datapizza-ai-clients-mistral 0.0.2__tar.gz

datapizza_ai_clients_mistral-0.0.2/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

datapizza_ai_clients_mistral-0.0.2/PKG-INFO

@@ -0,0 +1,13 @@
+Metadata-Version: 2.4
+Name: datapizza-ai-clients-mistral
+Version: 0.0.2
+Summary: Mistral AI client for the datapizza-ai framework
+Author-email: Datapizza <datapizza@datapizza.tech>
+License: MIT
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: <4,>=3.10.0
+Requires-Dist: datapizza-ai-core>=0.0.0
+Requires-Dist: mistralai<2.0.0,>=1.2.0
+Requires-Dist: requests<3.0.0,>=2.25.0

datapizza_ai_clients_mistral-0.0.2/datapizza/clients/mistral/__init__.py

@@ -0,0 +1,3 @@
+from datapizza.clients.mistral.mistral_client import MistralClient
+
+__all__ = ["MistralClient"]

datapizza_ai_clients_mistral-0.0.2/datapizza/clients/mistral/memory_adapter.py

@@ -0,0 +1,103 @@
+import base64
+import json
+
+from datapizza.memory.memory import Turn
+from datapizza.memory.memory_adapter import MemoryAdapter
+from datapizza.type import (
+    ROLE,
+    FunctionCallBlock,
+    FunctionCallResultBlock,
+    MediaBlock,
+    StructuredBlock,
+    TextBlock,
+)
+
+
+class MistralMemoryAdapter(MemoryAdapter):
+    def _turn_to_message(self, turn: Turn) -> dict:
+        content = []
+        tool_calls = []
+        tool_call_id = None
+
+        for block in turn:
+            block_dict = {}
+
+            match block:
+                case TextBlock():
+                    block_dict = {"type": "text", "text": block.content}
+                case FunctionCallBlock():
+                    tool_calls.append(
+                        {
+                            "id": block.id,
+                            "function": {
+                                "name": block.name,
+                                "arguments": json.dumps(block.arguments),
+                            },
+                            "type": "function",
+                        }
+                    )
+                case FunctionCallResultBlock():
+                    tool_call_id = block.id
+                    block_dict = {"type": "text", "text": block.result}
+                case StructuredBlock():
+                    block_dict = {"type": "text", "text": str(block.content)}
+                case MediaBlock():
+                    match block.media.media_type:
+                        case "image":
+                            block_dict = self._process_image_block(block)
+                        # case "pdf":
+                        #    block_dict = self._process_pdf_block(block)
+
+                        case _:
+                            raise NotImplementedError(
+                                f"Unsupported media type: {block.media.media_type}, only image are supported"
+                            )
+
+            if block_dict:
+                content.append(block_dict)
+
+        messages: dict = {
+            "role": turn.role.value,
+        }
+
+        if content:
+            messages["content"] = content
+
+        if tool_calls:
+            messages["tool_calls"] = tool_calls
+
+        if tool_call_id:
+            messages["tool_call_id"] = tool_call_id
+
+        return messages
+
+    def _text_to_message(self, text: str, role: ROLE) -> dict:
+        return {"role": role.value, "content": text}
+
+    def _process_image_block(self, block: MediaBlock) -> dict:
+        match block.media.source_type:
+            case "url":
+                return {
+                    "type": "image_url",
+                    "image_url": {"url": block.media.source},
+                }
+            case "base64":
+                return {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": f"data:image/{block.media.extension};base64,{block.media.source}"
+                    },
+                }
+            case "path":
+                with open(block.media.source, "rb") as image_file:
+                    base64_image = base64.b64encode(image_file.read()).decode("utf-8")
+                return {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": f"data:image/{block.media.extension};base64,{base64_image}"
+                    },
+                }
+            case _:
+                raise NotImplementedError(
+                    f"Unsupported media source type: {block.media.source_type}, only url, base64, path are supported"
+                )

