voyage-ledgerproof 0.1.0__tar.gz

voyage_ledgerproof-0.1.0/LICENSE

@@ -0,0 +1,189 @@
+                                 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 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 accept warranty
+      or additional liability for, or impose any obligations 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
+
+   Copyright 2026 LedgerProof Foundation (in formation)
+
+   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.

voyage_ledgerproof-0.1.0/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: voyage-ledgerproof
+Version: 0.1.0
+Summary: LedgerProof adapter for the Voyage AI Python SDK. Side-channel transparency receipts for EU AI Act Article 50 RAG pipeline evidence.
+Author: LedgerProof Foundation (in formation)
+License: Apache-2.0
+Project-URL: Homepage, https://ledgerproof.org
+Project-URL: Repository, https://github.com/ledgerproof/ledgerproof
+Project-URL: Documentation, https://docs.ledgerproof.org
+Keywords: ledgerproof,voyage,voyageai,embeddings,rerank,rag,eu-ai-act,article-50,transparency,receipts
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+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 :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security :: Cryptography
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: voyageai>=0.3
+Requires-Dist: cryptography>=41
+Requires-Dist: cbor2>=5.0
+Requires-Dist: pydantic>=2.0
+Provides-Extra: test
+Requires-Dist: pytest>=7.0; extra == "test"
+Requires-Dist: pytest-asyncio>=0.21; extra == "test"
+Dynamic: license-file
+
+# ledgerproof-voyage
+
+LedgerProof adapter for the [Voyage AI Python SDK](https://github.com/voyage-ai/voyageai-python) (embeddings + rerank).
+
+Emits **side-channel cryptographic transparency receipts** that capture the upstream retrieval evidence
+(embeddings, rerank scores) feeding a downstream chatbot, suitable as an evidence layer for the
+**EU AI Act Article 50** RAG pipeline scenario.
+
+This adapter is **not endorsed by Voyage AI** or MongoDB. It wraps the official `voyageai` SDK; it is not
+affiliated with Voyage AI Inc. or MongoDB Inc.
+
+## Why an embeddings adapter for an Article 50 protocol?
+
+Voyage AI is **upstream RAG infrastructure**. Calls to `voyageai.Client.embed()` and
+`voyageai.Client.rerank()` are **not themselves** direct Article 50(1) "AI system intended to interact
+directly with natural persons" surfaces — they are retrieval-side substrate.
+
+But they are the **evidence trail** for any RAG pipeline whose downstream chatbot output **is** under
+Article 50. When a regulator (or an internal auditor, or a litigant) asks the load-bearing question
+*"what sources did the model see, and how did they get there?"*, the answer is a chain:
+
+```
+user query
+  -> Voyage embed(query)              [embedding_inference/v1]
+  -> Voyage embed(documents)          [embedding_inference/v1]
+  -> ANN retrieval (vector DB)        [out of scope]
+  -> Voyage rerank(query, candidates) [rerank_inference/v1]
+  -> downstream chatbot turn          [bound by rag_pipeline_evidence/v1]
+```
+
+This adapter signs each link of that chain locally (constraint C4) so the full provenance is verifiable
+offline from the stored signed receipts. The downstream chatbot turn is captured by the matching
+LedgerProof chat adapter (`ledgerproof-openai`, `ledgerproof-anthropic`, `ledgerproof-cohere`, etc.) and
+both are stitched together by a `rag_pipeline_evidence/v1` envelope.
+
+This positioning matters because **most Tier-1 EU enterprise AI deployments under Article 50 enforcement
+(2 August 2026) are RAG-shaped**, and the regulator's first incident-response question is invariably
+"what evidence does the model have?". A signed Voyage embedding + rerank receipt is the cryptographic
+answer.
+
+## 5-minute quickstart
+
+```bash
+pip install ledgerproof-voyage
+export VOYAGE_API_KEY=...
+```
+
+```python
+from ledgerproof_voyage import LedgerProofVoyage, LogEmitter
+
+client = LedgerProofVoyage(
+    deployer_id="acme-corp-eu",
+    emitter=LogEmitter(),
+)
+
+result = client.embed(
+    texts=["Article 50 transparency obligations apply from 2 August 2026."],
+    model="voyage-3-large",
+    input_type="document",
+)
+
+print(result.embeddings[0][:4], "...")
