mombeu 0.1.0__tar.gz

mombeu-0.1.0/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.

mombeu-0.1.0/PKG-INFO

@@ -0,0 +1,318 @@
+Metadata-Version: 2.4
+Name: mombeu
+Version: 0.1.0
+Summary: OpenAI Python SDK wrapper with local LLM continuation
+License: MIT
+Keywords: openai,llm,wrapper,huggingface,continuation
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=1.0.0
+Requires-Dist: transformers>=4.40.0
+Requires-Dist: huggingface_hub>=0.23.0
+Requires-Dist: torch>=2.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.12.0; extra == "dev"
+Requires-Dist: black>=24.0.0; extra == "dev"
+Requires-Dist: ruff>=0.4.0; extra == "dev"
+Dynamic: license-file
+
+# Mombeu
+
+**Capa de inserción narrativa cultural guaraní para LLMs**
+
+> *Como cuando el abuelo responde algo cotidiano y al final dice "eso me recuerda..." — Mombeu agrega un fragmento de cosmovisión guaraní a la salida de cualquier LLM, sin que el usuario lo pida.*
+
+---
+
+## ¿Qué es Mombeu?
+
+Mombeu es una capa complementaria que se conecta a cualquier LLM existente. No es un chatbot ni un traductor — es un modelo pequeño especializado que intercepta respuestas generales y agrega al final un cierre narrativo basado en la cosmovisión guaraní, cuando la temática lo permite.
+
+El usuario sigue usando el LLM de siempre. Mombeu trabaja en el fondo.
+
+```
+Usuario pregunta
+        ↓
+LLM grande responde  (GPT, Claude, Llama, etc.)
+        ↓
+Mombeu — encoder de pertinencia temática
+    score > umbral?
+    │
+    ├── No → respuesta sin modificar
+    │
+    └── Sí → genera cierre narrativo
+              basado en Ñande Ypykuéra + grafo
+        ↓
+Respuesta enriquecida al usuario
+```
+
+### Ejemplo
+
+**Sin Mombeu:**
+> Los truenos ocurren cuando el aire caliente sube rápidamente y genera descargas eléctricas en las nubes.
+
+**Con Mombeu:**
+> Los truenos ocurren cuando el aire caliente sube rápidamente y genera descargas eléctricas en las nubes. Eso me recuerda a **Tupã**, cuya voz retumba en el cielo — para el pueblo guaraní, el trueno no era un fenómeno sino la presencia del creador.
+
+---
+
+## Motivación
+
+Paraguay es el único país de América donde una lengua indígena —el guaraní— es co-oficial y hablada por la mayoría de la población. Sin embargo, los LLMs actuales ignoran casi completamente su cultura y cosmovisión.
+
+Mombeu propone que cada respuesta sea una oportunidad de transmitir memoria colectiva — no como lección, sino como la tradición oral guaraní lo hace naturalmente: por evocación, por asociación, sin pedirlo.
+
+---
+
+## Arquitectura
+
+Mombeu tiene tres componentes internos:
+
+### 1. Encoder de pertinencia temática
+
+Modelo de clasificación liviano que decide si una respuesta merece un cierre cultural. No genera texto — solo responde si insertar o no.
+
+```python
+# Modelo base
+"intfloat/multilingual-e5-small"
+
+# Escala de pertinencia
+naturaleza, clima, cosmos        → alta
+emociones, familia, comunidad    → alta
+alimentación, tierra, animales   → media
+historia, sociedad, identidad    → media
+tareas técnicas, tecnología      → baja o nula
+```
+
+### 2. Modelo DPO de inserción narrativa
+
+Modelo generativo pequeño fine-tuneado con LoRA + DPO que genera el cierre narrativo cuando el encoder lo habilita. Entrenado con pares chosen/rejected anotados por expertos en cosmovisión guaraní.
+
+### 3. Grafo de conocimiento mitológico
+
+Extraído del texto *Ñande Ypykuéra*. Captura personajes, relaciones y atributos de la cosmovisión guaraní. Cumple dos funciones:
+- Validación automática de cierres antes de anotación humana
+- Balanceo de personajes en el dataset
+
+---
+
+## Instalación
+
+```bash
+pip install mombeu
+```
+
+No se descarga ningún modelo al instalar. El modelo se elige y descarga explícitamente con `mombeu.init()`.
+
+---
+
+## Uso rápido
+
+```python
+import mombeu
+
+# 1. Inicializar una vez — descarga y cachea el modelo en el primer uso
+mombeu.init(model="mombeu-v1", hf_token="hf_...")
+
+# 2. Usar exactamente igual que openai.OpenAI
+client = mombeu.OpenAI(api_key="sk-...")
+
+response = client.chat.completions.create(
+    model="gpt-4o",
+    messages=[{"role": "user", "content": "¿Qué son los truenos?"}],
+)
+
+print(response.choices[0].message.content)
+# → Respuesta de OpenAI ... seguida del cierre narrativo guaraní
+```
+
+---
+
+## Streaming
+
+```python
+mombeu.init(model="mombeu-v1", hf_token="hf_...")
+client = mombeu.OpenAI(api_key="sk-...")
+
+for chunk in client.chat.completions.create(
+    model="gpt-4o",
+    messages=[{"role": "user", "content": "¿Qué son los truenos?"}],
+    stream=True,
+):
+    delta = chunk.choices[0].delta.content or ""
+    print(delta, end="", flush=True)
+```
+
+**Comportamiento del streaming:**
+- Todos los chunks de OpenAI se emiten en tiempo real, sin cambios.
+- Al terminar el stream, el modelo local genera el cierre narrativo.
+- El cierre se emite como un único chunk final.
+- Se agrega un chunk de stop para terminar el stream correctamente.
+
+---
+
+## Modelos disponibles
+
+```python
+import mombeu
+
+print(mombeu.list_models())
+# ['mombeu-fast', 'mombeu-v1', 'mombeu-v2']
+```
+
+| Slug           | Descripción                                  |