datapizza_ai_clients_mistral-0.0.2/datapizza/clients/mistral/mistral_client.py

@@ -0,0 +1,466 @@
+import json
+import logging
+import os
+from collections.abc import AsyncIterator, Iterator
+from typing import Literal
+
+import requests
+from datapizza.core.cache import Cache
+from datapizza.core.clients import Client, ClientResponse
+from datapizza.memory import Memory
+from datapizza.tools import Tool
+from datapizza.tools.tool_converter import ToolConverter
+from datapizza.type import (
+    FunctionCallBlock,
+    Media,
+    MediaBlock,
+    Model,
+    StructuredBlock,
+    TextBlock,
+)
+from mistralai import Mistral
+from mistralai.models.ocrresponse import OCRResponse
+
+from datapizza.clients.mistral.memory_adapter import MistralMemoryAdapter
+
+log = logging.getLogger(__name__)
+
+
+class MistralClient(Client):
+    """A client for interacting with the Mistral API.
+
+    This class provides methods for invoking the Mistral API to generate responses
+    based on given input data. It extends the Client class.
+    """
+
+    def __init__(
+        self,
+        api_key: str,
+        model: str = "mistral-large-latest",
+        system_prompt: str = "",
+        temperature: float | None = None,
+        cache: Cache | None = None,
+    ):
+        """
+        Args:
+            api_key: The API key for the Mistral API.
+            model: The model to use for the Mistral API.
+            system_prompt: The system prompt to use for the Mistral API.
+            temperature: The temperature to use for the Mistral API.
+            cache: The cache to use for the Mistral API.
+        """
+        if temperature and not 0 <= temperature <= 2:
+            raise ValueError("Temperature must be between 0 and 2")
+
+        super().__init__(
+            model_name=model,
+            system_prompt=system_prompt,
+            temperature=temperature,
+            cache=cache,
+        )
+
+        self.api_key = api_key
+        self.memory_adapter = MistralMemoryAdapter()
+        self._set_client()
+
+    def _set_client(self):
+        self.client = Mistral(api_key=self.api_key)
+
+    def _response_to_client_response(
+        self, response, tool_map: dict[str, Tool] | None = None
+    ) -> ClientResponse:
+        blocks = []
+        for choice in response.choices:
+            if choice.message.content:
+                blocks.append(TextBlock(content=choice.message.content))
+
+            if choice.message.tool_calls:
+                for tool_call in choice.message.tool_calls:
+                    tool = tool_map.get(tool_call.function.name) if tool_map else None
+
+                    if tool is None:
+                        raise ValueError(f"Tool {tool_call.function.name} not found")
+
+                    blocks.append(
+                        FunctionCallBlock(
+                            id=tool_call.id,
+                            name=tool_call.function.name,
+                            arguments=json.loads(tool_call.function.arguments),
+                            tool=tool,
+                        )
+                    )
+
+            # Handle media content if present
+            if hasattr(choice.message, "media") and choice.message.media:
+                for media_item in choice.message.media:
+                    media = Media(
+                        media_type=media_item.type,
+                        source_type="url" if media_item.source_url else "base64",
+                        source=media_item.source_url or media_item.data,
+                        detail=getattr(media_item, "detail", "high"),
+                    )
+                    blocks.append(MediaBlock(media=media))
+
+        log.debug(f"{self.__class__.__name__} response = {response}")
+        return ClientResponse(
+            content=blocks,
+            stop_reason=response.choices[0].finish_reason,
+            prompt_tokens_used=response.usage.prompt_tokens,
+            completion_tokens_used=response.usage.completion_tokens,
+            cached_tokens_used=0,
+        )
+
+    def _convert_tools(self, tools: Tool) -> dict:
+        """Convert tools to Mistral function format"""
+        return ToolConverter.to_mistral_format(tools)
+
+    def _convert_tool_choice(
+        self, tool_choice: Literal["auto", "required", "none"] | list[str]
+    ) -> dict | Literal["auto", "required", "none"]:
+        if isinstance(tool_choice, list) and len(tool_choice) > 1:
+            raise NotImplementedError(
+                "multiple function names is not supported by Mistral"
+            )
+        elif isinstance(tool_choice, list):
+            return {
+                "type": "function",
+                "function": {"name": tool_choice[0]},
+            }
+        else:
+            return tool_choice
+
+    def _invoke(
+        self,
+        *,
+        input: str,
+        tools: list[Tool] | None,
+        memory: Memory | None,
+        tool_choice: Literal["auto", "required", "none"] | list[str],
+        temperature: float | None,
+        max_tokens: int,
+        system_prompt: str | None,
+        **kwargs,
+    ) -> ClientResponse:
+        if tools is None:
+            tools = []
+        log.debug(f"{self.__class__.__name__} input = {input}")
+        messages = self._memory_to_contents(system_prompt, input, memory)
+
+        tool_map = {tool.name: tool for tool in tools}
+
+        request_params = {
+            "model": self.model_name,
+            "messages": messages,
