iatoolkit 0.71.4__py3-none-any.whl → 1.4.2__py3-none-any.whl

iatoolkit/views/rag_api_view.py

@@ -0,0 +1,216 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Product: IAToolkit
+#
+# IAToolkit is open source software.
+
+
+from iatoolkit.common.exceptions import IAToolkitException
+from iatoolkit.services.knowledge_base_service import KnowledgeBaseService
+from iatoolkit.services.auth_service import AuthService
+from iatoolkit.common.util import Utility
+from iatoolkit.services.i18n_service import I18nService
+from flask import request, jsonify, send_file
+from flask.views import MethodView
+from injector import inject
+from datetime import datetime
+import io
+import mimetypes
+
+class RagApiView(MethodView):
+    """
+    API Endpoints for managing the RAG Knowledge Base.
+    """
+
+    @inject
+    def __init__(self,
+                 knowledge_base_service: KnowledgeBaseService,
+                 auth_service: AuthService,
+                 i18n_service: I18nService,
+                 utility: Utility):
+        self.knowledge_base_service = knowledge_base_service
+        self.auth_service = auth_service
+        self.utility = utility
+        self.i18n_service = i18n_service
+
+    def dispatch_request(self, *args, **kwargs):
+        """
+        Sobreescribimos el dispatch para soportar el mapeo de acciones personalizadas
+        pasadas a través de 'defaults' en add_url_rule (ej: action='list_files').
+        """
+        action = kwargs.pop('action', None)
+        if action:
+            method = getattr(self, action, None)
+            if method:
+                return method(*args, **kwargs)
+            else:
+                raise AttributeError(self.i18n_service.t('rag.management.action_not_found', action=action))
+
+        return super().dispatch_request(*args, **kwargs)
+
+    def list_files(self, company_short_name):
+        """
+        POST /api/rag/<company_short_name>/files
+        Returns a paginated list of documents based on filters provided in the JSON body.
+        """
+        try:
+            # 1. Authenticate the user from the current session.
+            auth_result = self.auth_service.verify()
+            if not auth_result.get("success"):
+                return jsonify(auth_result), auth_result.get("status_code")
+
+            # 2. Parse Input
+            data = request.get_json() or {}
+
+            status = data.get('status', [])
+            user_identifier = data.get('user_identifier')
+            keyword = data.get('filename_keyword')
+            from_date_str = data.get('from_date')
+            to_date_str = data.get('to_date')
+            collection = data.get('collection', '')
+            limit = int(data.get('limit', 100))
+            offset = int(data.get('offset', 0))
+
+            from_date = datetime.fromisoformat(from_date_str) if from_date_str else None
+            to_date = datetime.fromisoformat(to_date_str) if to_date_str else None
+
+            # 3. Call Service
+            documents = self.knowledge_base_service.list_documents(
+                company_short_name=company_short_name,
+                status=status,
+                collection=collection,
+                filename_keyword=keyword,
+                user_identifier=user_identifier,
+                from_date=from_date,
+                to_date=to_date,
+                limit=limit,
+                offset=offset
+            )
+
+            # 4. Format Response
+            response_list = []
+            for doc in documents:
+                response_list.append({
+                    'id': doc.id,
+                    'filename': doc.filename,
+                    'user_identifier': doc.user_identifier,
+                    'status': doc.status.value if hasattr(doc.status, 'value') else str(doc.status),
+                    'created_at': doc.created_at.isoformat() if doc.created_at else None,
+                    'metadata': doc.meta,
+                    'error_message': doc.error_message,
+                    'collection': doc.collection_type.name if doc.collection_type else None,
+                })
+
+            return jsonify({
+                'result': 'success',
+                'count': len(response_list),
+                'documents': response_list
+            }), 200
+
+        except IAToolkitException as e:
