ai-data-science-team 0.0.0.9009__py3-none-any.whl → 0.0.0.9010__py3-none-any.whl

ai_data_science_team/ml_agents/mlflow_tools_agent.py

@@ -0,0 +1,327 @@
+
+from typing import Any, Optional, Annotated, Sequence
+import operator
+
+import pandas as pd
+
+from IPython.display import Markdown
+
+from langchain_core.messages import BaseMessage, AIMessage
+
+from langgraph.prebuilt import create_react_agent, ToolNode
+from langgraph.prebuilt.chat_agent_executor import AgentState
+from langgraph.graph import START, END, StateGraph
+
+from ai_data_science_team.templates import BaseAgent
+from ai_data_science_team.utils.regex import format_agent_name
+from ai_data_science_team.tools.mlflow import (
+    mlflow_search_experiments, 
+    mlflow_search_runs,
+    mlflow_create_experiment, 
+    mlflow_predict_from_run_id,
+    mlflow_launch_ui,
+    mlflow_stop_ui,
+    mlflow_list_artifacts,
+    mlflow_download_artifacts,
+    mlflow_list_registered_models,
+    mlflow_search_registered_models,
+    mlflow_get_model_version_details,
+)
+
+AGENT_NAME = "mlflow_tools_agent"
+
+# TOOL SETUP
+tools = [
+    mlflow_search_experiments, 
+    mlflow_search_runs, 
+    mlflow_create_experiment, 
+    mlflow_predict_from_run_id,
+    mlflow_launch_ui,
+    mlflow_stop_ui,
+    mlflow_list_artifacts,
+    mlflow_download_artifacts,
+    mlflow_list_registered_models,
+    mlflow_search_registered_models,
+    mlflow_get_model_version_details,
+]
+
+class MLflowToolsAgent(BaseAgent):
+    """
+    An agent that can interact with MLflow by calling tools.
+    
+    Current tools include:
+    - List Experiments
+    - Search Runs
+    - Create Experiment
+    - Predict (from a Run ID)
+    
+    Parameters:
+    ----------
+    model : langchain.llms.base.LLM
+        The language model used to generate the tool calling agent.
+    mlfow_tracking_uri : str, optional
+        The tracking URI for MLflow. Defaults to None.
+    mlflow_registry_uri : str, optional
+        The registry URI for MLflow. Defaults to None.
+    **react_agent_kwargs : dict, optional
+        Additional keyword arguments to pass to the agent's react agent.
+    
+    Methods:
+    --------
+    update_params(**kwargs):
+        Updates the agent's parameters and rebuilds the compiled graph.
+    ainvoke_agent(user_instructions: str=None, data_raw: pd.DataFrame=None, **kwargs):
+        Asynchronously runs the agent with the given user instructions.
+    invoke_agent(user_instructions: str=None, data_raw: pd.DataFrame=None, **kwargs):
+        Runs the agent with the given user instructions.
+    get_internal_messages(markdown: bool=False):
+        Returns the internal messages from the agent's response.
+    get_mlflow_artifacts(as_dataframe: bool=False):
+        Returns the MLflow artifacts from the agent's response.
+    get_ai_message(markdown: bool=False):
+        Returns the AI message from the agent's response
+    
+    
+    
+    Examples:
+    --------
+    ```python
+    from ai_data_science_team.ml_agents import MLflowToolsAgent
+    
+    mlflow_agent = MLflowToolsAgent(llm)
+
+    mlflow_agent.invoke_agent(user_instructions="List the MLflow experiments")
+
+    mlflow_agent.get_response()
+
+    mlflow_agent.get_internal_messages(markdown=True)
+
+    mlflow_agent.get_ai_message(markdown=True)
+
+    mlflow_agent.get_mlflow_artifacts(as_dataframe=True)
+    
+    ```
+    
+    Returns
+    -------
+    MLflowToolsAgent : langchain.graphs.CompiledStateGraph 
+        An instance of the MLflow Tools Agent.
+    
+    """
+    
+    def __init__(
+        self, 
+        model: Any,
+        mlflow_tracking_uri: Optional[str]=None,
+        mlflow_registry_uri: Optional[str]=None,
+        **react_agent_kwargs,
+    ):
+        self._params = {
+            "model": model,
+            "mlflow_tracking_uri": mlflow_tracking_uri,
+            "mlflow_registry_uri": mlflow_registry_uri,
+            **react_agent_kwargs,
+        }
+        self._compiled_graph = self._make_compiled_graph()
+        self.response = None
+    
+    def _make_compiled_graph(self):
+        """
+        Creates the compiled graph for the agent.
+        """
+        self.response = None
+        return make_mlflow_tools_agent(**self._params)
+    
+    
+    def update_params(self, **kwargs):
+        """
+        Updates the agent's parameters and rebuilds the compiled graph.
+        """
+        for k, v in kwargs.items():
+            self._params[k] = v
+        self._compiled_graph = self._make_compiled_graph()
+        
+    async def ainvoke_agent(
+        self, 
+        user_instructions: str=None, 
+        data_raw: pd.DataFrame=None, 
+        **kwargs
+    ):
+        """
+        Runs the agent with the given user instructions.
+        
+        Parameters:
+        ----------
+        user_instructions : str, optional
+            The user instructions to pass to the agent.
+        data_raw : pd.DataFrame, optional
+            The data to pass to the agent. Used for prediction and tool calls where data is required.
+        kwargs : dict, optional
+            Additional keyword arguments to pass to the agents ainvoke method.
+        
+        """
+        response = await self._compiled_graph.ainvoke(