+# Receipt has already been emitted to the side-channel.
+```
+
+The Voyage `EmbeddingsObject` is returned **unchanged**. The receipt is emitted to the side channel only
+(C7).
+
+## Three schemas
+
+| Schema | Article 50 mapping | What it binds |
+| --- | --- | --- |
+| `embedding_inference/v1` | Supporting infrastructure | per-input SHA-256, per-vector SHA-256, vector dim, model_id, input_type |
+| `rerank_inference/v1` | Supporting infrastructure | query SHA-256, per-candidate SHA-256, relevance scores, post-rerank order, model_id |
+| `rag_pipeline_evidence/v1` | Article 50(1) variant | upstream embed + rerank receipt hashes -> downstream chat receipt hash + user query hash |
+
+`embedding_inference/v1` and `rerank_inference/v1` carry
+`regulatory_context.article_50_paragraph = "supporting"` — they are not Article 50(1) artefacts in
+themselves. `rag_pipeline_evidence/v1` carries `"1"` because that is the regulated user-facing turn.
+
+## Three integration patterns
+
+1. **Client wrapper** (recommended) — `LedgerProofVoyage` wraps `voyageai.Client` and intercepts
+   `embed()` and `rerank()`. Sync and async (`LedgerProofAsyncVoyage`) supported.
+2. **Decorator** — `@lpr_track_embed(deployer_id=..., model=...)` and
+   `@lpr_track_rerank(deployer_id=..., model=...)` for user-defined functions wrapping Voyage calls.
+3. **Manual emission** — `emit_embedding_receipt(...)`, `emit_rerank_receipt(...)`, and
+   `emit_rag_pipeline_receipt(...)` for full control inside a custom RAG orchestration layer.
+
+See `examples/`:
+
+- `examples/01_voyage_embed_quickstart.py` — vanilla `embed()`
+- `examples/02_voyage_rerank.py` — `rerank()` with relevance-score binding
+- `examples/03_rag_pipeline_evidence.py` — full embed -> rerank -> (downstream chat stub) -> `rag_pipeline_evidence/v1`
+
+## Architectural discipline (C1–C8)
+
+This adapter is implemented under the LedgerProof protocol's load-bearing constraints:
+
+- **C1**: **No claim of regulator endorsement. No claim of Article 40 presumption of conformity. Not
+  endorsed by Voyage AI Inc. or MongoDB Inc.** This adapter wraps the official Voyage Python SDK; it is
+  not affiliated with either company.
+- **C4**: Local verification only. The adapter does **not** phone home to LedgerProof servers during
+  normal operation. Signed receipts verify offline given the public key.
+- **C6**: Stream-aware signing primitives are exposed for downstream chat adapters. Voyage's own surfaces
+  (`embed`, `rerank`) are non-streaming today.
+- **C7**: Side-channel emission only. The adapter **cannot and does not modify** the Voyage response
+  payload. The `EmbeddingsObject` / `RerankingObject` is returned unchanged.
+
+## GDPR posture
+
+Receipts reference content by SHA-256 hash only. The adapter **does not store**:
+
+- raw input texts to `embed()`
+- raw document text fed to `rerank()`
+- raw embedding vectors (the vector is canonicalized to big-endian float64 and hashed; the hash is
+  stored, not the vector)
+- raw user queries fed into the downstream chatbot
+
+Identifiers (`deployer_id`, `document_id`, `tool_call_id`) are length-bounded and character-set-
+restricted (no free-form PII). The deployer is responsible for ensuring the inputs they feed in
+(e.g. `document_id` values) do not themselves leak PII.
+
+## Vector canonicalization
+
+Embedding vectors are canonicalized to **IEEE-754 big-endian float64** byte strings before hashing. This
+is portable across machines, Python versions, and operating systems. A verifier with the original vector
+can recompute `SHA-256(canonicalize_vector(vector))` and compare to `vector_sha256_hex` in the receipt.
+
+Voyage exposes `output_dtype=` for higher-precision dtypes (`int8`, `uint8`, `binary`, `ubinary`); the
+adapter records the requested `output_dtype` on `VoyageModelRef.output_dtype` for transparency, but
+always canonicalizes through float64 for one stable wire format.
