages=(HarborChatMessage.user("Summarize the results"),)),
+        prompt=ChatPrompt.CONCISE,
+    )
+```
+
+## Direct versus durable execution
+
+Direct execution is the default: `ingestion.run` does the work inline.
+
+The durable controls - `submit`, `status`, `pause`, `resume`, and `cancel` - need
+`execution_mode: temporal` in your configuration **and** the `harborrag[temporal]` extra.
+Calling them without both raises `ExecutionCapabilityError`:
+
+```python
+task = await harbor.ingestion.submit(request)
+status = await harbor.ingestion.status(task.task_id)
+await harbor.ingestion.pause(task.task_id)
+await harbor.ingestion.resume(task.task_id)
+await harbor.ingestion.cancel(task.task_id)
+```
+
+## Related packages
+
+`harborrag` re-exports stable APIs from the workspace packages. Install one directly for a
+narrower dependency tree:
+
+| Package | Contains |
+| --- | --- |
+| `harborrag-core` | provider-neutral contracts and domain models |
+| `harborrag-adapters` | connectors, parsers, model clients, repositories |
+| `harborrag-engine` | ingestion and retrieval orchestration |
+| `harborrag-memory` | scope-aware conversation memory |
+| `harborrag-runtime` | production composition and Temporal orchestration |
+| `harborrag-app` | CLI and HTTP API |
+| `harborrag-mcp-server` | MCP tools and transport |
+
+## Development
+
+Tests for this package live in `packages/harborrag/tests/`. Run them from the repository
+root:
+
+```shell
+uv run pytest packages/harborrag/tests
+```
+
+Licensed under the Apache License 2.0.

harborrag-2.0.0a1/pyproject.toml

@@ -0,0 +1,57 @@
+[project]
+name = "harborrag"
+version = "2.0.0a1"
+description = "Meta-package public facade for HarborRAG."
+requires-python = ">=3.12"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "HarborRAG Contributors" }]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3.12",
+    "Typing :: Typed",
+]
+dependencies = [
+    "harborrag-core==2.0.0a1",
+    "harborrag-runtime==2.0.0a1",
+]
+
+[project.urls]
+Homepage = "https://github.com/cbtw-apac/HarborRAG"
+Repository = "https://github.com/cbtw-apac/HarborRAG"
+Issues = "https://github.com/cbtw-apac/HarborRAG/issues"
+
+[project.optional-dependencies]
+local = [
+    "harborrag-adapters[chunking,control-plane,falkordb,llm,parsers,pdf-docling,qdrant,s3,tables]==2.0.0a1",
+]
+chat = ["harborrag-adapters[llm]==2.0.0a1"]
+cli = ["harborrag-app==2.0.0a1"]
+memory = ["harborrag-memory==2.0.0a1"]
+server = [
+    "harborrag-app[api]==2.0.0a1",
+    "harborrag-runtime[production,temporal]==2.0.0a1",
+]
+temporal = ["harborrag-runtime[temporal]==2.0.0a1"]
+mcp = ["harborrag-mcp-server[mcp]==2.0.0a1"]
+qdrant = ["harborrag-adapters[qdrant]==2.0.0a1"]
+falkordb = ["harborrag-adapters[falkordb]==2.0.0a1"]
+postgres = ["harborrag-adapters[control-plane,postgres]==2.0.0a1"]
+s3 = ["harborrag-adapters[s3]==2.0.0a1"]
+redis = ["harborrag-adapters[redis]==2.0.0a1"]
+all = [
+    "harborrag-adapters[parsers-all]==2.0.0a1",
+    "harborrag-app[api]==2.0.0a1",
+    "harborrag-mcp-server[mcp]==2.0.0a1",
+    "harborrag-memory==2.0.0a1",
+    "harborrag-runtime[production,temporal]==2.0.0a1",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/harborrag"]