+            "stream": False,
+            "max_tokens": max_tokens,
+            **kwargs,
+        }
+
+        if temperature:
+            request_params["temperature"] = temperature
+
+        if tools:
+            request_params["tools"] = [self._convert_tools(tool) for tool in tools]
+            request_params["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = self.client.chat.complete(**request_params)
+        return self._response_to_client_response(response, tool_map)
+
+    async def _a_invoke(
+        self,
+        *,
+        input: str,
+        tools: list[Tool] | None,
+        memory: Memory | None,
+        tool_choice: Literal["auto", "required", "none"] | list[str],
+        temperature: float | None,
+        max_tokens: int,
+        system_prompt: str | None,
+        **kwargs,
+    ) -> ClientResponse:
+        if tools is None:
+            tools = []
+        log.debug(f"{self.__class__.__name__} input = {input}")
+        messages = self._memory_to_contents(system_prompt, input, memory)
+
+        tool_map = {tool.name: tool for tool in tools}
+
+        request_params = {
+            "model": self.model_name,
+            "messages": messages,
+            "stream": False,
+            "max_tokens": max_tokens,
+            **kwargs,
+        }
+
+        if temperature:
+            request_params["temperature"] = temperature
+
+        if tools:
+            request_params["tools"] = [self._convert_tools(tool) for tool in tools]
+            request_params["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = await self.client.chat.complete_async(**request_params)
+        return self._response_to_client_response(response, tool_map)
+
+    def _stream_invoke(
+        self,
+        input: str,
+        tools: list[Tool] | None,
+        memory: Memory | None,
+        tool_choice: Literal["auto", "required", "none"] | list[str],
+        temperature: float | None,
+        max_tokens: int,
+        system_prompt: str | None,
+        **kwargs,
+    ) -> Iterator[ClientResponse]:
+        if tools is None:
+            tools = []
+        messages = self._memory_to_contents(system_prompt, input, memory)
+        request_params = {
+            "model": self.model_name,
+            "messages": messages,
+            "max_tokens": max_tokens,
+            **kwargs,
+        }
+
+        if temperature:
+            request_params["temperature"] = temperature
+
+        if tools:
+            request_params["tools"] = [self._convert_tools(tool) for tool in tools]
+            request_params["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = self.client.chat.stream(**request_params)
+        text = ""
+        for chunk in response:
+            delta = chunk.data.choices[0].delta.content or ""
+            text += delta
+            yield ClientResponse(
+                content=[],
+                delta=str(delta),
+                stop_reason=chunk.data.choices[0].finish_reason,
+                prompt_tokens_used=chunk.data.usage.prompt_tokens
+                if chunk.data.usage
+                else 0,
+                completion_tokens_used=chunk.data.usage.completion_tokens
+                if chunk.data.usage
+                else 0,
+                cached_tokens_used=0,
+            )
+
+    async def _a_stream_invoke(
+        self,
+        input: str,
+        tools: list[Tool] | None = None,
+        memory: Memory | None = None,
+        tool_choice: Literal["auto", "required", "none"] | list[str] = "auto",
+        temperature: float | None = None,
+        max_tokens: int | None = None,
+        system_prompt: str | None = None,
+        **kwargs,
+    ) -> AsyncIterator[ClientResponse]:
+        if tools is None:
+            tools = []
+        messages = self._memory_to_contents(system_prompt, input, memory)
+        request_params = {
+            "model": self.model_name,
+            "messages": messages,
+            "max_tokens": max_tokens or 1024,
+            **kwargs,
+        }
+
+        if temperature:
+            request_params["temperature"] = temperature
+
+        if tools:
+            request_params["tools"] = [self._convert_tools(tool) for tool in tools]
+            request_params["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = await self.client.chat.stream_async(**request_params)
+        text = ""
+        async for chunk in response:
+            delta = chunk.data.choices[0].delta.content or ""
+            text += delta
+            yield ClientResponse(
+                content=[],
+                delta=str(delta),
+                stop_reason=chunk.data.choices[0].finish_reason,
+                prompt_tokens_used=chunk.data.usage.prompt_tokens
+                if chunk.data.usage
+                else 0,
+                completion_tokens_used=chunk.data.usage.completion_tokens
+                if chunk.data.usage
+                else 0,
+                cached_tokens_used=0,
+            )
+
+    def _structured_response(
+        self,
+        input: str,
+        output_cls: type[Model],
+        memory: Memory | None,
+        temperature: float | None,
+        max_tokens: int,
+        system_prompt: str | None,
+        tools: list[Tool] | None,
+        tool_choice: Literal["auto", "required", "none"] | list[str] = "auto",
+        **kwargs,
+    ) -> ClientResponse:
+        # Add system message to enforce JSON output
+        messages = self._memory_to_contents(system_prompt, input, memory)
