nace-haystack 0.1.0__tar.gz

nace_haystack-0.1.0/.gitignore

@@ -0,0 +1,15 @@
+__pycache__/
+*.py[cod]
+.venv/
+dist/
+build/
+*.egg-info/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+coverage.xml
+.env
+.DS_Store
+.ipynb_checkpoints/
+examples/data/scanned_invoice.png

nace_haystack-0.1.0/CHANGELOG.md

@@ -0,0 +1,51 @@
+# Changelog
+
+## [Unreleased]
+
+## [0.1.0] - 2026-10-29
+
+First release.
+
+### Added
+
+- `NaceTextRouter`: routes a text to one output per label with Drex, with a `low_confidence` fallback and an opt-in
+  `probabilities` output. Takes images (`ImageContent`, `ByteStream`, or files uploaded to Drex).
+- `NaceDocumentClassifier`: answers typed questions about each document and stores Drex's answers in its metadata,
+  with parallel requests and per-document failure handling.
+- `NaceFaithfulnessEvaluator` and `NaceContextRelevanceEvaluator`: the inputs and outputs of Haystack's built-in LLM
+  evaluators, with one Drex request per item.
+- Same parameters and outputs as deepset's `typesafe-haystack` components, so Jev pipelines switch with the documented
+  edits.
+- Default model `drex-max-v1.1` (Drex Max v1.1). Any model ID is sent as given, and answers keep every field Drex returns, so new Drex
+  models, question types and answer fields work without a new release.
+- Images too big for one request are shrunk to fit (Pillow, optional).
+- OpenRouter backend, attribution headers, a 60-second timeout, and retries on 429 and 529 that honour
+  `retry-after-ms`.
+- Readable errors that keep nace-sdk's error classes.
+
+### Changed
+
+- Licensed under Apache-2.0, the licence of Haystack's own integrations.
+
+### Fixed
+
+Found while preparing the release, before anything was published:
+
+- With `raise_on_failure=True`, the classifier and evaluators stop sending requests as soon as one fails, instead of
+  sending every queued request first.
+- Waits that the server asks for between retries are capped at 60 seconds.
+- OpenRouter variants of text-only models, such as `nace-ai/drex-v2.0:floor`, are refused images before sending,
+  like the models themselves.
+- A `ByteStream` typed `application/octet-stream` is sent with its real image type.
+- A 402 from OpenRouter points to OpenRouter's credits page instead of Nace billing.
+- HTML error pages are summarised in one line, and long error messages are cut to 500 characters.
+- `run_async` works again after the event loop changes, for example a second `asyncio.run` or notebook cell; it
+  failed with "Event loop is closed".
+- A 16-bit grayscale scan that has to be shrunk keeps its content instead of turning into a blank white page.
+- A 404 or 405 error names the URL it went to, so a wrong base URL is easy to spot.
+- The router raises a clear error when the backend answers with a label it wasn't given, instead of dropping the
+  text.
+- A label named `type` with a description is refused, because a saved pipeline with it couldn't be loaded.
+- The evaluators explain that `images` takes one list per item when given a flat list.
+- `pydantic>=2.0` and `filetype>=1.0.0` are declared as dependencies; `filetype` 0.x can't be imported on
+  Python 3.11.