+
+## Scope disclaimer
+
+LedgerProof provides an **evidence layer for Article 50 transparency obligations only**.
+
+It does **not** cover:
+
+- Article 9 (risk management system)
+- Article 10 (data and data governance)
+- Article 13 (transparency and information to deployers)
+- Article 15 (accuracy, robustness, and cybersecurity)
+- Article 72 (post-market monitoring)
+
+LedgerProof does **not** confer presumption of conformity under Article 40. LedgerProof is not endorsed
+by the European Commission, the AI Office, any national competent authority, **Voyage AI Inc., or
+MongoDB Inc.**
+
+This adapter wraps the official `voyageai` Python SDK; it is not affiliated with Voyage AI Inc. or
+MongoDB Inc.
+
+## License
+
+Apache 2.0. Copyright 2026 LedgerProof Foundation (in formation: US 501(c)(3) Delaware + Dutch Stichting
+EU subsidiary).

voyage_ledgerproof-0.1.0/README.md

@@ -0,0 +1,156 @@
+# ledgerproof-voyage
+
+LedgerProof adapter for the [Voyage AI Python SDK](https://github.com/voyage-ai/voyageai-python) (embeddings + rerank).
+
+Emits **side-channel cryptographic transparency receipts** that capture the upstream retrieval evidence
+(embeddings, rerank scores) feeding a downstream chatbot, suitable as an evidence layer for the
+**EU AI Act Article 50** RAG pipeline scenario.
+
+This adapter is **not endorsed by Voyage AI** or MongoDB. It wraps the official `voyageai` SDK; it is not
+affiliated with Voyage AI Inc. or MongoDB Inc.
+
+## Why an embeddings adapter for an Article 50 protocol?
+
+Voyage AI is **upstream RAG infrastructure**. Calls to `voyageai.Client.embed()` and
+`voyageai.Client.rerank()` are **not themselves** direct Article 50(1) "AI system intended to interact
+directly with natural persons" surfaces — they are retrieval-side substrate.
+
+But they are the **evidence trail** for any RAG pipeline whose downstream chatbot output **is** under
+Article 50. When a regulator (or an internal auditor, or a litigant) asks the load-bearing question
+*"what sources did the model see, and how did they get there?"*, the answer is a chain:
+
+```
+user query
+  -> Voyage embed(query)              [embedding_inference/v1]
+  -> Voyage embed(documents)          [embedding_inference/v1]
+  -> ANN retrieval (vector DB)        [out of scope]
+  -> Voyage rerank(query, candidates) [rerank_inference/v1]
+  -> downstream chatbot turn          [bound by rag_pipeline_evidence/v1]
+```
+
+This adapter signs each link of that chain locally (constraint C4) so the full provenance is verifiable
+offline from the stored signed receipts. The downstream chatbot turn is captured by the matching
+LedgerProof chat adapter (`ledgerproof-openai`, `ledgerproof-anthropic`, `ledgerproof-cohere`, etc.) and
+both are stitched together by a `rag_pipeline_evidence/v1` envelope.
+
+This positioning matters because **most Tier-1 EU enterprise AI deployments under Article 50 enforcement
+(2 August 2026) are RAG-shaped**, and the regulator's first incident-response question is invariably
+"what evidence does the model have?". A signed Voyage embedding + rerank receipt is the cryptographic
+answer.
+
+## 5-minute quickstart
+
+```bash
+pip install ledgerproof-voyage
+export VOYAGE_API_KEY=...
+```
+
+```python
+from ledgerproof_voyage import LedgerProofVoyage, LogEmitter
+
+client = LedgerProofVoyage(
+    deployer_id="acme-corp-eu",
+    emitter=LogEmitter(),
+)
+
+result = client.embed(
+    texts=["Article 50 transparency obligations apply from 2 August 2026."],
+    model="voyage-3-large",
+    input_type="document",
+)
+
+print(result.embeddings[0][:4], "...")
+# Receipt has already been emitted to the side-channel.
+```
+
+The Voyage `EmbeddingsObject` is returned **unchanged**. The receipt is emitted to the side channel only
+(C7).