+
+        if not tools:
+            tools = []
+
+        if tools:
+            kwargs["tools"] = [self._convert_tools(tool) for tool in tools]
+            kwargs["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = self.client.chat.parse(
+            model=self.model_name,
+            messages=messages,
+            response_format=output_cls,
+            temperature=temperature,
+            max_tokens=max_tokens,
+            **kwargs,
+        )
+
+        if not response.choices:
+            raise ValueError("No response from Mistral")
+
+        log.debug(f"{self.__class__.__name__} structured response: {response}")
+        stop_reason = response.choices[0].finish_reason if response.choices else None
+        if hasattr(output_cls, "model_validate_json"):
+            structured_data = output_cls.model_validate_json(
+                str(response.choices[0].message.content)  # type: ignore
+            )
+        else:
+            structured_data = json.loads(str(response.choices[0].message.content))  # type: ignore
+        return ClientResponse(
+            content=[StructuredBlock(content=structured_data)],
+            stop_reason=stop_reason,
+            prompt_tokens_used=response.usage.prompt_tokens,
+            completion_tokens_used=response.usage.completion_tokens,
+            cached_tokens_used=0,
+        )
+
+    async def _a_structured_response(
+        self,
+        input: str,
+        output_cls: type[Model],
+        memory: Memory | None,
+        temperature: float | None,
+        max_tokens: int,
+        system_prompt: str | None,
+        tools: list[Tool] | None,
+        tool_choice: Literal["auto", "required", "none"] | list[str] = "auto",
+        **kwargs,
+    ) -> ClientResponse:
+        # Add system message to enforce JSON output
+        messages = self._memory_to_contents(system_prompt, input, memory)
+
+        if not tools:
+            tools = []
+
+        if tools:
+            kwargs["tools"] = [self._convert_tools(tool) for tool in tools]
+            kwargs["tool_choice"] = self._convert_tool_choice(tool_choice)
+
+        response = await self.client.chat.parse_async(
+            model=self.model_name,
+            messages=messages,
+            response_format=output_cls,
+            temperature=temperature,
+            max_tokens=max_tokens,
+            **kwargs,
+        )
+
+        if not response.choices:
+            raise ValueError("No response from Mistral")
+
+        log.debug(f"{self.__class__.__name__} structured response: {response}")
+        stop_reason = response.choices[0].finish_reason if response.choices else None
+        if hasattr(output_cls, "model_validate_json"):
+            structured_data = output_cls.model_validate_json(
+                str(response.choices[0].message.content)  # type: ignore
+            )
+        else:
+            structured_data = json.loads(str(response.choices[0].message.content))  # type: ignore
+        return ClientResponse(
+            content=[StructuredBlock(content=structured_data)],
+            stop_reason=stop_reason,
+            prompt_tokens_used=response.usage.prompt_tokens,
+            completion_tokens_used=response.usage.completion_tokens,
+            cached_tokens_used=0,
+        )
+
+    def _embed(
+        self, text: str | list[str], model_name: str | None, **kwargs
+    ) -> list[float] | list[list[float]]:
+        """Embed a text using the model"""
+        response = self.client.embeddings.create(
+            inputs=text, model=model_name or self.model_name, **kwargs
+        )
+
+        embeddings = [item.embedding for item in response.data]
+
+        if not embeddings:
+            return []
+
+        if isinstance(text, str) and embeddings[0]:
+            return embeddings[0]
+
+        return embeddings
+
+    async def _a_embed(
+        self, text: str | list[str], model_name: str | None, **kwargs
+    ) -> list[float] | list[list[float]]:
+        """Embed a text using the model"""
+        response = await self.client.embeddings.create_async(
+            inputs=text, model=model_name or self.model_name, **kwargs
+        )
+
+        embeddings = [item.embedding for item in response.data]
+
+        if not embeddings:
+            return []
+
+        if isinstance(text, str) and embeddings[0]:
+            return embeddings[0]
+
+        return embeddings or []
+
+    def parse_document(
+        self,
+        document_path: str,
+        autodelete: bool = True,
+        include_image_base64: bool = True,
+    ) -> OCRResponse:
+        filename = os.path.basename(document_path)
+        with open(document_path, "rb") as f:
+            uploaded_pdf = self.client.files.upload(
+                file={"file_name": filename, "content": f}, purpose="ocr"
+            )
+
+        signed_url = self.client.files.get_signed_url(file_id=uploaded_pdf.id)
+
+        response = self.client.ocr.process(
+            model="mistral-ocr-latest",
+            document={
+                "type": "document_url",
+                "document_url": signed_url.url,
+            },
+            include_image_base64=include_image_base64,
+        )
+
+        if autodelete:
+            url = f"https://api.mistral.ai/v1/files/{uploaded_pdf.id}"
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {self.api_key}",
+            }
+
+            requests.delete(url, headers=headers, timeout=30)
+
+        return response

