fast-universal-sentence-encoder 0.1.0__tar.gz

fast_universal_sentence_encoder-0.1.0/.gitattributes

@@ -0,0 +1,3 @@
+# Large model files are stored with Git LFS
+usem3/resources/*.npz filter=lfs diff=lfs merge=lfs -text
+usem3/resources/*.model filter=lfs diff=lfs merge=lfs -text

fast_universal_sentence_encoder-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,70 @@
+name: build-and-publish
+
+"on":
+  push:
+    tags:
+      - "v*"
+  workflow_dispatch:
+
+jobs:
+  test:
+    name: test (${{ matrix.os }})
+    strategy:
+      fail-fast: false
+      matrix:
+        # amd64, arm64, Windows x64, macOS Apple Silicon
+        os:
+          - ubuntu-latest          # linux amd64
+          - ubuntu-24.04-arm       # linux arm64
+          - windows-latest         # windows amd64
+          - macos-latest           # macOS arm64 (Apple Silicon)
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install package
+        run: pip install .
+      - name: Run tests
+        run: python tests/test_embedder.py
+
+  build:
+    name: build sdist + wheel
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install build tooling
+        run: pip install build
+      - name: Build distributions
+        run: python -m build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    name: publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_TOKEN }}
+          packages-dir: dist/

fast_universal_sentence_encoder-0.1.0/.gitignore

@@ -0,0 +1,6 @@
+__pycache__/
+*.pyc
+*.egg-info/
+dist/
+build/
+.venv/

fast_universal_sentence_encoder-0.1.0/LICENSE

@@ -0,0 +1,217 @@
+# Apache License, Version 2.0
+#
+# Copyright 2026 cnmoro
+#
+# 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.
+
+                                 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.

fast_universal_sentence_encoder-0.1.0/PKG-INFO

@@ -0,0 +1,98 @@
+Metadata-Version: 2.4
+Name: fast-universal-sentence-encoder
+Version: 0.1.0
+Summary: Fast, dependency-light Google USE multilingual v3 sentence embeddings (pure numpy, no C++ deps)
+Author: cnmoro
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cnmoro/fast-universal-sentence-encoder-3
+Keywords: embeddings,sentence-transformers,universal-sentence-encoder,pt-br,multilingual
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.22
+Provides-Extra: fast
+Requires-Dist: threadpoolctl>=3.1; extra == "fast"
+Dynamic: license-file
+
+# fast-universal-sentence-encoder
+
+Fast, dependency-light implementation of **Google's universal-sentence-encoder-multilingual v3**.
+Same SentencePiece (128k) vocabulary, same DAN + CNN n-gram encoder, same 512-dim L2-normalized output —
+reproducing the original quantized ONNX at **cosine ≥ 0.99** — with **no C++ dependencies**:
+a pure-Python port of the normalizer + unigram Viterbi and a pure numpy forward pass.
+
+## Install
+
+```bash
+pip install fast-universal-sentence-encoder
+```
+
+Only needs `numpy`. (Optionally `threadpoolctl` via `pip install "fast-universal-sentence-encoder[fast]"`
+for faster small-batch matmuls.)
+
+## Quickstart
+
+```python
+from usem3 import USE
+
+use = USE()
+vec = use.encode("o gato preto correu pelo jardim")   # (512,) L2-normalized
+vecs = use.encode(["a menina lê um livro", "investir em renda fixa é seguro"])  # (2, 512)
+
+use.similarity("gato preto correu", "o gato preto correu pelo jardim")
+# 0.53
+```
+
+> The package is distributed as `fast-universal-sentence-encoder`; the import
+> name is `usem3`.
+
+### Number denoising
+
+USE embeddings are sensitive to number tokens: two sentences that differ only in
+their quantities get cosine ~0.6-0.8 instead of ~1.0, which can hurt semantic
+search when the same content appears with different numbers. Normalizing numbers
+to a placeholder fixes this and is a no-op on clean text:
+
+```python
+use = USE(denoise=True)
+use.similarity("O projeto custou 1 milhão", "O projeto custou 5 milhões")
+# 0.97 (vs 0.80 without denoise)
+```
+
+`denoise=True` replaces number tokens (digits, separators, `%`) with a fixed
+placeholder before embedding. It is OFF by default because it slightly changes
+the embeddings; enable it when your corpus mixes quantities. See
+`examples/bench_numbers.py` for the evaluation.
+
+## Model
+
+- **Architecture**: deep averaging network (DAN) with CNN n-gram features (orders 2/3/5)
+  followed by a residual DNN, trained multi-task across 16 languages.
+- **Output**: 512-dim, L2-normalized sentence embeddings.
+- **Languages**: ar, de, en, es, fr, it, ja, ko, nl, pl, pt, ru, th, tr, zh, zh-TW.
+- **Size**: the package is ~33 MB (the embedding table is stored 6-bit-quantized
+  per chunk, which halves it with no measurable quality loss).
+
+## Files
+
+```
+usem3/
+├── resources/
+│   ├── sp.model        # sentencepiece model (128k vocab)
+│   └── weights.npz     # compact 6-bit-quantized weights
+├── backends/numpy.py   # pure numpy forward pass
+├── pure_tokenizer.py   # pure-Python sentencepiece port (normalizer + unigram)
+├── preprocess.py       # optional number denoising
+├── embedder.py         # USE front-end
+└── tokenizer.py        # tokenizer front-end (wraps pure_tokenizer)
+scripts/build_weights.py  # regenerate weights.npz from float32 weights
+```
+
+## License
+
+Apache-2.0. The underlying model is Google's
+[universal-sentence-encoder-multilingual-3](https://tfhub.dev/google/universal-sentence-encoder-multilingual/3)
+(Apache-2.0).