+            return jsonify({'result': 'error', 'message': e.message}), e.http_code
+        except Exception as e:
+            return jsonify({'result': 'error', 'message': str(e)}), 500
+
+    def get_file_content(self, company_short_name, document_id):
+        """
+        GET /api/rag/<company_short_name>/files/<document_id>/content
+        Streams the file content to the browser (inline view preferred).
+        """
+        try:
+            # 1. Authenticate
+            auth_result = self.auth_service.verify()
+            if not auth_result.get("success"):
+                return jsonify(auth_result), auth_result.get("status_code")
+
+            # 2. Get content from service
+            file_bytes, filename = self.knowledge_base_service.get_document_content(document_id)
+
+            if not file_bytes:
+                msg = self.i18n_service.t('rag.management.not_found')
+                return jsonify({'result': 'error', 'message': msg}), 404
+
+            # 3. Determine MIME type
+            mime_type, _ = mimetypes.guess_type(filename)
+            if not mime_type:
+                mime_type = 'application/octet-stream'
+
+            # 4. Stream response
+            return send_file(
+                io.BytesIO(file_bytes),
+                mimetype=mime_type,
+                as_attachment=False,  # Inline view
+                download_name=filename
+            )
+
+        except IAToolkitException as e:
+            return jsonify({'result': 'error', 'message': e.message}), e.http_code
+        except Exception as e:
+            return jsonify({'result': 'error', 'message': str(e)}), 500
+
+    def delete_file(self, company_short_name, document_id):
+        """
+        DELETE /api/rag/<company_short_name>/files/<document_id>
+        Deletes a document and its vectors.
+        """
+        try:
+            # 1. Authenticate
+            auth_result = self.auth_service.verify()
+            if not auth_result.get("success"):
+                return jsonify(auth_result), auth_result.get("status_code")
+
+            # 2. Call Service
+            success = self.knowledge_base_service.delete_document(document_id)
+
+            if success:
+                msg = self.i18n_service.t('rag.management.delete_success')
+                return jsonify({'result': 'success', 'message': msg}), 200
+            else:
+                msg = self.i18n_service.t('rag.management.not_found')
+                return jsonify({'result': 'error', 'message': msg}), 404
+
+        except IAToolkitException as e:
+            return jsonify({'result': 'error', 'message': e.message}), e.http_code
+        except Exception as e:
+            return jsonify({'result': 'error', 'message': str(e)}), 500
+
+    def search(self, company_short_name):
+        """
+        POST /api/rag/<company_short_name>/search
+        Synchronous semantic search for the "Search Lab" UI.
+        Returns detailed chunks with text and metadata using search_raw.
+        """
+        try:
+            # 1. Authenticate
+            auth_result = self.auth_service.verify()
+            if not auth_result.get("success"):
+                return jsonify(auth_result), auth_result.get("status_code")
+
+            # 2. Parse Input
+            data = request.get_json() or {}
+            query = data.get('query')
+            n_results = int(data.get('k', 5))
+            collection = data.get('collection')
+            metadata_filter = data.get('metadata_filter')
+
+            if not query:
+                msg = self.i18n_service.t('rag.search.query_required')
+                return jsonify({'result': 'error', 'message': msg}), 400
+
+            # 3. Call Service
+            chunks = self.knowledge_base_service.search_raw(
+                company_short_name=company_short_name,
+                query=query,
+                n_results=n_results,
+                collection=collection,
+                metadata_filter=metadata_filter,
+            )
+
+            return jsonify({
+                "result": "success",
+                "chunks": chunks
+            }), 200
+
+        except IAToolkitException as e:
+            return jsonify({'result': 'error', 'error_message': e.message}), 501
+        except Exception as e:
+            return jsonify({'result': 'error', 'error_message': str(e)}), 500

