iatoolkit 0.76.0__tar.gz → 0.108.1__tar.gz

iatoolkit-0.108.1/LICENSE_COMMUNITY.md

@@ -0,0 +1,15 @@
+# IAToolkit Community Edition License
+
+The IAToolkit Community Edition is licensed under the MIT License.
+
+This edition includes the full open-source IAToolkit Core, with the following usage scope:
+
+- Support for **one (1) Company**
+- Unlimited Tools within that Company
+- SQL integration
+- Basic RAG (standard retrieval & embeddings)
+- All Components of the open-source Intelligence Layer and Interfaces
+
+No additional technical limits apply beyond the single-Company constraint.
+
+This edition is designed for learning, prototyping, and single-business deployments.

iatoolkit-0.108.1/PKG-INFO

@@ -0,0 +1,268 @@
+Metadata-Version: 2.4
+Name: iatoolkit
+Version: 0.108.1
+Summary: IAToolkit
+Author: Fernando Libedinsky
+License-Expression: MIT
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: LICENSE_COMMUNITY.md
+Requires-Dist: bcrypt==4.2.1
+Requires-Dist: boto3==1.36.22
+Requires-Dist: botocore==1.36.22
+Requires-Dist: build==1.2.2.post1
+Requires-Dist: click==8.1.8
+Requires-Dist: cryptography==44.0.3
+Requires-Dist: Flask==3.1.0
+Requires-Dist: Flask-Bcrypt==1.0.1
+Requires-Dist: flask-cors==6.0.0
+Requires-Dist: Flask-Injector==0.15.0
+Requires-Dist: Flask-Session==0.8.0
+Requires-Dist: flatbuffers==24.3.25
+Requires-Dist: google-ai-generativelanguage==0.6.15
+Requires-Dist: google-api-core==2.24.1
+Requires-Dist: google-api-python-client==2.161.0
+Requires-Dist: google-auth==2.37.0
+Requires-Dist: google-auth-httplib2==0.2.0
+Requires-Dist: google-auth-oauthlib==1.2.1
+Requires-Dist: google-cloud-core==2.4.1
+Requires-Dist: google-cloud-storage==3.0.0
+Requires-Dist: google-crc32c==1.6.0
+Requires-Dist: google-generativeai==0.8.5
+Requires-Dist: google-resumable-media==2.7.2
+Requires-Dist: googleapis-common-protos==1.66.0
+Requires-Dist: gunicorn==23.0.0
+Requires-Dist: h11==0.14.0
+Requires-Dist: httpcore==1.0.7
+Requires-Dist: httplib2==0.22.0
+Requires-Dist: httptools==0.6.4
+Requires-Dist: httpx==0.28.0
+Requires-Dist: httpx-sse==0.4.0
+Requires-Dist: huggingface-hub==0.31.4
+Requires-Dist: humanfriendly==10.0
+Requires-Dist: idna==3.10
+Requires-Dist: injector==0.22.0
+Requires-Dist: Jinja2==3.1.5
+Requires-Dist: langchain==0.3.19
+Requires-Dist: langchain-core==0.3.35
+Requires-Dist: langchain-text-splitters==0.3.6
+Requires-Dist: markdown2==2.5.3
+Requires-Dist: openai==2.8.1
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: pandas==2.3.1
+Requires-Dist: pgvector==0.3.6
+Requires-Dist: pillow==11.0.0
+Requires-Dist: psutil==7.0.0
+Requires-Dist: psycopg2-binary==2.9.10
+Requires-Dist: PyJWT==2.10.1
+Requires-Dist: PyMuPDF==1.25.0
+Requires-Dist: python-dotenv==1.0.1
+Requires-Dist: pytest==8.3.4
+Requires-Dist: pytest-cov==5.0.0
+Requires-Dist: pytest-mock==3.14.0
+Requires-Dist: python-dateutil==2.9.0.post0
+Requires-Dist: python-docx==1.1.2
+Requires-Dist: pytesseract==0.3.13
+Requires-Dist: pytz==2025.2
+Requires-Dist: PyYAML==6.0.2
+Requires-Dist: redis==5.2.1
+Requires-Dist: regex==2024.11.6
+Requires-Dist: requests==2.32.3
+Requires-Dist: requests-oauthlib==2.0.0
+Requires-Dist: requests-toolbelt==1.0.0
+Requires-Dist: s3transfer==0.11.2
+Requires-Dist: sib-api-v3-sdk==7.6.0
+Requires-Dist: SQLAlchemy==2.0.36
+Requires-Dist: tiktoken==0.8.0
+Requires-Dist: tokenizers==0.21.0
+Requires-Dist: websocket-client==1.8.0
+Requires-Dist: websockets==14.1
+Requires-Dist: Werkzeug==3.1.3
+Requires-Dist: pyjwt[crypto]>=2.8.0
+Dynamic: license-file
+
+# 🧠 IAToolkit — Open-Source Framework for Real-World AI Assistants
+
+Build private, production-grade AI assistants that run entirely inside your environment and speak the language of your business.
+
+IAToolkit is not a demo wrapper or a prompt playground — it is a **full architecture** for implementing intelligent systems that combine LLMs, SQL data, internal documents, tools, workflows, and multi-tenant business logic.
+
+---
+
+## 🚀 Why IAToolkit?
+
+Modern AI development is fragmented: LangChain handles chains, LlamaIndex handles documents, 
+your backend handles SQL, your frontend handles chats, and your devs glue everything together.
+
+**IAToolkit brings all of this into one unified, production-ready framework.**
+
+It focuses on:
+
+- **real-world data** (SQL + documents)
+- **real workflows** (LLM tools + python services)
+- **real multi-tenant architecture** (1 company → many companies)
+- **real constraints** (security, reproducibility, governance)
+- **real deployment** (your servers, your infrastructure)
+