fast_universal_sentence_encoder-0.1.0/README.md

@@ -0,0 +1,79 @@
+# fast-universal-sentence-encoder
+
+Fast, dependency-light implementation of **Google's universal-sentence-encoder-multilingual v3**.
+Same SentencePiece (128k) vocabulary, same DAN + CNN n-gram encoder, same 512-dim L2-normalized output —
+reproducing the original quantized ONNX at **cosine ≥ 0.99** — with **no C++ dependencies**:
+a pure-Python port of the normalizer + unigram Viterbi and a pure numpy forward pass.
+
+## Install
+
+```bash
+pip install fast-universal-sentence-encoder
+```
+
+Only needs `numpy`. (Optionally `threadpoolctl` via `pip install "fast-universal-sentence-encoder[fast]"`
+for faster small-batch matmuls.)
+
+## Quickstart
+
+```python
+from usem3 import USE
+
+use = USE()
+vec = use.encode("o gato preto correu pelo jardim")   # (512,) L2-normalized
+vecs = use.encode(["a menina lê um livro", "investir em renda fixa é seguro"])  # (2, 512)
+
+use.similarity("gato preto correu", "o gato preto correu pelo jardim")
+# 0.53
+```
+
+> The package is distributed as `fast-universal-sentence-encoder`; the import
+> name is `usem3`.
+
+### Number denoising
+
+USE embeddings are sensitive to number tokens: two sentences that differ only in
+their quantities get cosine ~0.6-0.8 instead of ~1.0, which can hurt semantic
+search when the same content appears with different numbers. Normalizing numbers
+to a placeholder fixes this and is a no-op on clean text:
+
+```python
+use = USE(denoise=True)
+use.similarity("O projeto custou 1 milhão", "O projeto custou 5 milhões")
+# 0.97 (vs 0.80 without denoise)
+```
+
+`denoise=True` replaces number tokens (digits, separators, `%`) with a fixed
+placeholder before embedding. It is OFF by default because it slightly changes
+the embeddings; enable it when your corpus mixes quantities. See
+`examples/bench_numbers.py` for the evaluation.
+
+## Model
+
+- **Architecture**: deep averaging network (DAN) with CNN n-gram features (orders 2/3/5)
+  followed by a residual DNN, trained multi-task across 16 languages.
+- **Output**: 512-dim, L2-normalized sentence embeddings.
+- **Languages**: ar, de, en, es, fr, it, ja, ko, nl, pl, pt, ru, th, tr, zh, zh-TW.
+- **Size**: the package is ~33 MB (the embedding table is stored 6-bit-quantized
+  per chunk, which halves it with no measurable quality loss).
+
+## Files
+
+```
+usem3/
+├── resources/
+│   ├── sp.model        # sentencepiece model (128k vocab)
+│   └── weights.npz     # compact 6-bit-quantized weights
+├── backends/numpy.py   # pure numpy forward pass
+├── pure_tokenizer.py   # pure-Python sentencepiece port (normalizer + unigram)
+├── preprocess.py       # optional number denoising
+├── embedder.py         # USE front-end
+└── tokenizer.py        # tokenizer front-end (wraps pure_tokenizer)
+scripts/build_weights.py  # regenerate weights.npz from float32 weights
+```
+
+## License
+
+Apache-2.0. The underlying model is Google's
+[universal-sentence-encoder-multilingual-3](https://tfhub.dev/google/universal-sentence-encoder-multilingual/3)
+(Apache-2.0).

