analyxa 0.1.0__tar.gz

analyxa-0.1.0/.gitignore

@@ -0,0 +1,11 @@
+.env
+.venv/
+__pycache__/
+*.pyc
+.pytest_cache/
+*.egg-info/
+dist/
+build/
+.memoria.json
+.memoria-sessions.json
+node_modules/

analyxa-0.1.0/CLAUDE.md

@@ -0,0 +1,131 @@
+# ANALYXA — Contexto para Claude
+
+> Este archivo es la puerta de entrada al proyecto.
+> Cualquier sesión de Claude que trabaje en este proyecto debe leer este archivo primero.
+> Última actualización: 2026-03-12
+
+---
+
+## ¿Qué es Analyxa?
+
+Analyxa es un motor de extracción multi-dimensional que convierte conversaciones de agentes de IA en inteligencia estructurada, indexada y consultable. Toma una conversación opaca y la descompone en N dimensiones configurables (sentimiento, intensidad, temas, riesgo, progreso, etc.) almacenadas como vectores semánticos de 1,536 dimensiones.
+
+**Dominio:** analyxa.ai
+**Paquete PyPI:** analyxa
+**Licencia:** Apache 2.0 (motor) + Propietario (schemas premium, cloud)
+**Origen:** Genericización de MNEMOS, el motor de análisis clínico de Ishara (plataforma terapéutica IA)
+
+---
+
+## Arquitectura
+
+```
+Conversación → [Source] → [Analyzer] → [LLM + Schema YAML] → [JSON N campos + Vector 1536D] → [Sink]
+```
+
+**Sources:** Redis, archivos, API REST
+**Sinks:** Qdrant, JSON, stdout
+**LLM:** Claude Sonnet (primario), OpenAI GPT-4o (compatible)
+**Embeddings:** OpenAI text-embedding-3-small (1536D)
+**Schemas:** YAML configurables. Universal (10 campos) + Verticales premium
+
+---
+
+## Schema Universal (10 campos base)
+
+| # | Campo | Tipo | Descripción |
+|---|-------|------|-------------|
+| 1 | title | string | Nombre corto de la sesión (5-8 palabras) |
+| 2 | summary | string | Resumen 3-5 oraciones. Se vectoriza. |
+| 3 | sentiment | keyword | positive / negative / mixed / neutral |
+| 4 | sentiment_intensity | keyword | low / medium / high |
+| 5 | topics | keyword[] | Temas reales detectados |
+| 6 | session_outcome | keyword | resolved / unresolved / escalated / abandoned |
+| 7 | user_intent | string | Lo que el usuario realmente buscaba |
+| 8 | risk_signals | keyword[] | Señales de alerta |
+| 9 | key_entities | keyword[] | Personas, productos, fechas mencionadas |
+| 10 | action_items | string[] | Compromisos o siguientes pasos |
+
+---
+
+## Verticales Premium
+
+- **Soporte:** +6 campos (satisfaction_prediction, issue_category, escalation_needed, resolution_quality, first_contact_resolution, customer_effort_score)
+- **Ventas:** +6 campos (buying_stage, objections, budget_signals, decision_urgency, competitive_mentions, next_best_action)
+- **Coaching:** +8 campos (emotional_valence, emotional_intensity, progress_indicators, behavioral_patterns, growth_markers, therapeutic_momentum, adaptation_level, coping_strategies)
+
+---
+
+## Stack Tecnológico
+
+| Componente | Tecnología |
+|-----------|-----------|
+| LLM primario | Claude Sonnet (Anthropic) |
+| Embeddings | OpenAI text-embedding-3-small |
+| Conversaciones | Redis 7 (Docker) |
+| Vectores | Qdrant (Docker) |
+| Lenguaje | Python 3.10+ |
+| CLI | Click |
+| VPS | Contabo 66.94.117.83, Ubuntu 22.04, 8GB RAM |
+
+---
+
+## Estructura del Proyecto
+
+```
+/opt/analyxa/
+├── memory/              # Artefactos MEMORIA v3.0
+├── src/analyxa/         # Código fuente
+│   ├── analyzer.py      # Orquestador principal
+│   ├── schema.py        # Carga y valida schemas YAML
+│   ├── prompt_builder.py
+│   ├── llm_client.py
+│   ├── embeddings.py
+│   ├── config.py
+│   ├── cli.py
+│   ├── batch.py
+│   ├── sources/         # redis_source.py, file_source.py
+│   ├── sinks/           # qdrant_sink.py, json_sink.py, stdout_sink.py
+│   └── schemas/         # universal.yaml, support.yaml, sales.yaml, coaching.yaml
+├── tests/
+├── examples/
+├── docs/
+├── docker/
+├── .env
+└── pyproject.toml
+```
+
+---
+
+## Sistema de Memoria
+
+Protocolo MEMORIA v3.0. Los archivos viven en `memory/`:
+
+| Archivo | Propósito | Actualización |
+|---------|-----------|---------------|
+| CLAUDE.md | Puerta de entrada | Cuando cambian fundamentos |
+| ANALYXA-STATE.md | Estado actual | Cada IF completada |
+| ANALYXA-BLUEPRINT.md | Plan de fabricación | Cada IF completada |
+| ANALYXA-CHANGELOG.md | Log de cambios | Cada IF completada |
+| ANALYXA-DECISIONS.md | Decisiones (ADR) | Cada decisión importante |
+
+### Protocolo de sesión
+
+**Al iniciar:** Leer ANALYXA-STATE.md → verificar consistencia (Gate)
+**Durante:** Diseñar IF según ANALYXA-BLUEPRINT.md
+**Al cerrar:** Verificar que fabricante actualizó memoria
+
+---
+
+## Modelo de Negocio
+
+1. **GitHub Open Source** → Adopción de developers
+2. **Product Hunt + Content** → Visibilidad
+3. **Fiverr + Servicios directos** → Ingresos inmediatos ($297-$997)
+4. **Cloud API SaaS** → Escala ($49-$199/mes)
+
+---
+
+## Estado Actual
+
+> **Ver ANALYXA-STATE.md para el estado detallado actualizado.**