+IAToolkit lets you build the assistant that *your* organization needs — not a generic chatbot.
+
+---
+
+## 🧩 Architecture in a Nutshell
+
+IAToolkit is a structured, layered framework:
+
+Interfaces (Web & API)
+        ↓
+Intelligence Layer (prompts, tools, SQL orchestration, RAG)
+        ↓
+Execution Layer (services, workflows, validation)
+        ↓
+Data Access (SQLAlchemy, connectors)
+        ↓
+Company Modules (company.yaml + custom tools)
+
+### ✔ Interfaces  
+Chat UI, REST API, auth, sessions, JSON/HTML responses.
+
+### ✔ Intelligence Layer  
+Core logic: prompt rendering, SQL orchestration, RAG, LLM tool dispatching.
+
+### ✔ Execution Layer  
+Python services that implement real workflows: querying data, generating reports, retrieving documents, executing business logic.
+
+### ✔ Data Access  
+A clean repository pattern using SQLAlchemy.
+
+### ✔ Company Modules  
+Each company has:
+
+- its own `company.yaml`
+- its own prompts
+- its own tools
+- its own services
+- its own vector store & SQL context
+
+This modularity allows **true multi-tenancy**.
+
+---
+
+## 🔌 Connect to Anything
+
+IAToolkit integrates naturally with:
+
+- **SQL databases** (PostgreSQL, MySQL, SQL Server, etc.)
+- **Document retrieval** (PDF, text, embeddings)
+- **External APIs**
+- **Internal microservices**
+- **Custom Python tools**
+
+It also includes a **production-grade RAG pipeline**, combining:
+
+- embeddings  
+- chunking  
+- hybrid search  
+- SQL queries + document retrieval  
+- tool execution  
+
+Everything orchestrated through the Intelligence Layer.
+
+---
+
+## 🏢 Multi-Tenant Architecture
+
+A single installation of IAToolkit can power assistants for multiple companies, departments, or customers.
+```text
+companies/
+    company_a
+    company_b
+    company_c
+```
+Each Company is fully isolated:
+
+- prompts  
+- tools  
+- credentials  
+- documents  
+- SQL contexts  
+- business rules  
+
+This makes IAToolkit ideal for SaaS products, agencies, consultancies, and organizations with multiple business units.
+
+---
+
+## 🆓 Community Edition vs Enterprise Edition
+
+IAToolkit follows a modern **open-core** model:
+
+### 🟦 Community Edition (MIT License)
+- Full Open-Source Core  
+- SQL + Basic RAG  
+- One Company  
+- Custom Python tools  
+- Self-managed deployment  
+
+Perfect for developers, small teams, single-business use cases, and experimentation.
+
+### 🟥 Enterprise Edition (Commercial License)
+- Unlimited Companies (multi-tenant)  
+- Payment services integration 
+- Enterprise Agent Workflows
+- SSO integration
+- Priority support & continuous updates  
+- Activation via **License Key**  
+
+👉 Licensing information:  
+- [Community Edition (MIT)](LICENSE_COMMUNITY.md)  
+- [Enterprise License](ENTERPRISE_LICENSE.md)
+
+---
+
+## 🧩 Who Is IAToolkit For?
+
+- Companies building internal “ChatGPT for the business”  
+- SaaS products adding AI assistants for multiple customers  
+- AI teams that need reproducible prompts and controlled tools  
+- Developers who want real workflows, not toy demos  
+- Organizations requiring privacy, security, and self-hosting  
+- Teams working with SQL-heavy business logic  
+- Consultancies deploying AI for multiple clients  
+
+---
+
+## ⭐ Key Differentiators
+
+- prioritizes **architecture-first design**, not chains or wrappers  
+- supports **multi-company** out of the box  
+- integrates **SQL, RAG, and tools** into a single intelligence layer  
+- keeps **business logic isolated** inside Company modules  
+- runs entirely **on your own infrastructure**  
+- ships with a **full web chat**, and API.  
+- is built for **production**, not prototypes  
+
+---
+
+## 📚 Documentation
+
+- 🚀 **[Quickstart](docs/quickstart.md)** – Set up your environment and run the project
+- ☁️ **[Deployment Guide](docs/deployment_guide.md)** – Production deployment instructions
+- 🏗️ **[Companies & Components](docs/companies_and_components.md)** – how Company modules work
+- 🧠 **[Programming Guide](docs/programming_guide.md)** – services, intelligence layer, dispatching
+- 🗃️ **[Database Guide](docs/database_guide.md)** – internal schema overview
+- 🌱 **[Foundation Article](https://iatoolkit.com/pages/foundation)** – the “Why” behind the architecture
+- 📘 **[Mini-Project (3 months)](https://iatoolkit.com/pages/mini_project)** – how to deploy a corporate AI assistant
+
+
+---
+
+## 🤝 Contributing
+
+IAToolkit is open-source and community-friendly.  
+PRs, issues, ideas, and feedback are always welcome.
+
+---
+
+## ⭐ Support the Project
+
+If you find IAToolkit useful, please **star the GitHub repo** — it helps visibility and adoption.