fast_universal_sentence_encoder-0.1.0/examples/bench_numbers.py

@@ -0,0 +1,96 @@
+"""Evaluate whether number/noise tokens corrupt USE embeddings, and show the
+value of the denoise preprocessing step.
+
+Findings:
+* USE multilingual v3 is sensitive to number tokens. Two sentences that differ
+  only in their numbers get cosine ~0.6-0.8 instead of ~1.0 (harms semantic
+  search / similarity for the same content with different quantities).
+* Injecting a number clause into 800/2448 ASSIN2 pairs drops STS spearman
+  0.688 -> 0.640 and entailment AUC 0.752 -> 0.735.
+* Normalizing numbers to a placeholder restores cosine 0.72 -> ~0.99 for
+  number-differing paraphrases, and is a no-op on clean text.
+
+Run:  python bench_numbers.py
+"""
+
+import sys
+import os
+import re
+
+import numpy as np
+
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."))
+from usem3 import USE
+
+DENOISE = USE(denoise=True)
+RAW = USE()
+
+
+def cos(a, b):
+    return float(np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)))
+
+
+def main():
+    print("=== 1. Same meaning, numbers swapped -> raw cosine is low ===")
+    pairs = [
+        ("O projeto custou 1 milhão de reais.", "O projeto custou 5 milhões de reais."),
+        ("Em 2010 foram criados 100 novos empregos.", "Em 2020 foram criados 300 novos empregos."),
+        ("A empresa tem 50 funcionários.", "A empresa tem 200 funcionários."),
+        ("O preço subiu 10% este ano.", "O preço subiu 25% este ano."),
+        ("Foram vendidas 1000 unidades.", "Foram vendidas 2500 unidades."),
+        ("A reunião às 10h foi adiada.", "A reunião às 15h foi adiada."),
+    ]
+    raw_c = []
+    den_c = []
+    for a, b in pairs:
+        r = cos(*RAW.encode([a, b]))
+        d = cos(*DENOISE.encode([a, b]))
+        raw_c.append(r)
+        den_c.append(d)
+        print(f"  {a[:32]:<34} raw={r:.3f}  denoised={d:.3f}")
+    print(f"  MEAN                         raw={np.mean(raw_c):.3f}  denoised={np.mean(den_c):.3f}")
+
+    print("\n=== 2. Effect of number-noise at scale (ASSIN2 pt-br) ===")
+    try:
+        from datasets import load_dataset
+        from scipy.stats import spearmanr
+        from sklearn.metrics import roc_auc_score
+
+        ds = load_dataset("nilc-nlp/assin2", split="test")
+        s1, s2 = list(ds["premise"]), list(ds["hypothesis"])
+        y = np.array(ds["entailment_judgment"])
+        g = np.array(ds["relatedness_score"], dtype=float)
+        rng = np.random.default_rng(0)
+        idx = set(rng.choice(len(s1), 800, replace=False))
+
+        def inject(t):
+            return t + " em 2020 foram 12345 unidades no total"
+
+        s1n = [inject(t) if i in idx else t for i, t in enumerate(s1)]
+        s2n = [inject(t) if i in idx else t for i, t in enumerate(s2)]
+
+        def score(e1, e2):
+            pred = np.array([cos(a, b) for a, b in zip(e1, e2)])
+            return spearmanr(pred, g)[0], roc_auc_score(y, pred)
+
+        e1 = RAW.encode(s1)
+        e2 = RAW.encode(s2)
+        rho0, auc0 = score(e1, e2)
+        e1n = RAW.encode(s1n)
+        e2n = RAW.encode(s2n)
+        rho1, auc1 = score(e1n, e2n)
+        print(f"  clean            spearman={rho0:.4f}  auc={auc0:.4f}")
+        print(f"  +number clause   spearman={rho1:.4f}  auc={auc1:.4f}")
+        print(f"  delta            spearman={rho1-rho0:+.4f}  auc={auc1-auc0:+.4f}")
+    except ImportError as e:
+        print("  (skip: need datasets/scipy/scikit-learn:", e, ")")
+
+    print("\n=== 3. Denoise is a no-op on clean text ===")
+    clean = "o gato preto correu pelo jardim e a menina lê um livro na sala."
+    r = cos(*RAW.encode([clean, clean]))
+    d = cos(*DENOISE.encode([clean, clean]))
+    print(f"  clean vs clean: raw={r:.4f} denoised={d:.4f}")
+
+
+if __name__ == "__main__":
+    main()

fast_universal_sentence_encoder-0.1.0/examples/quickstart.py

@@ -0,0 +1,28 @@
+"""Quickstart for usem3."""
+
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), ".."))
+
+from usem3 import USE
+
+use = USE()
+
+texts = [
+    "o gato preto correu pelo jardim",
+    "a menina lê um livro",
+    "investir em renda fixa é seguro",
+    "O desmatamento da Amazônia contribui para o aumento das emissões de carbono.",
+]
+
+vecs = use.encode(texts)
+print("shape:", vecs.shape)  # (4, 512)
+
+sim = use.similarity(texts, texts)
+print("similarity matrix (4x4):")
+for row in sim:
+    print("  " + " ".join(f"{v:.2f}" for v in row))
+
+# single string -> 1-d vector
+print("single:", use.encode("só uma frase").shape)