iatoolkit 0.3.1__py3-none-any.whl

iatoolkit-0.3.1.dist-info/METADATA

@@ -0,0 +1,252 @@
+Metadata-Version: 2.4
+Name: iatoolkit
+Version: 0.3.1
+Summary: IAToolkit
+Author: Fernando Libedinsky
+License-Expression: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: aiohappyeyeballs==2.4.4
+Requires-Dist: aiohttp==3.11.9
+Requires-Dist: aiosignal==1.3.1
+Requires-Dist: annotated-types==0.7.0
+Requires-Dist: anyio==4.6.2.post1
+Requires-Dist: asgiref==3.8.1
+Requires-Dist: async-timeout==4.0.3
+Requires-Dist: attrs==24.3.0
+Requires-Dist: backoff==2.2.1
+Requires-Dist: bcrypt==4.2.1
+Requires-Dist: beautifulsoup4==4.12.3
+Requires-Dist: blinker==1.9.0
+Requires-Dist: boto3==1.36.22
+Requires-Dist: botocore==1.36.22
+Requires-Dist: build==1.2.2.post1
+Requires-Dist: cachelib==0.13.0
+Requires-Dist: cachetools==5.5.0
+Requires-Dist: certifi==2024.12.14
+Requires-Dist: cffi==1.17.1
+Requires-Dist: charset-normalizer==3.4.0
+Requires-Dist: click==8.1.8
+Requires-Dist: coloredlogs==15.0.1
+Requires-Dist: contourpy==1.3.3
+Requires-Dist: coverage==7.6.10
+Requires-Dist: cryptography==44.0.3
+Requires-Dist: cycler==0.12.1
+Requires-Dist: dataclasses-json==0.6.7
+Requires-Dist: Deprecated==1.2.15
+Requires-Dist: distro==1.9.0
+Requires-Dist: durationpy==0.9
+Requires-Dist: ecs-logging==2.2.0
+Requires-Dist: elastic-apm==6.23.0
+Requires-Dist: et_xmlfile==2.0.0
+Requires-Dist: exceptiongroup==1.2.2
+Requires-Dist: fastapi==0.115.6
+Requires-Dist: filelock==3.16.1
+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: fonttools==4.59.2
+Requires-Dist: frozenlist==1.5.0
+Requires-Dist: fsspec==2024.10.0
+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: grpcio==1.74.0
+Requires-Dist: grpcio-status==1.71.2
+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: importlib_metadata==8.5.0
+Requires-Dist: importlib_resources==6.4.5
+Requires-Dist: iniconfig==2.0.0
+Requires-Dist: injector==0.22.0
+Requires-Dist: itsdangerous==2.2.0
+Requires-Dist: Jinja2==3.1.5
+Requires-Dist: jiter==0.8.0
+Requires-Dist: jmespath==1.0.1
+Requires-Dist: joblib==1.4.2
+Requires-Dist: jsonpatch==1.33
+Requires-Dist: jsonpointer==3.0.0
+Requires-Dist: kiwisolver==1.4.9
+Requires-Dist: kubernetes==31.0.0
+Requires-Dist: langchain==0.3.19
+Requires-Dist: langchain-core==0.3.35
+Requires-Dist: langchain-text-splitters==0.3.6
+Requires-Dist: langsmith==0.3.8
+Requires-Dist: lxml==5.3.0
+Requires-Dist: markdown-it-py==3.0.0
+Requires-Dist: markdown2==2.5.3
+Requires-Dist: MarkupSafe==3.0.2
+Requires-Dist: marshmallow==3.23.1
+Requires-Dist: matplotlib==3.10.6
+Requires-Dist: mdurl==0.1.2
+Requires-Dist: mmh3==5.0.1
+Requires-Dist: monotonic==1.6
+Requires-Dist: mpmath==1.3.0
+Requires-Dist: msgspec==0.19.0
+Requires-Dist: multidict==6.1.0
+Requires-Dist: mypy-extensions==1.0.0
+Requires-Dist: narwhals==2.3.0
+Requires-Dist: networkx==3.4.2
+Requires-Dist: numpy==2.2.3
+Requires-Dist: oauth2client==4.1.3
+Requires-Dist: oauthlib==3.2.2
+Requires-Dist: onnxruntime==1.19.2
+Requires-Dist: openai==1.79.0
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: opentelemetry-api==1.28.2
+Requires-Dist: opentelemetry-exporter-otlp-proto-common==1.28.2
+Requires-Dist: opentelemetry-exporter-otlp-proto-grpc==1.28.2
+Requires-Dist: opentelemetry-instrumentation==0.49b2
+Requires-Dist: opentelemetry-instrumentation-asgi==0.49b2
+Requires-Dist: opentelemetry-instrumentation-fastapi==0.49b2
+Requires-Dist: opentelemetry-proto==1.28.2
+Requires-Dist: opentelemetry-sdk==1.28.2
+Requires-Dist: opentelemetry-semantic-conventions==0.49b2
+Requires-Dist: opentelemetry-util-http==0.49b2
+Requires-Dist: orjson==3.10.12
+Requires-Dist: overrides==7.7.0
+Requires-Dist: packaging==24.2
+Requires-Dist: pandas==2.3.1
+Requires-Dist: pgvector==0.3.6
+Requires-Dist: pillow==11.0.0
+Requires-Dist: plotly==6.3.0
+Requires-Dist: pluggy==1.5.0
+Requires-Dist: posthog==3.7.4
+Requires-Dist: propcache==0.2.1