nace_haystack-0.1.0/LICENSE.txt

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

nace_haystack-0.1.0/PKG-INFO

@@ -0,0 +1,230 @@
+Metadata-Version: 2.5
+Name: nace-haystack
+Version: 0.1.0
+Summary: Haystack integration for Drex decision models by Nace
+Project-URL: Documentation, https://console.nace.ai/docs
+Project-URL: Issues, https://github.com/nace-ai/nace-haystack/issues
+Project-URL: Source, https://github.com/nace-ai/nace-haystack
+Author-email: Nace AI <hello@nace.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Keywords: Drex,Haystack,Nace,classification,decision model,evaluation,routing
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Requires-Python: >=3.11
+Requires-Dist: filetype>=1.0.0
+Requires-Dist: haystack-ai>=3.0.0
+Requires-Dist: httpx<1.0,>=0.27
+Requires-Dist: nace-sdk<1.0.0,>=0.3.0
+Requires-Dist: pydantic>=2.0
+Description-Content-Type: text/markdown
+
+# nace-haystack
+
+Haystack components for [Drex](https://console.nace.ai/docs), Nace's decision models.
+
+Drex models don't generate text. They answer typed questions about a text, JSON or images in one request and return
+calibrated probabilities:
+
+- `choice` picks one label from a set of options,
+- `score` rates the input on ordered levels,
+- `noul` gives the probability that a yes/no statement is true.
+
+This package brings them to Haystack pipelines:
+
+| Component | What it does |
+| --- | --- |
+| `NaceTextRouter` | Routes a text (and optional images) to one output per label, with a `low_confidence` fallback |
+| `NaceDocumentClassifier` | Answers questions about each document and stores the answers in its metadata |
+| `NaceFaithfulnessEvaluator` | Judges whether answers are supported by their contexts, like Haystack's `FaithfulnessEvaluator` |
+| `NaceContextRelevanceEvaluator` | Judges whether retrieved contexts help answer the question, like `ContextRelevanceEvaluator` |
+
+The router and classifier mirror deepset's `typesafe-haystack` components for Jev, so a Jev pipeline switches to Drex
+with a few edits (see [Switching from TypeSafe](#switching-from-typesafe)).
+
+## Installation
+
+```bash
+pip install nace-haystack
+```
+
+Create an API key at [console.nace.ai](https://console.nace.ai) and set it as `NACE_API_KEY`.
+
+## Usage
+
+### Route text
+
+```python
+from haystack_integrations.components.routers.nace import NaceTextRouter
+
+router = NaceTextRouter(
+    labels={
+        "billing": "Payments, invoices, refunds and charges",
+        "technical": "Bugs, crashes and errors in the product",
+    },
+    instructions="Which team should handle this support request?",
+    min_confidence=0.6,
+)
+
+print(router.run(text="I was charged twice for my subscription."))
+# {'billing': 'I was charged twice for my subscription.'}
+```
+
+Texts whose answer is less confident than `min_confidence` go to the `low_confidence` output, for a fallback such
+as an LLM or a person. With `include_probabilities=True`, a `probabilities` output carries the full answer, so
+thresholds stay in your pipeline.
+
+### Classify documents
+
+```python
+from haystack import Document
+
+from haystack_integrations.components.classifiers.nace import NaceDocumentClassifier
+
+classifier = NaceDocumentClassifier(
+    questions={
+        "department": {
+            "type": "choice",
+            "instructions": "Which department should handle this ticket?",
+            "criteria": {"billing": None, "technical": None, "sales": None},
+        },
+        "urgency": {
+            "type": "score",
+            "instructions": "How urgent is this ticket?",
+            "criteria": ["can wait", "this week", "today"],
+        },
+        "refund": {"type": "noul", "instructions": "Is the customer asking for a refund?"},
+    },
+)
+
+result = classifier.run(documents=[Document(content="I was charged twice, please refund me today.")])
+print(result["documents"][0].meta["nace"]["department"])
+# {'type': 'choice', 'choice': 'billing', 'confidence': 0.97, 'probabilities': {...}}
+```
+
+Each document is one request carrying every question, with up to `max_workers` requests (default 3) at once.
+Documents that can't be classified are returned in `failed_documents` with the reason in
+`meta["classification_error"]`.
+
+### Evaluate RAG answers
+
+```python
+from haystack_integrations.components.evaluators.nace import NaceFaithfulnessEvaluator
+
+evaluator = NaceFaithfulnessEvaluator()
+result = evaluator.run(
+    questions=["Who won the race?"],
+    contexts=[["Ada won the 2026 city race."]],
+    predicted_answers=["Ada won the race."],
+)
+print(result["score"], result["individual_scores"])
+```
+