+|----------------|----------------------------------------------|
+| `mombeu-v1`    | Modelo de inserción narrativa general        |
+| `mombeu-v2`    | Mayor precisión cultural, más pesado         |
+| `mombeu-fast`  | Liviano, menor latencia                      |
+
+---
+
+## API reference
+
+### `mombeu.init(model, hf_token)`
+
+Inicializa Mombeu. Debe llamarse antes de crear un cliente.
+
+| Parámetro  | Tipo  | Descripción                                                    |
+|------------|-------|----------------------------------------------------------------|
+| `model`    | `str` | Slug del modelo. Ver `mombeu.list_models()`.                   |
+| `hf_token` | `str` | Token de HuggingFace con acceso de lectura al repositorio.     |
+
+Lanza `ValueError` si el slug no es soportado o el token es inválido.  
+Lanza `RuntimeError` si el pipeline del modelo falla al cargar.
+
+---
+
+### `mombeu.OpenAI(**kwargs)`
+
+Reemplazo directo de `openai.OpenAI`. Acepta los mismos argumentos de constructor.
+
+Todos los atributos no relacionados con `chat.completions` se delegan transparentemente a la instancia subyacente de `openai.OpenAI` (e.g. `embeddings`, `images`, `audio`).
+
+---
+
+### `mombeu.list_models() → list[str]`
+
+Retorna la lista ordenada de slugs de modelos soportados.
+
+---
+
+### `mombeu.current_model() → str | None`
+
+Retorna el slug del modelo actualmente cargado, o `None` si aún no se inicializó.
+
+---
+
+### `mombeu.reset()`
+
+Limpia todo el estado en memoria (modelo, pipeline). Útil para testing o cambio de modelo.
+
+---
+
+## Dataset
+
+El dataset de preferencias es la contribución central del proyecto — el primer corpus de pares chosen/rejected basado en cosmovisión guaraní.
+
+| Campo | Descripción |
+|---|---|
+| `prompt` | Respuesta del LLM grande |
+| `chosen` | Cierre mitológico correcto y naturalmente integrado |
+| `rejected` | Cierre incorrecto, forzado o culturalmente inexacto |
+
+Todos los cierres provienen exclusivamente del texto *Ñande Ypykuéra*. El modelo no inventa ni mezcla fuentes — esto garantiza coherencia cultural y trazabilidad completa.
+
+---
+
+## Sobre el riesgo de exotización
+
+Mombeu toma cuatro medidas explícitas para evitar folklorizar o estereotipar la cultura guaraní:
+
+1. **Fuente única.** Solo *Ñande Ypykuéra* — sin mezcla de fuentes ni referencias de internet.
+2. **Validación experta.** Anotadores con conocimiento especializado en cosmovisión guaraní.
+3. **Grafo como validador.** Rechaza automáticamente cierres que contradicen el texto fuente.
+4. **Naturalidad como criterio.** Un cierre correcto pero forzado es rechazado. El objetivo es que suene como el abuelo, no como un libro de folklore.
+
+---
+
+## Evaluación
+
+Se comparan cuatro condiciones con evaluación humana:
+
+| Condición         | Descripción                                             |
+|-------------------|---------------------------------------------------------|
+| Baseline          | LLM grande sin capa cultural                            |
+| Prompt engineering| Instrucción en el sistema para agregar cierres          |
+| SFT               | Fine-tuning con ejemplos del formato                    |
+| DPO               | Alineamiento con preferencias culturales                |
+
+Dimensiones evaluadas: naturalidad, memorabilidad, percepción cultural, intrusividad.
+
+---
+
+## Stack tecnológico
+
+| Componente              | Herramienta                          |
+|-------------------------|--------------------------------------|
+| Encoder de pertinencia  | multilingual-e5-small + fine-tuning  |
+| Modelo generativo       | LLaMA 3.1 8B o Mistral 7B            |
+| Fine-tuning             | LoRA + SFT                           |
+| Alineamiento            | DPO                                  |
+| Grafo                   | NetworkX                             |
+| Wrapper Python          | openai SDK + transformers            |
+| Demo                    | Gradio en HuggingFace Spaces         |
+
+---
+
+## Desarrollo
+
+```bash
+# Instalar con dependencias de desarrollo
+pip install -e ".[dev]"
+
+# Correr tests
+pytest tests/ -v
+
+# Formatear
+black mombeu/ tests/
+
+# Lint
+ruff check mombeu/ tests/
+```
+
+---
+
+## Notas técnicas
+
+- El modelo se cachea en `~/.cache/huggingface/` tras la primera descarga.
+- Se usa GPU automáticamente si CUDA está disponible; si no, cae a CPU.
+- La generación del cierre agrega latencia proporcional a `max_new_tokens` (default: 150).
+- Si la generación falla por cualquier motivo, se retorna la respuesta original de OpenAI sin modificar, con un warning.
+
+---
+
+## Aliados institucionales
+
+- **Secretaría de Políticas Lingüísticas (SPL)** — validación cultural y anotadores expertos
+- **Ateneo de Lengua y Cultura Guaraní** — validación mitológica
+- **SomosNLP** — plataforma del hackathon
+
+---
+
+## ODS vinculados
+
+- **ODS 4** — Educación de calidad
+- **ODS 10** — Reducción de desigualdades lingüísticas en IA
+- **ODS 16** — Derechos lingüísticos y acceso cultural
+
+---
+
+## Licencia
+
+MIT
+
+---
+
+> *"Porque cada respuesta es una oportunidad de recordar quiénes somos."*