+Requires-Dist: proto-plus==1.26.0
+Requires-Dist: protobuf==5.29.1
+Requires-Dist: psutil==7.0.0
+Requires-Dist: psycopg2-binary==2.9.10
+Requires-Dist: pyarrow==21.0.0
+Requires-Dist: pyasn1==0.6.1
+Requires-Dist: pyasn1_modules==0.4.1
+Requires-Dist: pycparser==2.22
+Requires-Dist: pydantic==2.10.2
+Requires-Dist: pydantic-settings==2.6.1
+Requires-Dist: pydantic_core==2.27.1
+Requires-Dist: PyDrive==1.3.1
+Requires-Dist: Pygments==2.18.0
+Requires-Dist: PyJWT==2.10.1
+Requires-Dist: PyMuPDF==1.25.0
+Requires-Dist: pyparsing==3.2.1
+Requires-Dist: pypdf==5.1.0
+Requires-Dist: PyPika==0.48.9
+Requires-Dist: pyproject_hooks==1.2.0
+Requires-Dist: pytesseract==0.3.13
+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: python-dotenv==1.0.1
+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: rich==13.9.4
+Requires-Dist: rsa==4.9
+Requires-Dist: s3transfer==0.11.2
+Requires-Dist: safetensors==0.5.2
+Requires-Dist: scikit-learn==1.7.1
+Requires-Dist: scipy==1.15.1
+Requires-Dist: seaborn==0.13.2
+Requires-Dist: setuptools==75.8.0
+Requires-Dist: shellingham==1.5.4
+Requires-Dist: sib-api-v3-sdk==7.6.0
+Requires-Dist: six==1.17.0
+Requires-Dist: sniffio==1.3.1
+Requires-Dist: soupsieve==2.6
+Requires-Dist: SQLAlchemy==2.0.36
+Requires-Dist: starlette==0.41.3
+Requires-Dist: sympy==1.13.1
+Requires-Dist: tenacity==9.0.0
+Requires-Dist: threadpoolctl==3.5.0
+Requires-Dist: tiktoken==0.8.0
+Requires-Dist: tokenizers==0.21.0
+Requires-Dist: tomli==2.2.1
+Requires-Dist: tqdm==4.67.1
+Requires-Dist: typer==0.15.1
+Requires-Dist: typing-inspect==0.9.0
+Requires-Dist: typing_extensions==4.12.2
+Requires-Dist: tzdata==2025.2
+Requires-Dist: uritemplate==4.1.1
+Requires-Dist: urllib3==2.3.0
+Requires-Dist: uvicorn==0.32.1
+Requires-Dist: uvloop==0.21.0
+Requires-Dist: watchfiles==1.0.0
+Requires-Dist: websocket-client==1.8.0
+Requires-Dist: websockets==14.1
+Requires-Dist: Werkzeug==3.1.3
+Requires-Dist: whitenoise==6.8.2
+Requires-Dist: wikipedia==1.4.0
+Requires-Dist: wrapt==1.17.0
+Requires-Dist: yarl==1.18.3
+Requires-Dist: zipp==3.21.0
+Requires-Dist: zstandard==0.23.0
+
+# iatoolkit
+
+IAToolkit is a comprehensive, open-source framework designed for building enterprise-grade 
+AI chatbots and conversational applications. 
+Built on Flask with dependency injection, it provides a robust foundation for scalable AI solutions.
+
+## 🚀 Key Features
+- **Universal LLM Integration**: OpenAI GPT, Google Gemini
+- **Template System**: Jinja2-powered prompt templates with variables
+- **Context Management**: Maintain conversation context across sessions
+
+### 🔒 **Enterprise Security**
+- **JWT Authentication**: Secure token-based authentication
+- **Session Management**: Redis-backed secure sessions
+- **CORS Configuration**: Flexible cross-origin resource sharing
+
+### 🛠 **Function Calling & Tools**
+- **Native Function Calls**: Direct integration with LLM function calling
+- **Custom Tools**: Build and register custom tools for your chatbot
+- **SQL Query Generation**: Natural language to SQL conversion
+- **API Integrations**: Connect to external services and APIs
+
+### 🗄 **Database & Storage**
+- **Multi-Database Support**: PostgreSQL, MySQL, SQLite via SQLAlchemy
+- **Vector Store Integration**: Semantic search and retrieval
+- **Document Processing**: PDF, Word, Excel, and text file handling
+
+### 📊 **Analytics & Monitoring**
+- **Query Logging**: Track all LLM interactions
+- **Performance Metrics**: Response times, token usage, costs
+- **Benchmarking**: Compare model performance
+- **Task Management**: Async task processing with status tracking
+
+### 🔧 **Developer Experience**
+- **Dependency Injection**: Clean, testable architecture
+- **CLI Tools**: Command-line interface for common tasks
+- **Hot Reloading**: Development-friendly configuration
+- **Comprehensive Logging**: Debug and monitor easily
+
+## License
+MIT License
+
+