+Both evaluators take the same inputs and return the same outputs (`score`, `individual_scores`, `results`, `meta`) as
+Haystack's built-in LLM evaluators. Each item is one Drex request, and its score is the probability that the answer
+is faithful (or that the contexts are relevant).
+
+## Models
+
+The default model is `drex-max-v1.1` (Drex Max v1.1), which reads text, JSON and images. The default moves to the
+newest Drex model in package releases, and a new model can shift probabilities, so **pin `model=` in production** if
+your pipeline relies on thresholds.
+
+`drex-v2.0` reads text only and bills fewer tokens on short texts: for a short email with three questions, we
+measured 74 input tokens on `drex-v2.0` and 165 on `drex-max-v1.1` (2026-10-29). See
+[Drex's limits](https://console.nace.ai/docs/drex/reference/limits) for questions per request and state sizes.
+Any model ID is sent as given, so new Drex models work without a new release of this package.
+
+## Images
+
+The router and the evaluators take images: `ImageContent`, `ByteStream`, or files uploaded to Drex with nace-sdk
+(`client.documents.upload(...)`). Prompts refer to them as "Image 1", "Image 2" and so on.
+
+```python
+from haystack.dataclasses import ImageContent
+
+router = NaceTextRouter(
+    labels={"invoice": "A bill or invoice", "receipt": "A proof of payment", "other": None},
+    instructions="What kind of document is Image 1?",
+)
+router.run(text="A customer attached a scan.", images=[ImageContent.from_file_path("scan.jpg")])
+```
+
+Images too big to send in one request are shrunk automatically, with a logged warning. Drex Max reads images at about
+1.6 megapixels (1,638,400 pixels), and an image is never shrunk below about 1 megapixel: if the text leaves too little
+room for the images, you get a clear error instead of a blurry image. Photos are turned upright using their EXIF
+orientation before shrinking. Shrinking needs `pip install pillow`; to skip it, downscale earlier with
+`ImageFileToImageContent(size=(2048, 2048))` or `PDFToImageContent(size=(2048, 2048))`. PDFs must be converted to
+images first.
+
+## Other backends
+
+Set `api_base_url` to use Drex through [OpenRouter](https://openrouter.ai) (`https://openrouter.ai/api/v1`, with
+model IDs such as `nace-ai/drex-max`) or another TypeSafe-compatible host. OpenRouter takes inline images only.
+
+## Errors and retries
+
+Requests that hit a rate limit (429) or an overloaded model (529) are retried, waiting as long as Drex asks. Other
+errors are raised as nace-sdk's error classes with a readable message, for example:
+
+```text
+422 from Drex: the request is invalid
+  questions.department.criteria: must have at least 2 labels
+```
+
+## Switching from TypeSafe
+
+The router and classifier take the same parameters and produce the same outputs as `TypeSafeTextRouter` and
+`TypeSafeDocumentClassifier`.
+
+In Python code that uses Jev's default model, change the import, the class name and the API key:
+
+```diff
+-from haystack_integrations.components.routers.typesafe import TypeSafeTextRouter
++from haystack_integrations.components.routers.nace import NaceTextRouter
+
+-router = TypeSafeTextRouter(labels=..., min_confidence=0.6)
++router = NaceTextRouter(labels=..., min_confidence=0.6)
+```
+
+```diff
+-export TYPESAFE_API_KEY=...
++export NACE_API_KEY=...
+```
+
+The classifier writes answers to `meta["nace"]` by default. If your code reads `meta["typesafe"]` (in a filter or a
+`MetadataRouter` rule, for example), pass `metadata_field="typesafe"` to keep the old key.
+
+Questions built with `typesafe_sdk` objects (`Choice`, `Score`, `Noul`) work as they are; you can switch them to
+`nace_sdk`'s classes of the same names when convenient. Where your code catches `TypeSafeError`, catch
+`nace_sdk.NaceError` instead.
+
+In a saved YAML pipeline, make three edits per component:
+
+```diff
+-    type: haystack_integrations.components.routers.typesafe.text_router.TypeSafeTextRouter
++    type: haystack_integrations.components.routers.nace.text_router.NaceTextRouter
+...
+-        - TYPESAFE_API_KEY
++        - NACE_API_KEY
+...
+-      model: jev-latest
++      model: drex-max-v1.1
+```
+
+The classifier's type becomes `haystack_integrations.components.classifiers.nace.document_classifier.NaceDocumentClassifier`.
+A saved pipeline keeps `metadata_field: typesafe`, so answers stay where your filters read them. Model names aren't
+translated: Drex rejects `jev-latest` with a message listing its models.
+
+Drex's own guide covers the API side: [Migrate from TypeSafe](https://console.nace.ai/docs/drex/guides/migrate-from-typesafe).
+
+## License
+
+Apache-2.0