+            {
+                "user_instructions": user_instructions,
+                "data_raw": data_raw.to_dict() if data_raw is not None else None,
+            }, 
+            **kwargs
+        )
+        self.response = response
+        return None
+    
+    def invoke_agent(
+        self, 
+        user_instructions: str=None, 
+        data_raw: pd.DataFrame=None, 
+        **kwargs
+    ):
+        """
+        Runs the agent with the given user instructions.
+        
+        Parameters:
+        ----------
+        user_instructions : str, optional
+            The user instructions to pass to the agent.
+        data_raw : pd.DataFrame, optional
+            The raw data to pass to the agent. Used for prediction and tool calls where data is required.
+        kwargs : dict, optional
+            Additional keyword arguments to pass to the agents invoke method.
+        
+        """
+        response = self._compiled_graph.invoke(
+            {
+                "user_instructions": user_instructions,
+                "data_raw": data_raw.to_dict() if data_raw is not None else None,
+            },
+            **kwargs
+        )
+        self.response = response
+        return None
+    
+    def get_internal_messages(self, markdown: bool=False):
+        """
+        Returns the internal messages from the agent's response.
+        """
+        pretty_print = "\n\n".join([f"### {msg.type.upper()}\n\nID: {msg.id}\n\nContent:\n\n{msg.content}" for msg in self.response["internal_messages"]])       
+        if markdown:
+            return Markdown(pretty_print)
+        else:
+            return self.response["internal_messages"]
+    
+    def get_mlflow_artifacts(self, as_dataframe: bool=False):
+        """
+        Returns the MLflow artifacts from the agent's response.
+        """
+        if as_dataframe:
+            return pd.DataFrame(self.response["mlflow_artifacts"])
+        else:
+            return self.response["mlflow_artifacts"]
+    
+    def get_ai_message(self, markdown: bool=False):
+        """
+        Returns the AI message from the agent's response.
+        """
+        if markdown:
+            return Markdown(self.response["messages"][0].content)
+        else:
+            return self.response["messages"][0].content
+            
+    
+    
+
+def make_mlflow_tools_agent(
+    model: Any,
+    mlflow_tracking_uri: str=None,
+    mlflow_registry_uri: str=None,
+    **react_agent_kwargs,
+):
+    """
+    MLflow Tool Calling Agent
+    """
+    
+    try:
+        import mlflow
+    except ImportError:
+        return "MLflow is not installed. Please install it by running: !pip install mlflow"
+    
+    if mlflow_tracking_uri is not None:
+        mlflow.set_tracking_uri(mlflow_tracking_uri)
+    
+    if mlflow_registry_uri is not None:
+        mlflow.set_registry_uri(mlflow_registry_uri)
+    
+    class GraphState(AgentState):
+        internal_messages: Annotated[Sequence[BaseMessage], operator.add]
+        user_instructions: str
+        data_raw: dict
+        mlflow_artifacts: dict
+
+    
+    def mflfow_tools_agent(state):
+        """
+        Postprocesses the MLflow state, keeping only the last message
+        and extracting the last tool artifact.
+        """
+        print(format_agent_name(AGENT_NAME))
+        print("    * RUN REACT TOOL-CALLING AGENT")
+        
+        tool_node = ToolNode(
+            tools=tools
+        )
+        
+        mlflow_agent = create_react_agent(
+            model, 
+            tools=tool_node, 
+            state_schema=GraphState,
+            **react_agent_kwargs,
+        )
+        
+        response = mlflow_agent.invoke(
+            {
+                "messages": [("user", state["user_instructions"])],
+                "data_raw": state["data_raw"],
+            },
+        )
+        
+        print("    * POST-PROCESS RESULTS")
+
+        internal_messages = response['messages']
+
+        # Ensure there is at least one AI message
+        if not internal_messages:
+            return {
+                "internal_messages": [],
+                "mlflow_artifacts": None,
+            }
+
+        # Get the last AI message
+        last_ai_message = AIMessage(internal_messages[-1].content, role = AGENT_NAME)
+
+        # Get the last tool artifact safely
+        last_tool_artifact = None
+        if len(internal_messages) > 1:
+            last_message = internal_messages[-2]  # Get second-to-last message
+            if hasattr(last_message, "artifact"):  # Check if it has an "artifact"
+                last_tool_artifact = last_message.artifact
+            elif isinstance(last_message, dict) and "artifact" in last_message:
+                last_tool_artifact = last_message["artifact"]
+
+        return {
+            "messages": [last_ai_message], 
+            "internal_messages": internal_messages,
+            "mlflow_artifacts": last_tool_artifact,
+        }
+
+    
+    workflow = StateGraph(GraphState)
+    
+    workflow.add_node("mlflow_tools_agent", mflfow_tools_agent)
+    
+    workflow.add_edge(START, "mlflow_tools_agent")
+    workflow.add_edge("mlflow_tools_agent", END)
+    
+    app = workflow.compile()
+
+    return app
+    