iatoolkit-0.3.1.dist-info/RECORD

@@ -0,0 +1,28 @@
+iatoolkit/__init__.py,sha256=Yu9XbQmEjs0gA1HBnqiaORL7HUfoKuEElUIs8scg4IQ,1125
+iatoolkit/base_company.py,sha256=VWfpNofFlmgHQQK8BCw2KSOPLd2DM9eA68lGQ3SDE7M,1639
+iatoolkit/company_registry.py,sha256=saOf5JxsEtvAs-JqkNp-UfOIQvtVCXyujvv6G5_zi5k,3332
+iatoolkit/iatoolkit.py,sha256=YX5Oh-WWBKX0DDrzeOeaNoBrPLm0O7t4ttntYC_rk-8,15186
+iatoolkit/toolkit_config.py,sha256=y4y6DV_HvHbEHCKC3v5FtX9zZyuYR5qOoULPNuiNfXI,492
+services/__init__.py,sha256=fSvSfIcPW1dHwTBY1hQ5dBEhaoorzk_GzR4G46gD8tY,173
+services/api_service.py,sha256=VTM5OfKF7-eCT-dpl46ZnZ3ptbTxLUDH2IxnbS4T3jA,1113
+services/benchmark_service.py,sha256=g9JVrmAqIe_iI0D1DwdQ6DJ2_FJRCTndarESNSVfhbw,5907
+services/dispatcher_service.py,sha256=iNu_gUZS_AgbwmCxtLBk0A33-jxsnMGYAKI5ScaJ-yE,13207
+services/document_service.py,sha256=sm5QtbrKs2dF9hpLuSLMB-IMWYNBD7yWHv3rd80aD0o,5960
+services/excel_service.py,sha256=wE9Udbyb96kGRSnZZ6KM2mbE484rKjTEhta9GKKpy-8,3630
+services/file_processor_service.py,sha256=82UArWtwpr94CAMkkoRP0_nPtoqItymdKSIABS0Xkxw,2943
+services/history_service.py,sha256=dl-D7qgdnzpY9QhjuxJokBYZZ1AF0y59HbRzwpPet58,1654
+services/jwt_service.py,sha256=dC45Sn6FyzdzRiQJnzgkjN3Hy21V1imRxB0hTyWRvlA,3979
+services/load_documents_service.py,sha256=_-OTUih8Zk0m4dHqAhkE7kAwU2mbz_QoMrOKnrq7ZWs,8821
+services/mail_service.py,sha256=ystFit1LuYUC4ekYYebyiy1rqYQmxeL6K8h58MxEkOY,2233
+services/profile_service.py,sha256=z1dSX45HDv8VJE4w8-ucpb3kBpE2fkyOdtgnrHc9vuE,17918
+services/prompt_manager_service.py,sha256=nnr_iNIFeJzOY_1fbuu5-reyJS04RvGx5JW_d3YFUbk,7966
+services/query_service.py,sha256=Fx_P1WcuoAp_TyocN5LGlv_hc_03ImzU5QdAIqQg0ek,15591
+services/search_service.py,sha256=oJD6WRXCJBD7WUVHWWKxexRkhR8nQSrFtcPV3pFO2KQ,1153
+services/sql_service.py,sha256=H7CIPpXTcxLXLojD2fBFr_mIAD0PW1vEJhKHLfJi4Hk,1418
+services/tasks_service.py,sha256=hHJDlcsSOPtEleD6_Vv3pocfxWNmthIhmZSdnoWFpEM,6861
+services/user_feedback_service.py,sha256=YtCndRBekDEWYEbac431Ksn2gMO5iBrI3WqKK0xtShE,2513
+services/user_session_context_service.py,sha256=5qn7fqpuiU8KgMpU4M5-iRUsETumz1raBw-EeZLuE1A,3868
+iatoolkit-0.3.1.dist-info/METADATA,sha256=fhcbOmNc0NQoNP0HA_QpNc0Y7VIqgPfLWV14fz7e_IQ,8801
+iatoolkit-0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+iatoolkit-0.3.1.dist-info/top_level.txt,sha256=dqlBbmgo9okD9d_WMR9uYzdup7Rxgj26yFF85jRGeu4,19
+iatoolkit-0.3.1.dist-info/RECORD,,