analyxa-0.1.0/LICENSE

@@ -0,0 +1,191 @@
+
+                                 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 the 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 the 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 any 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
+
+   Copyright 2026 Next AI Ecosystem
+
+   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.

analyxa-0.1.0/PKG-INFO

@@ -0,0 +1,242 @@
+Metadata-Version: 2.4
+Name: analyxa
+Version: 0.1.0
+Summary: Multi-dimensional extraction engine for AI conversations
+Author-email: Next AI Ecosystem <nextaiecosystem@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://analyxa.ai
+Project-URL: Repository, https://github.com/next-ai-ecosystem/analyxa
+Project-URL: Documentation, https://analyxa.ai/docs
+Keywords: ai,conversations,analytics,llm,extraction,nlp
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: anthropic>=0.40.0
+Requires-Dist: openai>=1.0.0
+Requires-Dist: click>=8.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: redis>=5.0.0
+Requires-Dist: qdrant-client>=1.7.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Dynamic: license-file
+
+# Analyxa
+
+**Multi-dimensional extraction engine for AI conversations.**
+
+Analyxa takes opaque conversations between users and AI agents and decomposes them into N configurable dimensions — sentiment, intensity, topics, risk signals, intent, entities, and more — stored as 1,536-dimensional semantic vectors.
+
+[![PyPI version](https://badge.fury.io/py/analyxa.svg)](https://pypi.org/project/analyxa/)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+
+---
+
+## What it does
+
+```
+Conversation → Analyxa → Structured JSON (N fields) + Semantic Vector (1536D)
+```
+
+One conversation in, structured intelligence out:
+
+- **10 universal fields** extracted from any conversation (sentiment, topics, risk signals, intent, entities, action items...)
+- **Vertical schemas** add domain-specific fields: support (16), sales (16), coaching (18)
+- **Semantic vectors** enable similarity search across thousands of conversations
+- **Pipeline ready**: Redis queue → Analyxa → Qdrant vector DB
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install analyxa
+```
+
+### Python API
+
+```python
+from analyxa import analyze
+
+result = analyze(
+    "User: I was charged twice for my subscription.\n"
+    "Agent: I see the duplicate charge. Processing a refund now.\n"
+    "User: Thanks, but please make sure it doesn't happen again.",
+    schema="support"
+)
+
+print(result.fields["sentiment"])           # "negative"
+print(result.fields["satisfaction_prediction"])  # "dissatisfied"
+print(result.fields["issue_category"])      # "billing"
+print(result.fields["risk_signals"])        # ["frustration", "repeat_contact"]
+```
+
+### CLI
+
+```bash
+# Analyze a conversation file
+analyxa analyze conversation.txt --schema support --output result.json
+
+# List available schemas
+analyxa schemas list
+
+# Show schema fields
+analyxa schemas show support
+
+# Batch analyze a directory
+analyxa batch ./conversations/ --schema universal --output-dir ./results/
+```
+
+### Environment Setup
+
+Create a `.env` file:
+
+```bash
+ANTHROPIC_API_KEY=sk-ant-...      # Required for analysis
+OPENAI_API_KEY=sk-...              # Optional, for embeddings
+ANALYXA_PROVIDER=anthropic         # or "openai"
+ANALYXA_SCHEMA=universal           # Default schema
+```
+
+## Schemas
+
+Analyxa uses YAML schemas to define what to extract. Schemas are hierarchical — vertical schemas inherit all universal fields.
+
+| Schema | Fields | Description |
+|--------|--------|-------------|
+| **universal** | 10 | Base fields for any conversation |
+| **support** | 16 | Customer support (+satisfaction, issue category, effort score...) |
+| **sales** | 16 | Sales conversations (+buying stage, objections, budget signals...) |
