operonx-kb 0.2.1__tar.gz

operonx_kb-0.2.1/.gitignore

@@ -0,0 +1,10 @@
+__pycache__/
+*.pyc
+.venv/
+.operonx/
+.pytest_cache/
+.ruff_cache/
+.hypothesis/
+dist/
+*.egg-info/
+.env

operonx_kb-0.2.1/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.

operonx_kb-0.2.1/PKG-INFO

@@ -0,0 +1,130 @@
+Metadata-Version: 2.5
+Name: operonx-kb
+Version: 0.2.1
+Summary: Knowledge base and document intelligence on OperonX: versioned documents with span-level provenance
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: defusedxml>=0.7.1
+Requires-Dist: httpx>=0.24
+Requires-Dist: numpy>=1.24
+Requires-Dist: operonx>=1.16
+Requires-Dist: pydantic>=2.0
+Provides-Extra: admin
+Requires-Dist: operonx[serve]; extra == 'admin'
+Requires-Dist: pillow>=10; extra == 'admin'
+Requires-Dist: pypdfium2>=4.30; extra == 'admin'
+Provides-Extra: all
+Requires-Dist: docling-parse>=7.22; extra == 'all'
+Requires-Dist: operonx[faiss]; extra == 'all'
+Requires-Dist: operonx[openai]; extra == 'all'
+Requires-Dist: operonx[serve]; extra == 'all'
+Requires-Dist: pillow>=10; extra == 'all'
+Requires-Dist: psycopg-pool>=3.2; extra == 'all'
+Requires-Dist: psycopg[binary]>=3.1; extra == 'all'
+Requires-Dist: pypdfium2>=4.30; extra == 'all'
+Provides-Extra: answer
+Requires-Dist: operonx[openai]; extra == 'answer'
+Provides-Extra: faiss
+Requires-Dist: operonx[faiss]; extra == 'faiss'
+Provides-Extra: layout
+Requires-Dist: docling-ibm-models[opencv-python-headless]>=4.0; extra == 'layout'
+Requires-Dist: docling-parse>=7.22; extra == 'layout'
+Requires-Dist: pypdfium2>=4.30; extra == 'layout'
+Requires-Dist: torch>=2.2.2; extra == 'layout'
+Requires-Dist: torchvision; extra == 'layout'
+Provides-Extra: pdf
+Requires-Dist: docling-parse>=7.22; extra == 'pdf'
+Provides-Extra: pgvector
+Requires-Dist: operonx[pgvector]; extra == 'pgvector'
+Provides-Extra: postgres
+Requires-Dist: psycopg-pool>=3.2; extra == 'postgres'
+Requires-Dist: psycopg[binary]>=3.1; extra == 'postgres'
+Provides-Extra: qdrant
+Requires-Dist: operonx[qdrant]; extra == 'qdrant'
+Description-Content-Type: text/markdown
+
+# operonx-kb
+
+Knowledge base and document intelligence on [operonx](https://github.com/batman1m2001-cyber/Operonx): files become versioned documents
+whose every character has an address (version, span → page, bbox), indexed for retrieval, and
+answers cite spans that were checked against the text they quote.
+
+```bash
+uv sync --extra pdf --extra faiss     # core + PDF text layer + FAISS index
+PYTHONPATH=../operonx-wt/feat-kb-upstream uv run pytest -q   # until operonx PR #74 merges
+```
+
+```python
+import operonx
+from operonx_kb import CollectionSpec, DenseIndexSpec, KnowledgeBase
+from operonx_kb.model.collection import LexicalIndexSpec
+
+operonx.bootstrap(resources="resources.yaml")  # kb_catalog:, kb_blob:, kb_lexical:, embedding:, vector_store:, llm:
+kb = KnowledgeBase()
+kb.create_collection("handbook", CollectionSpec(
+    dense=DenseIndexSpec(embedder="e5", store="vector_store:kb",
+                         passage_template="passage: {text}", query_template="query: {text}"),
+    lexical=LexicalIndexSpec(),  # SQLite FTS5 or Postgres FTS
+    filterable={"dept": "keyword"},
+))
+await kb.add("handbook", "policy.pdf", key="policy.pdf", tags=["hr"], acl=["team:hr"],
+             metadata={"dept": "hr"})
+found = await kb.search("handbook", "how many days of leave", mode="hybrid",
+                        filter={"acl_any": ["team:hr"]}, reranker="ce")
+answer = await kb.ask("handbook", "how many days of leave", "assistant")
+answer["citations"]  # each: quote, canonical span, pages, bboxes; unverified ones are in answer["dropped"]
+```
+
+```bash
+operonx-kb query handbook "how many days of leave" --mode hybrid --tag hr
+operonx-kb query wiki "who directed the film that won in 1999" --mode graph   # created with --graph
+operonx-kb query handbook "how many days of leave" --answer assistant
+operonx-kb eval handbook datasets/handbook.jsonl --mode hybrid
+```
+
+## Use it inside your flows
+
+A search is an operonx graph, so it is one step of your own flow — traced with it, no service in
+between (`tests/graphs/test_in_a_flow.py`):
+
+```python
+from operonx.kb.graphs import search   # module level: the collection's settings are read per run
+
+@graph
+def answer_flow(question, catalog):
+    found = search(query=question, collection="handbook", filter=None, k=5, mode="hybrid",
+                   catalog=catalog)
+    reply = cite(hits=found["hits"])          # your own op
+    START >> found >> reply >> END
+
+engine = Operon(answer_flow, params={"question": None, "catalog": None})
+out = await engine.run(inputs={"question": "...", "catalog": "kb_catalog:main"})
+```
+
+For an agent (operonx-agents installed beside it), `kb_tools` gives a read-only `kb_search` /
+`kb_read` toolset. The scope comes from your code or the run's context — the model only sends a
+query — and `kb_read` checks it again (`tests/graphs/test_agent_tools.py`):
+
+```python
+from operonx.kb.tools import kb_tools
+
+tools = kb_tools(kb, "handbook", scope=lambda ctx: {"acl_any": ctx.deps.principals})
+agent = Agent(name="hr", model=Model("assistant"), tools=[tools])
+```
+
+Studio's Knowledge tab reads a knowledge base through its admin API (extra `admin`), served as
+one of the project's services:
+
+```python
+import operonx
+from operonx.app import Service, asgi
+from operonx_kb.admin import kb_admin_app
+
+operonx.bootstrap()  # operonx serve loads no resources for an asgi service
+Service("kb_admin", asgi("/kb", port=8021), app=kb_admin_app(llm="assistant"))
+```
+
+Outstanding work (K5 visual retrieval needs a GPU): [BACKLOG.md](BACKLOG.md).
+Design and phase gates: [PLAN.md](PLAN.md); measured gates: [docs/bench](docs/bench).
+Contributor and agent rules: [AGENTS.md](AGENTS.md).