iatoolkit-0.3.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

iatoolkit-0.3.1.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+iatoolkit
+services

services/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Producto: IAToolkit
+# Todos los derechos reservados.
+# En trámite de registro en el Registro de Propiedad Intelectual de Chile.
+

services/api_service.py

@@ -0,0 +1,30 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Producto: IAToolkit
+# Todos los derechos reservados.
+# En trámite de registro en el Registro de Propiedad Intelectual de Chile.
+
+from infra.call_service import CallServiceClient
+from injector import inject
+from common.exceptions import IAToolkitException
+import json
+
+
+class ApiService:
+    @inject
+    def __init__(self, call_service: CallServiceClient):
+        self.call_service = call_service
+
+    def call_api(self, endpoint: str, method: str, **kwargs):
+        if method == 'get':
+            response, status_code = self.call_service.get(endpoint)
+        elif method == 'post':
+            response, status_code = self.call_service.post(endpoint=endpoint, json_dict=kwargs)
+        else:
+            raise IAToolkitException(IAToolkitException.ErrorType.INVALID_PARAMETER,
+                               f'API error, {method} not supported')
+
+        if status_code != 200:
+            raise IAToolkitException(IAToolkitException.ErrorType.CALL_ERROR,
+                               f'API {endpoint} error: {status_code}')
+
+        return json.dumps(response)