{iatoolkit-0.76.0 → iatoolkit-0.108.1}/pyproject.toml

@@ -4,16 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "iatoolkit"
-version = "0.76.0"
+dynamic = ["version", "dependencies"]
 requires-python = ">=3.12"
 description = "IAToolkit"
 readme = "readme.md"
 license = "MIT"
 authors = [{ name = "Fernando Libedinsky" }]
 
-# Si quieres seguir leyendo deps de requirements.txt:
-dynamic = ["dependencies"]
-
 [tool.setuptools]
 package-dir = {"" = "src"}
 
@@ -23,6 +20,7 @@ exclude = ["tests*", "*/tests*"]
 
 
 [tool.setuptools.dynamic]
+version = { attr = "iatoolkit.__version__" }
 dependencies = { file = ["requirements.txt"] }
 
 [tool.setuptools.package-data]

iatoolkit-0.108.1/readme.md

@@ -0,0 +1,184 @@
+# 🧠 IAToolkit — Open-Source Framework for Real-World AI Assistants
+
+Build private, production-grade AI assistants that run entirely inside your environment and speak the language of your business.
+
+IAToolkit is not a demo wrapper or a prompt playground — it is a **full architecture** for implementing intelligent systems that combine LLMs, SQL data, internal documents, tools, workflows, and multi-tenant business logic.
+
+---
+
+## 🚀 Why IAToolkit?
+
+Modern AI development is fragmented: LangChain handles chains, LlamaIndex handles documents, 
+your backend handles SQL, your frontend handles chats, and your devs glue everything together.
+
+**IAToolkit brings all of this into one unified, production-ready framework.**
+
+It focuses on:
+
+- **real-world data** (SQL + documents)
+- **real workflows** (LLM tools + python services)
+- **real multi-tenant architecture** (1 company → many companies)
+- **real constraints** (security, reproducibility, governance)
+- **real deployment** (your servers, your infrastructure)
+
+IAToolkit lets you build the assistant that *your* organization needs — not a generic chatbot.
+
+---
+
+## 🧩 Architecture in a Nutshell
+
+IAToolkit is a structured, layered framework:
+
+Interfaces (Web & API)
+        ↓
+Intelligence Layer (prompts, tools, SQL orchestration, RAG)
+        ↓
+Execution Layer (services, workflows, validation)
+        ↓
+Data Access (SQLAlchemy, connectors)
+        ↓
+Company Modules (company.yaml + custom tools)
+
+### ✔ Interfaces  
+Chat UI, REST API, auth, sessions, JSON/HTML responses.
+
+### ✔ Intelligence Layer  
+Core logic: prompt rendering, SQL orchestration, RAG, LLM tool dispatching.
+
+### ✔ Execution Layer  
+Python services that implement real workflows: querying data, generating reports, retrieving documents, executing business logic.
+
+### ✔ Data Access  
+A clean repository pattern using SQLAlchemy.
+
+### ✔ Company Modules  
+Each company has:
+
+- its own `company.yaml`
+- its own prompts
+- its own tools
+- its own services
+- its own vector store & SQL context
+
+This modularity allows **true multi-tenancy**.
+
+---
+
+## 🔌 Connect to Anything
+
+IAToolkit integrates naturally with:
+
+- **SQL databases** (PostgreSQL, MySQL, SQL Server, etc.)
+- **Document retrieval** (PDF, text, embeddings)
+- **External APIs**
+- **Internal microservices**
+- **Custom Python tools**
+
+It also includes a **production-grade RAG pipeline**, combining:
+
+- embeddings  
+- chunking  