+
+## Three schemas
+
+| Schema | Article 50 mapping | What it binds |
+| --- | --- | --- |
+| `embedding_inference/v1` | Supporting infrastructure | per-input SHA-256, per-vector SHA-256, vector dim, model_id, input_type |
+| `rerank_inference/v1` | Supporting infrastructure | query SHA-256, per-candidate SHA-256, relevance scores, post-rerank order, model_id |
+| `rag_pipeline_evidence/v1` | Article 50(1) variant | upstream embed + rerank receipt hashes -> downstream chat receipt hash + user query hash |
+
+`embedding_inference/v1` and `rerank_inference/v1` carry
+`regulatory_context.article_50_paragraph = "supporting"` — they are not Article 50(1) artefacts in
+themselves. `rag_pipeline_evidence/v1` carries `"1"` because that is the regulated user-facing turn.
+
+## Three integration patterns
+
+1. **Client wrapper** (recommended) — `LedgerProofVoyage` wraps `voyageai.Client` and intercepts
+   `embed()` and `rerank()`. Sync and async (`LedgerProofAsyncVoyage`) supported.
+2. **Decorator** — `@lpr_track_embed(deployer_id=..., model=...)` and
+   `@lpr_track_rerank(deployer_id=..., model=...)` for user-defined functions wrapping Voyage calls.
+3. **Manual emission** — `emit_embedding_receipt(...)`, `emit_rerank_receipt(...)`, and
+   `emit_rag_pipeline_receipt(...)` for full control inside a custom RAG orchestration layer.
+
+See `examples/`:
+
+- `examples/01_voyage_embed_quickstart.py` — vanilla `embed()`
+- `examples/02_voyage_rerank.py` — `rerank()` with relevance-score binding
+- `examples/03_rag_pipeline_evidence.py` — full embed -> rerank -> (downstream chat stub) -> `rag_pipeline_evidence/v1`
+
+## Architectural discipline (C1–C8)
+
+This adapter is implemented under the LedgerProof protocol's load-bearing constraints:
+
+- **C1**: **No claim of regulator endorsement. No claim of Article 40 presumption of conformity. Not
+  endorsed by Voyage AI Inc. or MongoDB Inc.** This adapter wraps the official Voyage Python SDK; it is
+  not affiliated with either company.
+- **C4**: Local verification only. The adapter does **not** phone home to LedgerProof servers during
+  normal operation. Signed receipts verify offline given the public key.
+- **C6**: Stream-aware signing primitives are exposed for downstream chat adapters. Voyage's own surfaces
+  (`embed`, `rerank`) are non-streaming today.
+- **C7**: Side-channel emission only. The adapter **cannot and does not modify** the Voyage response
+  payload. The `EmbeddingsObject` / `RerankingObject` is returned unchanged.
+
+## GDPR posture
+
+Receipts reference content by SHA-256 hash only. The adapter **does not store**:
+
+- raw input texts to `embed()`
+- raw document text fed to `rerank()`
+- raw embedding vectors (the vector is canonicalized to big-endian float64 and hashed; the hash is
+  stored, not the vector)
+- raw user queries fed into the downstream chatbot
+
+Identifiers (`deployer_id`, `document_id`, `tool_call_id`) are length-bounded and character-set-
+restricted (no free-form PII). The deployer is responsible for ensuring the inputs they feed in
+(e.g. `document_id` values) do not themselves leak PII.
+
+## Vector canonicalization
+
+Embedding vectors are canonicalized to **IEEE-754 big-endian float64** byte strings before hashing. This
+is portable across machines, Python versions, and operating systems. A verifier with the original vector
+can recompute `SHA-256(canonicalize_vector(vector))` and compare to `vector_sha256_hex` in the receipt.
+
+Voyage exposes `output_dtype=` for higher-precision dtypes (`int8`, `uint8`, `binary`, `ubinary`); the
+adapter records the requested `output_dtype` on `VoyageModelRef.output_dtype` for transparency, but
+always canonicalizes through float64 for one stable wire format.
+
+## Scope disclaimer
+
+LedgerProof provides an **evidence layer for Article 50 transparency obligations only**.