operonx_kb-0.2.1/README.md

@@ -0,0 +1,84 @@
+# operonx-kb
+
+Knowledge base and document intelligence on [operonx](https://github.com/batman1m2001-cyber/Operonx): files become versioned documents
+whose every character has an address (version, span → page, bbox), indexed for retrieval, and
+answers cite spans that were checked against the text they quote.
+
+```bash
+uv sync --extra pdf --extra faiss     # core + PDF text layer + FAISS index
+PYTHONPATH=../operonx-wt/feat-kb-upstream uv run pytest -q   # until operonx PR #74 merges
+```
+
+```python
+import operonx
+from operonx_kb import CollectionSpec, DenseIndexSpec, KnowledgeBase
+from operonx_kb.model.collection import LexicalIndexSpec
+
+operonx.bootstrap(resources="resources.yaml")  # kb_catalog:, kb_blob:, kb_lexical:, embedding:, vector_store:, llm:
+kb = KnowledgeBase()
+kb.create_collection("handbook", CollectionSpec(
+    dense=DenseIndexSpec(embedder="e5", store="vector_store:kb",
+                         passage_template="passage: {text}", query_template="query: {text}"),
+    lexical=LexicalIndexSpec(),  # SQLite FTS5 or Postgres FTS
+    filterable={"dept": "keyword"},
+))
+await kb.add("handbook", "policy.pdf", key="policy.pdf", tags=["hr"], acl=["team:hr"],
+             metadata={"dept": "hr"})
+found = await kb.search("handbook", "how many days of leave", mode="hybrid",
+                        filter={"acl_any": ["team:hr"]}, reranker="ce")
+answer = await kb.ask("handbook", "how many days of leave", "assistant")
+answer["citations"]  # each: quote, canonical span, pages, bboxes; unverified ones are in answer["dropped"]
+```
+
+```bash
+operonx-kb query handbook "how many days of leave" --mode hybrid --tag hr
+operonx-kb query wiki "who directed the film that won in 1999" --mode graph   # created with --graph
+operonx-kb query handbook "how many days of leave" --answer assistant
+operonx-kb eval handbook datasets/handbook.jsonl --mode hybrid
+```
+
+## Use it inside your flows
+
+A search is an operonx graph, so it is one step of your own flow — traced with it, no service in
+between (`tests/graphs/test_in_a_flow.py`):
+
+```python
+from operonx.kb.graphs import search   # module level: the collection's settings are read per run
+
+@graph
+def answer_flow(question, catalog):
+    found = search(query=question, collection="handbook", filter=None, k=5, mode="hybrid",
+                   catalog=catalog)
+    reply = cite(hits=found["hits"])          # your own op
+    START >> found >> reply >> END
+
+engine = Operon(answer_flow, params={"question": None, "catalog": None})
+out = await engine.run(inputs={"question": "...", "catalog": "kb_catalog:main"})
+```
+
+For an agent (operonx-agents installed beside it), `kb_tools` gives a read-only `kb_search` /
+`kb_read` toolset. The scope comes from your code or the run's context — the model only sends a
+query — and `kb_read` checks it again (`tests/graphs/test_agent_tools.py`):
+
+```python
+from operonx.kb.tools import kb_tools
+
+tools = kb_tools(kb, "handbook", scope=lambda ctx: {"acl_any": ctx.deps.principals})
+agent = Agent(name="hr", model=Model("assistant"), tools=[tools])
+```
+
+Studio's Knowledge tab reads a knowledge base through its admin API (extra `admin`), served as
+one of the project's services:
+
+```python
+import operonx
+from operonx.app import Service, asgi
+from operonx_kb.admin import kb_admin_app
+
+operonx.bootstrap()  # operonx serve loads no resources for an asgi service
+Service("kb_admin", asgi("/kb", port=8021), app=kb_admin_app(llm="assistant"))
+```
+
+Outstanding work (K5 visual retrieval needs a GPU): [BACKLOG.md](BACKLOG.md).
+Design and phase gates: [PLAN.md](PLAN.md); measured gates: [docs/bench](docs/bench).
+Contributor and agent rules: [AGENTS.md](AGENTS.md).