harborrag-2.0.0a1/src/harborrag/__init__.py

@@ -0,0 +1,123 @@
+"""Stable, lightweight public facade for HarborRAG."""
+
+from __future__ import annotations
+
+from importlib import import_module
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from harborrag_core import Document
+    from harborrag_core.chunking import RelationType
+    from harborrag_core.models.chat import (
+        HarborChatMessage,
+        HarborChatRequest,
+        HarborChatResponse,
+    )
+    from harborrag_core.retrieval import (
+        GraphDirection,
+        GraphPathQuery,
+        GraphSubgraphQuery,
+        GraphTripletQuery,
+    )
+    from harborrag_core.security import AccessContext
+    from harborrag_runtime.chat import ChatPrompt
+    from harborrag_runtime.sdk import (
+        ExecutionMode,
+        GraphPathRequest,
+        GraphPathResponse,
+        GraphSubgraphRequest,
+        GraphSubgraphResponse,
+        GraphTripletRequest,
+        GraphTripletResponse,
+        HarborRAG,
+        HarborRAGConfig,
+        IngestionRequest,
+        IngestionResult,
+        IngestionStatus,
+        IngestionTaskReference,
+        RetrievalLane,
+        RetrievalRequest,
+        RetrievalResponse,
+    )
+
+__all__ = [
+    "AccessContext",
+    "ChatPrompt",
+    "Document",
+    "ExecutionMode",
+    "GraphDirection",
+    "GraphPathQuery",
+    "GraphPathRequest",
+    "GraphPathResponse",
+    "GraphSubgraphQuery",
+    "GraphSubgraphRequest",
+    "GraphSubgraphResponse",
+    "GraphTripletQuery",
+    "GraphTripletRequest",
+    "GraphTripletResponse",
+    "HarborChatMessage",
+    "HarborChatRequest",
+    "HarborChatResponse",
+    "HarborRAG",
+    "HarborRAGConfig",
+    "IngestionRequest",
+    "IngestionResult",
+    "IngestionStatus",
+    "IngestionTaskReference",
+    "RelationType",
+    "RetrievalLane",
+    "RetrievalRequest",
+    "RetrievalResponse",
+]
+
+_EXPORT_MODULES = {
+    "AccessContext": "harborrag_core.security",
+    "ChatPrompt": "harborrag_runtime.chat",
+    "Document": "harborrag_core",
+    "GraphDirection": "harborrag_core.retrieval",
+    "GraphPathQuery": "harborrag_core.retrieval",
+    "GraphSubgraphQuery": "harborrag_core.retrieval",
+    "GraphTripletQuery": "harborrag_core.retrieval",
+    "HarborChatMessage": "harborrag_core.models.chat",
+    "HarborChatRequest": "harborrag_core.models.chat",
+    "HarborChatResponse": "harborrag_core.models.chat",
+    "RelationType": "harborrag_core.chunking",
+    **dict.fromkeys(
+        (
+            "ExecutionMode",
+            "GraphPathRequest",
+            "GraphPathResponse",
+            "GraphSubgraphRequest",
+            "GraphSubgraphResponse",
+            "GraphTripletRequest",
+            "GraphTripletResponse",
+            "HarborRAG",
+            "HarborRAGConfig",
+            "IngestionRequest",
+            "IngestionResult",
+            "IngestionStatus",
+            "IngestionTaskReference",
+            "RetrievalLane",
+            "RetrievalRequest",
+            "RetrievalResponse",
+        ),
+        "harborrag_runtime.sdk",
+    ),
+}
+
+
+def __getattr__(name: str) -> Any:
+    """Load each public contract only when a caller first requests it."""
+    try:
+        module_name = _EXPORT_MODULES[name]
+    except KeyError as error:
+        raise AttributeError(f"module {__name__!r} has no attribute {name!r}") from error
+
+    value = getattr(import_module(module_name), name)
+    globals()[name] = value
+    return value
+
+
+def __dir__() -> list[str]:
+    """Include lazy public exports in interactive discovery."""
+    return sorted(set(globals()) | set(__all__))

harborrag-2.0.0a1/src/harborrag/py.typed

@@ -0,0 +1 @@
+# PEP 561 marker: the public facade ships inline type information.