datapizza_ai_clients_mistral-0.0.2/pyproject.toml

@@ -0,0 +1,59 @@
+# Build system configuration
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+# Project metadata
+[project]
+name = "datapizza-ai-clients-mistral"
+version = "0.0.2"
+description = "Mistral AI client for the datapizza-ai framework"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+    {name = "Datapizza", email = "datapizza@datapizza.tech"}
+]
+requires-python = ">=3.10.0,<4" 
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "datapizza-ai-core>=0.0.0",
+    "mistralai>=1.2.0,<2.0.0",
+    "requests>=2.25.0,<3.0.0",
+]
+
+# Development dependencies
+[dependency-groups]
+dev = [
+    "deptry>=0.23.0",
+    "pytest",
+    "ruff>=0.11.5",
+]
+
+# Hatch build configuration
+[tool.hatch.build.targets.sdist]
+include = ["datapizza"]
+exclude = ["**/BUILD"]
+
+[tool.hatch.build.targets.wheel]
+include = ["datapizza"]
+exclude = ["**/BUILD"]
+
+# Ruff configuration
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+select = [
+    "W",   # pycodestyle warnings
+    "F",   # pyflakes
+    "B",   # flake8-bugbear
+    "I",   # isort
+    "UP",  # pyupgrade
+    "SIM", # flake8-simplify
+    "RUF", # Ruff-specific rules
+    "C4",  # flake8-comprehensions
+]