ai_data_science_team/multiagents/sql_data_analyst.py

@@ -1,6 +1,5 @@
 
 from langchain_core.messages import BaseMessage
-from langgraph.checkpoint.memory import MemorySaver
 from langgraph.types import Checkpointer
 
 from langgraph.graph import START, END, StateGraph
@@ -19,7 +18,7 @@ from IPython.display import Markdown
 from ai_data_science_team.templates import BaseAgent
 from ai_data_science_team.agents import SQLDatabaseAgent, DataVisualizationAgent
 from ai_data_science_team.utils.plotly import plotly_from_dict
-from ai_data_science_team.tools.regex import remove_consecutive_duplicates, get_generic_summary
+from ai_data_science_team.utils.regex import remove_consecutive_duplicates, get_generic_summary
 
 
 class SQLDataAnalyst(BaseAgent):
@@ -91,7 +90,7 @@ class SQLDataAnalyst(BaseAgent):
             self._params[k] = v
         self._compiled_graph = self._make_compiled_graph()
         
-    def ainvoke_agent(self, user_instructions, max_retries:int=3, retry_count:int=0, **kwargs):
+    async def ainvoke_agent(self, user_instructions, max_retries:int=3, retry_count:int=0, **kwargs):
         """
         Asynchronosly nvokes the SQL Data Analyst Multi-Agent.
         
@@ -144,7 +143,7 @@ class SQLDataAnalyst(BaseAgent):
         sql_data_analyst.get_plotly_graph()
         ```
         """
-        response = self._compiled_graph.ainvoke({
+        response = await self._compiled_graph.ainvoke({
             "user_instructions": user_instructions,
             "max_retries": max_retries,
             "retry_count": retry_count,

ai_data_science_team/{tools → parsers}/parsers.py

@@ -3,7 +3,6 @@
 # ***
 # Parsers
 
-from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.output_parsers import BaseOutputParser
 
 import re

ai_data_science_team/templates/agent_templates.py

@@ -12,8 +12,8 @@ import json
 
 from typing import Any, Callable, Dict, Type, Optional, Union, List
 
-from ai_data_science_team.tools.parsers import PythonOutputParser
-from ai_data_science_team.tools.regex import (
+from ai_data_science_team.parsers.parsers import PythonOutputParser
+from ai_data_science_team.utils.regex import (
     relocate_imports_inside_function, 
     add_comments_to_top,
     remove_consecutive_duplicates
@@ -93,7 +93,7 @@ class BaseAgent(CompiledStateGraph):
         
         return self.response
     
-    def ainvoke(
+    async def ainvoke(
         self, 
         input: Union[dict[str, Any], Any], 
         config: Optional[RunnableConfig] = None, 
@@ -110,7 +110,7 @@ class BaseAgent(CompiledStateGraph):
         Returns:
             Any: The agent's response.
         """
-        self.response = self._compiled_graph.ainvoke(input=input, config=config,**kwargs)
+        self.response = await self._compiled_graph.ainvoke(input=input, config=config,**kwargs)
         
         if self.response.get("messages"):
             self.response["messages"] = remove_consecutive_duplicates(self.response["messages"])
@@ -148,7 +148,7 @@ class BaseAgent(CompiledStateGraph):
         
         return self.response
     
-    def astream(
+    async def astream(
         self,
         input: dict[str, Any] | Any,
         config: RunnableConfig | None = None,
@@ -172,7 +172,7 @@ class BaseAgent(CompiledStateGraph):
         Returns:
             Any: The agent's response.
         """
-        self.response = self._compiled_graph.astream(input=input, config=config, stream_mode=stream_mode, **kwargs)
+        self.response = await self._compiled_graph.astream(input=input, config=config, stream_mode=stream_mode, **kwargs)
         
         if self.response.get("messages"):
             self.response["messages"] = remove_consecutive_duplicates(self.response["messages"])