+| **coaching** | 18 | Coaching/therapeutic (+emotional valence, behavioral patterns, coping strategies...) |
+
+### Universal Fields (included in all schemas)
+
+| Field | Type | Description |
+|-------|------|-------------|
+| title | string | Descriptive session name |
+| summary | string | 3-5 sentence summary (vectorized for search) |
+| sentiment | keyword | User sentiment: positive, negative, mixed, neutral |
+| sentiment_intensity | keyword | low, medium, high |
+| topics | keyword_array | Specific topics discussed |
+| session_outcome | keyword | resolved, unresolved, escalated, abandoned |
+| user_intent | string | What the user really needed |
+| risk_signals | keyword_array | frustration, churn_risk, complaint, urgency... |
+| key_entities | keyword_array | People, products, dates, amounts mentioned |
+| action_items | string_array | Explicit commitments or next steps |
+
+### Custom Schemas
+
+Create your own schema by inheriting from universal:
+
+```yaml
+metadata:
+  name: my_vertical
+  version: "1.0"
+  description: "Custom schema for my use case"
+  inherits: universal
+
+fields:
+  - name: custom_field
+    type: keyword
+    required: true
+    description: "My custom dimension"
+    prompt_hint: "Instructions for the LLM on how to extract this field"
+    allowed_values: [option_a, option_b, option_c]
+```
+
+## Production Pipeline
+
+### Redis → Analyxa → Qdrant
+
+```bash
+# Start infrastructure
+cd docker && docker compose up -d
+
+# Push conversations to Redis queue
+analyxa redis push conversation.txt --schema support
+
+# Process all pending conversations
+analyxa redis process
+
+# Search by semantic similarity
+analyxa search "frustrated customer with billing issue" --limit 5
+```
+
+### Python Pipeline
+
+```python
+from analyxa.sources.redis_source import RedisSource
+from analyxa.sinks.qdrant_sink import QdrantSink
+from analyxa.batch import batch_analyze_from_redis
+
+# Process Redis queue → Qdrant
+result = batch_analyze_from_redis()
+print(f"Processed: {result.successful}/{result.total}")
+
+# Search similar conversations
+sink = QdrantSink()
+similar = sink.search_similar(query_embedding, limit=10, filters={"sentiment": "negative"})
+```
+
+## Configuration
+
+All settings via environment variables or `.env` file:
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| ANTHROPIC_API_KEY | — | Anthropic API key |
+| OPENAI_API_KEY | — | OpenAI API key (for embeddings) |
+| ANALYXA_PROVIDER | anthropic | LLM provider: anthropic or openai |
+| ANALYXA_MODEL | (provider default) | Model override |
+| ANALYXA_SCHEMA | universal | Default schema |
+| ANALYXA_EMBEDDINGS | true | Enable/disable embeddings |
+| REDIS_URL | redis://localhost:6379 | Redis connection |
+| QDRANT_URL | http://localhost:6333 | Qdrant connection |
+
+## Architecture
+
+```
+src/analyxa/
+├── analyzer.py          # Pipeline orchestrator
+├── schema.py            # YAML schema loader with inheritance
+├── prompt_builder.py    # Dynamic prompt generation from schemas
+├── llm_client.py        # Multi-provider LLM abstraction
+├── embeddings.py        # Semantic vector generation (1536D)
+├── config.py            # Centralized configuration
+├── cli.py               # Click CLI
+├── batch.py             # Batch processing
+├── sources/
+│   ├── file_source.py   # Read from files
+│   └── redis_source.py  # Read from Redis queue
+├── sinks/
+│   ├── json_sink.py     # Write to JSON files
+│   ├── stdout_sink.py   # Print to terminal
+│   └── qdrant_sink.py   # Store in Qdrant
+└── schemas/
+    ├── universal.yaml   # 10 base fields
+    ├── support.yaml     # +6 support fields
+    ├── sales.yaml       # +6 sales fields
+    └── coaching.yaml    # +8 coaching fields
+```
+
+## License
+
+Apache 2.0 — see [LICENSE](LICENSE) for details.
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+---
+
+Built by [Next AI Ecosystem](https://analyxa.ai)