+
+It does **not** cover:
+
+- Article 9 (risk management system)
+- Article 10 (data and data governance)
+- Article 13 (transparency and information to deployers)
+- Article 15 (accuracy, robustness, and cybersecurity)
+- Article 72 (post-market monitoring)
+
+LedgerProof does **not** confer presumption of conformity under Article 40. LedgerProof is not endorsed
+by the European Commission, the AI Office, any national competent authority, **Voyage AI Inc., or
+MongoDB Inc.**
+
+This adapter wraps the official `voyageai` Python SDK; it is not affiliated with Voyage AI Inc. or
+MongoDB Inc.
+
+## License
+
+Apache 2.0. Copyright 2026 LedgerProof Foundation (in formation: US 501(c)(3) Delaware + Dutch Stichting
+EU subsidiary).

voyage_ledgerproof-0.1.0/ledgerproof_voyage/__init__.py

@@ -0,0 +1,102 @@
+"""
+LedgerProof adapter for the Voyage AI Python SDK (embeddings + rerank).
+
+Side-channel cryptographic transparency receipts for EU AI Act Article 50 RAG
+pipeline evidence. Voyage AI is upstream RAG infrastructure; this adapter binds
+embedding + rerank evidence to a downstream chatbot turn so the full
+retrieval -> generation chain is cryptographically verifiable.
+
+Discipline:
+  - C1: No regulator endorsement. No Article 40 presumption of conformity.
+        Not endorsed by Voyage AI / MongoDB.
+  - C4: Offline verification only; no phone-home.
+  - C6: Stream-aware SHA-256 primitives available for downstream chat receipts.
+  - C7: Side-channel emission only; never modifies the Voyage response.
+"""
+
+from .async_client_wrapper import LedgerProofAsyncVoyage
+from .client_wrapper import LedgerProofVoyage
+from .decorator import lpr_track_embed, lpr_track_rerank
+from .emitter import (
+    Emitter,
+    LogEmitter,
+    MultiEmitter,
+    QueueEmitter,
+    StderrEmitter,
+    WebhookEmitter,
+)
+from .manual import (
+    build_embedding_refs,
+    build_rerank_result_refs,
+    build_voyage_model_ref,
+    emit_embedding_receipt,
+    emit_rag_pipeline_receipt,
+    emit_rerank_receipt,
+    extract_embeddings,
+    extract_rerank_results,
+    extract_total_tokens,
+)
+from .schema import (
+    DownstreamChatRef,
+    EmbeddingRef,
+    ReceiptV1,
+    RegulatoryContext,
+    RerankResultRef,
+    UpstreamReceiptRef,
+    VoyageModelRef,
+    build_embedding_inference_receipt,
+    build_rag_pipeline_evidence_receipt,
+    build_rerank_inference_receipt,
+)
+from .signer import (
+    AwsKmsEd25519Signer,
+    Ed25519Signer,
+    GcpKmsEd25519Signer,
+    Signer,
+    verify,
+)
+from .version import __version__
+
+__all__ = [
+    "__version__",
+    # client wrappers
+    "LedgerProofVoyage",
+    "LedgerProofAsyncVoyage",
+    # decorators
+    "lpr_track_embed",
+    "lpr_track_rerank",
+    # manual
+    "emit_embedding_receipt",
+    "emit_rerank_receipt",
+    "emit_rag_pipeline_receipt",
+    "build_embedding_refs",
+    "build_rerank_result_refs",
+    "build_voyage_model_ref",
+    "extract_embeddings",
+    "extract_rerank_results",
+    "extract_total_tokens",
+    # schemas
+    "EmbeddingRef",
+    "RerankResultRef",
+    "UpstreamReceiptRef",
+    "DownstreamChatRef",
+    "VoyageModelRef",
+    "ReceiptV1",
+    "RegulatoryContext",
+    "build_embedding_inference_receipt",
+    "build_rerank_inference_receipt",
+    "build_rag_pipeline_evidence_receipt",
+    # emitters
+    "Emitter",
+    "LogEmitter",
+    "StderrEmitter",
+    "WebhookEmitter",
+    "QueueEmitter",
+    "MultiEmitter",
+    # signers
+    "Signer",
+    "Ed25519Signer",
+    "AwsKmsEd25519Signer",
+    "GcpKmsEd25519Signer",
+    "verify",
+]