harborrag-2.0.0a1/tests/test_meta_package.py

@@ -0,0 +1,102 @@
+from __future__ import annotations
+
+import subprocess
+import sys
+import tomllib
+from pathlib import Path
+
+import harborrag
+from harborrag import (
+    AccessContext,
+    ChatPrompt,
+    Document,
+    ExecutionMode,
+    GraphPathQuery,
+    GraphPathRequest,
+    GraphSubgraphQuery,
+    GraphSubgraphRequest,
+    GraphTripletQuery,
+    GraphTripletRequest,
+    HarborChatMessage,
+    HarborChatRequest,
+    HarborRAG,
+    HarborRAGConfig,
+    RelationType,
+    RetrievalLane,
+)
+
+PACKAGE_ROOT = Path(__file__).resolve().parents[1]
+
+
+def test_meta_exports_implemented_public_facade() -> None:
+    assert Document.__name__ == "Document"
+    assert AccessContext.__name__ == "AccessContext"
+    assert HarborRAG.__name__ == "HarborRAG"
+    assert HarborRAGConfig.__name__ == "HarborRAGConfig"
+    assert ExecutionMode.DIRECT == "direct"
+    assert RetrievalLane.HYBRID == "hybrid"
+    assert ChatPrompt.CONCISE == "concise"
+    assert RelationType.LINKS_TO == "links_to"
+    assert "CompositionRoot" not in harborrag.__all__
+
+
+def test_every_declared_public_export_resolves() -> None:
+    assert set(harborrag.__all__) <= set(dir(harborrag))
+    assert all(getattr(harborrag, name) is not None for name in harborrag.__all__)
+
+
+def test_chat_sdk_request_is_constructible_from_public_exports() -> None:
+    request = HarborChatRequest(messages=(HarborChatMessage.user("Hello"),))
+
+    assert request.messages[0].content == "Hello"
+
+
+def test_graph_sdk_requests_are_constructible_from_public_exports() -> None:
+    access = AccessContext(principal_id="user-1", tenant_id="tenant-1")
+
+    triplet = GraphTripletRequest(
+        access=access,
+        query=GraphTripletQuery(subject="document-1"),
+    )
+    path = GraphPathRequest(
+        access=access,
+        query=GraphPathQuery(start_node="document-1", end_node="document-2"),
+    )
+    subgraph = GraphSubgraphRequest(
+        access=access,
+        query=GraphSubgraphQuery(start_node="document-1"),
+    )
+
+    assert triplet.access == path.access == subgraph.access == access
+
+
+def test_base_install_declares_only_directly_imported_packages() -> None:
+    project = tomllib.loads((PACKAGE_ROOT / "pyproject.toml").read_text(encoding="utf-8"))[
+        "project"
+    ]
+
+    version = project["version"]
+    assert project["dependencies"] == [
+        f"harborrag-core=={version}",
+        f"harborrag-runtime=={version}",
+    ]
+    assert project["optional-dependencies"]["chat"] == [f"harborrag-adapters[llm]=={version}"]
+    assert project["optional-dependencies"]["local"] == [
+        "harborrag-adapters[chunking,control-plane,falkordb,llm,parsers,"
+        f"pdf-docling,qdrant,s3,tables]=={version}"
+    ]
+    assert f"harborrag-adapters[parsers-all]=={version}" in project["optional-dependencies"]["all"]
+
+
+def test_base_facade_import_does_not_load_optional_providers() -> None:
+    script = """
+import sys
+import harborrag
+from harborrag import HarborRAG
+
+assert HarborRAG.__name__ == "HarborRAG"
+for module in ("aioboto3", "falkordb", "litellm", "qdrant_client", "temporalio"):
+    assert module not in sys.modules, module
+"""
+
+    subprocess.run([sys.executable, "-c", script], check=True, timeout=15)