+- hybrid search  
+- SQL queries + document retrieval  
+- tool execution  
+
+Everything orchestrated through the Intelligence Layer.
+
+---
+
+## 🏢 Multi-Tenant Architecture
+
+A single installation of IAToolkit can power assistants for multiple companies, departments, or customers.
+```text
+companies/
+    company_a
+    company_b
+    company_c
+```
+Each Company is fully isolated:
+
+- prompts  
+- tools  
+- credentials  
+- documents  
+- SQL contexts  
+- business rules  
+
+This makes IAToolkit ideal for SaaS products, agencies, consultancies, and organizations with multiple business units.
+
+---
+
+## 🆓 Community Edition vs Enterprise Edition
+
+IAToolkit follows a modern **open-core** model:
+
+### 🟦 Community Edition (MIT License)
+- Full Open-Source Core  
+- SQL + Basic RAG  
+- One Company  
+- Custom Python tools  
+- Self-managed deployment  
+
+Perfect for developers, small teams, single-business use cases, and experimentation.
+
+### 🟥 Enterprise Edition (Commercial License)
+- Unlimited Companies (multi-tenant)  
+- Payment services integration 
+- Enterprise Agent Workflows
+- SSO integration
+- Priority support & continuous updates  
+- Activation via **License Key**  
+
+👉 Licensing information:  
+- [Community Edition (MIT)](LICENSE_COMMUNITY.md)  
+- [Enterprise License](ENTERPRISE_LICENSE.md)
+
+---
+
+## 🧩 Who Is IAToolkit For?
+
+- Companies building internal “ChatGPT for the business”  
+- SaaS products adding AI assistants for multiple customers  
+- AI teams that need reproducible prompts and controlled tools  
+- Developers who want real workflows, not toy demos  
+- Organizations requiring privacy, security, and self-hosting  
+- Teams working with SQL-heavy business logic  
+- Consultancies deploying AI for multiple clients  
+
+---
+
+## ⭐ Key Differentiators
+
+- prioritizes **architecture-first design**, not chains or wrappers  
+- supports **multi-company** out of the box  
+- integrates **SQL, RAG, and tools** into a single intelligence layer  
+- keeps **business logic isolated** inside Company modules  
+- runs entirely **on your own infrastructure**  
+- ships with a **full web chat**, and API.  
+- is built for **production**, not prototypes  
+
+---
+
+## 📚 Documentation
+
+- 🚀 **[Quickstart](docs/quickstart.md)** – Set up your environment and run the project
+- ☁️ **[Deployment Guide](docs/deployment_guide.md)** – Production deployment instructions
+- 🏗️ **[Companies & Components](docs/companies_and_components.md)** – how Company modules work
+- 🧠 **[Programming Guide](docs/programming_guide.md)** – services, intelligence layer, dispatching
+- 🗃️ **[Database Guide](docs/database_guide.md)** – internal schema overview
+- 🌱 **[Foundation Article](https://iatoolkit.com/pages/foundation)** – the “Why” behind the architecture
+- 📘 **[Mini-Project (3 months)](https://iatoolkit.com/pages/mini_project)** – how to deploy a corporate AI assistant
+
+
+---
+
+## 🤝 Contributing
+
+IAToolkit is open-source and community-friendly.  
+PRs, issues, ideas, and feedback are always welcome.
+
+---
+
+## ⭐ Support the Project
+
+If you find IAToolkit useful, please **star the GitHub repo** — it helps visibility and adoption.