iatoolkit/views/root_redirect_view.py

@@ -0,0 +1,22 @@
+from flask import redirect, url_for
+from flask.views import MethodView
+from iatoolkit.company_registry import get_company_registry
+
+
+class RootRedirectView(MethodView):
+    """
+    Vista que redirige la raíz '/' al home de la primera compañía disponible.
+    """
+
+    def get(self):
+        registry = get_company_registry()
+        companies = registry.get_all_company_instances()
+
+        if companies:
+            # Obtener el short_name de la primera compañía registrada.
+            # En Python 3.7+, los diccionarios mantienen el orden de inserción.
+            first_company_short_name = next(iter(companies))
+            return redirect(url_for('home', company_short_name=first_company_short_name))
+
+        # Fallback: Si no hay compañías, ir al index genérico (o a un 404)
+        return redirect(url_for('index'))

iatoolkit/views/signup_view.py

@@ -22,7 +22,7 @@ class SignupView(MethodView):
         self.branding_service = branding_service # 3. Guardar la instancia
         self.i18n_service = i18n_service
 
-        self.serializer = URLSafeTimedSerializer(os.getenv("USER_VERIF_KEY"))
+        self.serializer = URLSafeTimedSerializer(os.getenv("IATOOLKIT_SECRET_KEY"))
 
 
     def get(self, company_short_name: str):
@@ -33,9 +33,12 @@ class SignupView(MethodView):
                                    message=self.i18n_service.t('errors.templates.company_not_found')), 404
 
         branding_data = self.branding_service.get_company_branding(company_short_name)
+        current_lang = request.args.get("lang") or "en"
+
         return render_template('signup.html',
                                company_short_name=company_short_name,
-                               branding=branding_data)
+                               branding=branding_data,
+                               lang=current_lang)
 
     def post(self, company_short_name: str):
         try:
@@ -52,6 +55,9 @@ class SignupView(MethodView):
             password = request.form.get('password')
             confirm_password = request.form.get('confirm_password')
 
+            # get the language from the form, then query
+            current_lang = request.form.get("lang") or request.args.get("lang")
+
             # create verification token and url for verification
             token = self.serializer.dumps(email, salt='email-confirm')
             verification_url = url_for('verify_account',
@@ -71,6 +77,7 @@ class SignupView(MethodView):
                     'signup.html',
                     company_short_name=company_short_name,
                     branding=branding_data,
+                    lang=current_lang,
                     form_data={
                         "first_name": first_name,
                         "last_name": last_name,
@@ -80,7 +87,7 @@ class SignupView(MethodView):
                     }), 400
 
             flash(response["message"], 'success')
-            return redirect(url_for('home', company_short_name=company_short_name))
+            return redirect(url_for('home', company_short_name=company_short_name, lang=current_lang))
 
         except Exception as e:
             message = self.i18n_service.t('errors.templates.processing_error', error=str(e))
@@ -88,5 +95,6 @@ class SignupView(MethodView):
                 "error.html",
                 company_short_name=company_short_name,
                 branding=branding_data,
-                message=message
+                message=message,
+                lang=current_lang
             ), 500

iatoolkit/views/static_page_view.py

@@ -0,0 +1,27 @@
+from flask import render_template
+from flask.views import MethodView
+from injector import inject
+
+
+class StaticPageView(MethodView):
+    """
+    View genérica para servir páginas estáticas simples (sin lógica de negocio compleja).
+    """
+
+    @inject
+    def __init__(self):
+        pass
+
+    def get(self, page_name: str):
+        # Mapeo seguro de nombres de página a plantillas
+        # Esto evita que se intente cargar cualquier archivo arbitrario
+        valid_pages = {
+            'foundation': 'docs/foundation.html',
+            'mini_project': 'docs/mini_project.html'
+        }
+
+        if page_name not in valid_pages:
+            # Si la página no existe, podríamos retornar un 404 o redirigir al index
+            return render_template('error.html', message=f"Página no encontrada: {page_name}"), 404
+
+        return render_template(valid_pages[page_name])

iatoolkit/views/users_api_view.py

@@ -0,0 +1,33 @@
+from flask.views import MethodView
+from flask import jsonify
+from injector import inject
+from iatoolkit.services.auth_service import AuthService
+from iatoolkit.services.profile_service import ProfileService
+import logging
+
+
+class UsersApiView(MethodView):
+    """
+    list company users and their roles
+    """
+    @inject
+    def __init__(self,
+                 auth_service: AuthService,
+                 profile_service: ProfileService):
+        self.auth_service = auth_service
+        self.profile_service = profile_service
+
+    def get(self, company_short_name: str):
+        try:
+            auth_result = self.auth_service.verify(anonymous=True)
+            if not auth_result.get("success"):
+                return jsonify(auth_result), auth_result.get("status_code", 401)
+
+            # get users of the company
+            users = self.profile_service.get_company_users(company_short_name)
+
+            return jsonify(users), 200
+
+        except Exception as e:
+            logging.exception(f"Error fetching users for {company_short_name}: {e}")
+            return jsonify({"error": "Unexpected error", "details": str(e)}), 500

iatoolkit/views/verify_user_view.py

@@ -22,7 +22,7 @@ class VerifyAccountView(MethodView):
         self.profile_service = profile_service
         self.branding_service = branding_service
         self.i18n_service = i18n_service
-        self.serializer = URLSafeTimedSerializer(os.getenv("USER_VERIF_KEY"))
+        self.serializer = URLSafeTimedSerializer(os.getenv("IATOOLKIT_SECRET_KEY"))
 
     def get(self, company_short_name: str, token: str):
         try:

iatoolkit-1.4.2.dist-info/METADATA

@@ -0,0 +1,268 @@
+Metadata-Version: 2.4
+Name: iatoolkit
+Version: 1.4.2
+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.