services/benchmark_service.py

@@ -0,0 +1,139 @@
+# Copyright (c) 2024 Fernando Libedinsky
+# Producto: IAToolkit
+# Todos los derechos reservados.
+# En trámite de registro en el Registro de Propiedad Intelectual de Chile.
+
+import pandas as pd
+import time
+import logging
+from injector import inject
+from services.query_service import QueryService
+from repositories.profile_repo import ProfileRepo
+from common.exceptions import IAToolkitException
+
+
+class BenchmarkService:
+    @inject
+    def __init__(self, query_service: QueryService, profile_repo: ProfileRepo):
+        self.query_service = query_service
+        self.profile_repo = profile_repo
+
+    def _update_results_row(self, df: pd.DataFrame, index: int,
+                            status: str,
+                            context_time: float,
+                            gpt_time: float,
+                            answer: str,
+                            error_msg: str,
+                            query_id: int,
+                            stats: dict):
+        df.at[index, 'status'] = status
+        df.at[index, 'context_time'] = round(context_time, 2)
+        df.at[index, 'gpt_time'] = round(gpt_time, 2)
+        df.at[index, 'answer'] = answer
+        df.at[index, 'error_message'] = error_msg[:512]
+        df.at[index, 'query_id'] = query_id
+        df.at[index, 'in_tokens'] = stats.get('input_tokens', 0)
+        df.at[index, 'out_tokens'] = stats.get('output_tokens', 0)
+        df.at[index, 'retry'] = stats.get('sql_retry_count', 0)
+
+    def run(self, company_short_name: str, file_path: str):
+        if not file_path.endswith('.xlsx'):
+            raise IAToolkitException(IAToolkitException.ErrorType.INVALID_PARAMETER,
+                        f"solo se leer archivos .xlsx")
+
+        try:
+            df = pd.read_excel(file_path, keep_default_na=False)
+        except FileNotFoundError:
+            raise IAToolkitException(IAToolkitException.ErrorType.INVALID_NAME,
+                        f"El archivo no fue encontrado en: {file_path}")
+
+        required_columns = ['username', 'client_identity', 'prompt_name', 'question', 'model']
+        if not all(col in df.columns for col in required_columns):
+            raise IAToolkitException(IAToolkitException.ErrorType.INVALID_PARAMETER,
+                               f"La planilla debe contener las columnas: {required_columns}")
+
+        # Añadir columnas para los resultados
+        df['status'] = 'pending'
+        df['context_time'] = 0.0
+        df['gpt_time'] = 0.0
+        df['answer'] = ''
+        df['error_message'] = ''
+        df['query_id'] = 0
+        df['in_tokens'] = 0
+        df['out_tokens'] = 0
+        df['retry'] = 0
+
+        company = self.profile_repo.get_company_by_short_name(company_short_name)
+        if not company:
+            raise IAToolkitException(IAToolkitException.ErrorType.CONFIG_ERROR, "Compañía 'maxxa' no encontrada.")
+
+        total_rows = len(df)
+        logging.info(f"Iniciando benchmark para {total_rows} casos de prueba desde el archivo: {file_path}")
+
+        for index, row in df.iterrows():
+            status = 'OK'
+            error_msg = ''
+            answer = ''
+            stats = {}
+
+            try:
+                username = str(row['username'])
+                client_identity = str(row['client_identity'])
+                prompt_name = str(row['prompt_name'])
+                question = str(row['question'])
+                model = str(row['model'])
+
+                logging.info(
+                    f"*** Procesando caso {index + 1}/{total_rows}: client_rut='{client_identity}', prompt='{prompt_name}'")
+
+                # 1. init context with user executing the test
+                start_time = time.time()
+                self.query_service.llm_init_context(company.short_name,
+                                                    external_user_id=username,
+                                                    model=model)
+                context_time = time.time() - start_time
+
+                # 2. prepare client data.
+                client_data = {'client_identity': client_identity}
+
+                # 3. execute the query
+                start_time = time.time()
+                response = self.query_service.llm_query(
+                    company_short_name=company.short_name,
+                    prompt_name=prompt_name,
+                    question=question,
+                    external_user_id=username,
+                    client_data=client_data
+                )
+                gpt_time = time.time() - start_time
+
+                # 4. process the response
+                if response.get('error') or not response.get('valid_response'):
+                    status = 'FAILED'
+                    error_msg = response.get('error_message', 'Error desconocido en la respuesta.')
+                else:
+                    answer = response.get('answer', '')
+                    stats = response.get('stats', {})
+
+                query_id = response.get('query_id', 0)
+
+            except Exception as e:
+                status = 'FAILED'
+                error_msg = f"Excepción durante la ejecución: {type(e).__name__} - {str(e)}"
+                logging.error(f"Fallo en el caso {index + 1}: {error_msg}")
+
+            finally:
+                self._update_results_row(df, index,
+                                         status=status,
+                                         context_time=context_time,
+                                         gpt_time=gpt_time,
+                                         answer=answer,
+                                         error_msg=error_msg,
+                                         stats=stats,
+                                         query_id=query_id)
+
+        output_filename = file_path.replace('.xlsx', '_results.xlsx')
+        df.to_excel(output_filename, index=False)
+        logging.info(f"Benchmark finalizado. Resultados guardados en: {output_filename}")
+
+        return output_filename