iatoolkit-0.76.0/src/iatoolkit.egg-info/requires.txt → iatoolkit-0.108.1/requirements.txt

@@ -38,7 +38,7 @@ langchain==0.3.19
 langchain-core==0.3.35
 langchain-text-splitters==0.3.6
 markdown2==2.5.3
-openai==1.79.0
+openai==2.8.1
 openpyxl==3.1.5
 pandas==2.3.1
 pgvector==0.3.6
@@ -69,3 +69,4 @@ tokenizers==0.21.0
 websocket-client==1.8.0
 websockets==14.1
 Werkzeug==3.1.3
+pyjwt[crypto]>=2.8.0

{iatoolkit-0.76.0 → iatoolkit-0.108.1}/src/iatoolkit/__init__.py

@@ -1,14 +1,17 @@
-"""
-IAToolkit Package
-"""
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+__version__ = "0.108.1"
 
 # Expose main classes and functions at the top level of the package
 
 # main IAToolkit class
-from .iatoolkit import IAToolkit, create_app, current_iatoolkit
+from iatoolkit.core import IAToolkit, create_app, current_iatoolkit
 
 # for registering the client companies
-from .company_registry import register_company
+from .company_registry import register_company, set_company_registry
 from .base_company import BaseCompany
 
 # --- Services ---
@@ -18,12 +21,17 @@ from iatoolkit.services.search_service import SearchService
 from iatoolkit.services.sql_service import SqlService
 from iatoolkit.services.load_documents_service import LoadDocumentsService
 from iatoolkit.infra.call_service import CallServiceClient
+from iatoolkit.services.profile_service import ProfileService
+from iatoolkit.services.mail_service import MailService
+from iatoolkit.repositories.models import Base as OrmModel
+from iatoolkit.base_company import BaseCompany
 