operonx_kb-0.2.1/operonx_kb/__init__.py

@@ -0,0 +1,71 @@
+"""operonx-kb: versioned documents with span-level provenance, on OperonX.
+
+Read ``PLAN.md`` first. The model lives in :mod:`operonx_kb.model`, the pure
+text and span functions in :mod:`operonx_kb.text`, the structurer in
+:mod:`operonx_kb.structure`, parsers in :mod:`operonx_kb.parsing` and
+:mod:`operonx_kb.pdf`, the ops and graphs in :mod:`operonx_kb.ops` and
+:mod:`operonx_kb.graphs`, and the library API in :class:`KnowledgeBase`.
+
+Its resource categories (``kb_catalog``, ``kb_blob``) reach operonx through
+``operonx.resources`` entry points, and importing the package registers them too.
+"""
+
+from operonx_kb import registry as _registry  # noqa: F401 — registers kb_* categories
+from operonx_kb.errors import (
+    CatalogError,
+    DocumentParseError,
+    KBError,
+    MissingExtraError,
+    SpanInvariantError,
+    UnsupportedFormatError,
+)
+from operonx_kb.kb import DEFAULT_MODE, IngestError, KnowledgeBase, QueryError
+from operonx_kb.model.collection import (
+    ChunkerSpec,
+    Collection,
+    CollectionSpec,
+    ContextualSpec,
+    DenseIndexSpec,
+    GraphSpec,
+    LayoutSpec,
+    TreeSpec,
+)
+from operonx_kb.model.document import (
+    Chunk,
+    Document,
+    DocumentVersion,
+    Element,
+    Page,
+    Region,
+    VersionChunk,
+)
+
+__version__ = "0.2.1"
+
+__all__ = [
+    "Chunk",
+    "ChunkerSpec",
+    "Collection",
+    "CollectionSpec",
+    "ContextualSpec",
+    "DenseIndexSpec",
+    "Document",
+    "DocumentVersion",
+    "Element",
+    "LayoutSpec",
+    "Page",
+    "Region",
+    "TreeSpec",
+    "GraphSpec",
+    "VersionChunk",
+    "DEFAULT_MODE",
+    "IngestError",
+    "QueryError",
+    "KnowledgeBase",
+    "KBError",
+    "SpanInvariantError",
+    "UnsupportedFormatError",
+    "DocumentParseError",
+    "CatalogError",
+    "MissingExtraError",
+]

operonx_kb-0.2.1/operonx_kb/admin/__init__.py

@@ -0,0 +1,24 @@
+"""The admin API Studio's Knowledge tab talks to (track5 §16.2): ``operonx-kb/1``.
+
+Studio never imports this package; it finds a KB by asking a served ``asgi``
+service for ``GET <path>/.well-known/operonx-kb`` and speaks the HTTP contract
+below. The contract is versioned (:data:`API`) so the two repos release
+independently.
+
+    import operonx
+    from operonx.app import Service, asgi
+    from operonx_kb.admin import kb_admin_app
+
+    operonx.bootstrap()  # the project's resources.yaml: operonx serve loads none for an asgi service
+    Service("kb_admin", asgi("/kb", port=8021), app=kb_admin_app(llm="gpt-4o-mini"))
+
+:mod:`operonx_kb.admin.views` holds what each route answers (pure reads of the
+catalog and blob store, and the query runs); :mod:`operonx_kb.admin.asgi` only
+routes. The ASGI app needs the ``admin`` extra (Starlette, and pypdfium2 for
+page images).
+"""
+
+from operonx_kb.admin.asgi import kb_admin_app
+from operonx_kb.admin.views import API
+
+__all__ = ["API", "kb_admin_app"]