 __all__ = [
     'IAToolkit',
     'create_app',
     'current_iatoolkit',
     'register_company',
+    'set_company_registry',
     'BaseCompany',
     'QueryService',
     'SqlService',
@@ -31,4 +39,8 @@ __all__ = [
     'SearchService',
     'LoadDocumentsService',
     'CallServiceClient',
+    'ProfileService',
+    'MailService',
+    'OrmModel',
+    'BaseCompany',
 ]

iatoolkit-0.108.1/src/iatoolkit/base_company.py

@@ -0,0 +1,21 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+# companies/base_company.py
+from abc import ABC, abstractmethod
+
+class BaseCompany(ABC):
+
+    @abstractmethod
+    # execute the specific action configured in the intent table
+    def handle_request(self, tag: str, params: dict) -> dict:
+        raise NotImplementedError("La subclase debe implementar el método handle_request()")
+
+    @abstractmethod
+    def register_cli_commands(self, app):
+        pass
+
+    def unsupported_operation(self, tag):
+        raise NotImplementedError(f"La operación '{tag}' no está soportada por esta empresa.")

{iatoolkit-0.76.0 → iatoolkit-0.108.1}/src/iatoolkit/cli_commands.py

@@ -5,20 +5,22 @@
 
 import click
 import logging
-from .iatoolkit import IAToolkit
+from iatoolkit.core import IAToolkit
 from iatoolkit.services.profile_service import ProfileService
 
+
 def register_core_commands(app):
     """Registra los comandos CLI del núcleo de IAToolkit."""
 
     @app.cli.command("api-key")
     @click.argument("company_short_name")
-    def api_key(company_short_name: str):
+    @click.argument("key_name")
+    def api_key(company_short_name: str, key_name: str):
         """⚙️ Genera una nueva API key para una compañía ya registrada."""
         try:
             profile_service = IAToolkit.get_instance().get_injector().get(ProfileService)
             click.echo(f"🔑 Generating API-KEY for company: '{company_short_name}'...")
-            result = profile_service.new_api_key(company_short_name)
+            result = profile_service.new_api_key(company_short_name, key_name)
 
             if 'error' in result:
                 click.echo(f"❌ Error: {result['error']}")
@@ -43,17 +45,5 @@ def register_core_commands(app):
             logging.exception(e)
             click.echo(f"Error: {str(e)}")
 
-    @app.cli.command("exec-tasks")
-    @click.argument("company_short_name")
-    def exec_pending_tasks(company_short_name: str):
-        from iatoolkit.services.tasks_service import TaskService
-        task_service = IAToolkit.get_instance().get_injector().get(TaskService)
-
-        try:
-            result = task_service.trigger_pending_tasks(company_short_name)
-            click.echo(result['message'])
-        except Exception as e:
-            logging.exception(e)
-            click.echo(f"Error: {str(e)}")
 
 

{iatoolkit-0.76.0 → iatoolkit-0.108.1}/src/iatoolkit/common/exceptions.py

@@ -38,6 +38,7 @@ class IAToolkitException(Exception):
         INVALID_USER = 26
         VECTOR_STORE_ERROR = 27
         EMBEDDING_ERROR = 28
+        MODEL = 29
 
 
 

iatoolkit-0.108.1/src/iatoolkit/common/interfaces/asset_storage.py

@@ -0,0 +1,34 @@
+from enum import Enum
+from typing import List
+import abc
+
+
+class AssetType(Enum):
+    CONFIG = "config"
+    PROMPT = "prompts"
+    SCHEMA = "schema"
+    CONTEXT = "context"
+
+
+class AssetRepository(abc.ABC):
+    @abc.abstractmethod
+    def exists(self, company_short_name: str, asset_type: AssetType, filename: str) -> bool:
+        pass
+
+    @abc.abstractmethod
+    def read_text(self, company_short_name: str, asset_type: AssetType, filename: str) -> str:
+        pass
+
+    @abc.abstractmethod
+    def list_files(self, company_short_name: str, asset_type: AssetType, extension: str = None) -> List[str]:
+        pass
+
+    @abc.abstractmethod
+    def write_text(self, company_short_name: str, asset_type: AssetType, filename: str, content: str) -> None:
+        """Creates or updates a text asset."""
+        pass
+
+    @abc.abstractmethod
+    def delete(self, company_short_name: str, asset_type: AssetType, filename: str) -> None:
+        """Deletes an asset if it exists."""
+        pass