Feat yaml config all attributes (#985)

* WIP: yaml proper mapping for agents and agent * WIP: added output_json and output_pydantic setup * WIP: core logic added, need cleanup * code cleanup * updated docs and example template to use yaml to reference agents within tasks * cleanup type errors * Update Start-a-New-CrewAI-Project.md --------- Co-authored-by: João Moura <[email protected]>
crewAIInc · Jul 23, 2024 · 4da5cc9 · 4da5cc9
1 parent 6930656
commit 4da5cc9
Show file tree

Hide file tree

Showing 6 changed files with 267 additions and 8 deletions.
diff --git a/docs/how-to/Start-a-New-CrewAI-Project.md b/docs/how-to/Start-a-New-CrewAI-Project.md
@@ -79,8 +79,75 @@ research_candidates_task:
     {job_requirements}
   expected_output: >
     A list of 10 potential candidates with their contact information and brief profiles highlighting their suitability.
+  agent: researcher # THIS NEEDS TO MATCH THE AGENT NAME IN THE AGENTS.YAML FILE AND THE AGENT DEFINED IN THE Crew.PY FILE
+  context: # THESE NEED TO MATCH THE TASK NAMES DEFINED ABOVE AND THE TASKS.YAML FILE AND THE TASK DEFINED IN THE Crew.PY FILE
+    - researcher
 ```
 
+### Referencing Variables:
+Your defined functions with the same name will be used. For example, you can reference the agent for specific tasks from task.yaml file. Ensure your annotated agent and function name is the same otherwise your task wont recognize the reference properly.
+
+#### Example References
+agent.yaml
+```yaml
+email_summarizer:
+    role: >
+      Email Summarizer
+    goal: >
+      Summarize emails into a concise and clear summary
+    backstory: >
+      You will create a 5 bullet point summary of the report
+    llm: mixtal_llm
+```
+
+task.yaml
+```yaml
+email_summarizer_task:
+    description: >
+      Summarize the email into a 5 bullet point summary
+    expected_output: >
+      A 5 bullet point summary of the email
+    agent: email_summarizer
+    context:
+      - reporting_task
+      - research_task
+```
+
+Use the annotations are used to properly reference the agent and task in the crew.py file.
+Annotations include:
+- @agent
+- @task
+- @crew
+- @llm
+- @tool
+- @callback
+- @output_json
+- @output_pydantic
+- @cache_handler
+
+crew.py
+```py
+...
+    @llm
+    def mixtal_llm(self):
+        return ChatGroq(temperature=0, model_name="mixtral-8x7b-32768")
+
+    @agent
+    def email_summarizer(self) -> Agent:
+        return Agent(
+            config=self.agents_config["email_summarizer"],
+        )
+    ## ...other tasks defined
+    @task
+    def email_summarizer_task(self) -> Task:
+        return Task(
+            config=self.tasks_config["email_summarizer_task"],
+        )
+...
+```
+
+
+
 ## Installing Dependencies
 
 To install the dependencies for your project, you can use Poetry. First, navigate to your project directory:

diff --git a/src/crewai/cli/templates/config/tasks.yaml b/src/crewai/cli/templates/config/tasks.yaml
@@ -5,6 +5,7 @@ research_task:
     the current year is 2024.
   expected_output: >
     A list with 10 bullet points of the most relevant information about {topic}
+  agent: researcher
 
 reporting_task:
   description: >
@@ -13,3 +14,4 @@ reporting_task:
   expected_output: >
     A fully fledge reports with the mains topics, each with a full section of information.
     Formatted as markdown without '```'
+  agent: reporting_analyst
diff --git a/src/crewai/cli/templates/crew.py b/src/crewai/cli/templates/crew.py
@@ -32,14 +32,12 @@ def reporting_analyst(self) -> Agent:
 	def research_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['research_task'],
-			agent=self.researcher()
 		)
 
 	@task
 	def reporting_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['reporting_task'],
-			agent=self.reporting_analyst(),
 			output_file='report.md'
 		)
 

diff --git a/src/crewai/project/__init__.py b/src/crewai/project/__init__.py
@@ -1,2 +1,25 @@
-from .annotations import agent, crew, task
+from .annotations import (
+    agent,
+    crew,
+    task,
+    output_json,
+    output_pydantic,
+    tool,
+    callback,
+    llm,
+    cache_handler,
+)
 from .crew_base import CrewBase
+
+__all__ = [
+    "agent",
+    "crew",
+    "task",
+    "output_json",
+    "output_pydantic",
+    "tool",
+    "callback",
+    "CrewBase",
+    "llm",
+    "cache_handler",
+]
diff --git a/src/crewai/project/annotations.py b/src/crewai/project/annotations.py
@@ -30,6 +30,37 @@ def agent(func):
     return func
 
 
+def llm(func):
+    func.is_llm = True
+    func = memoize(func)
+    return func
+
+
+def output_json(cls):
+    cls.is_output_json = True
+    return cls
+
+
+def output_pydantic(cls):
+    cls.is_output_pydantic = True
+    return cls
+
+
+def tool(func):
+    func.is_tool = True
+    return memoize(func)
+
+
+def callback(func):
+    func.is_callback = True
+    return memoize(func)
+
+
+def cache_handler(func):
+    func.is_cache_handler = True
+    return memoize(func)
+
+
 def crew(func):
     def wrapper(self, *args, **kwargs):
         instantiated_tasks = []

diff --git a/src/crewai/project/crew_base.py b/src/crewai/project/crew_base.py
@@ -1,6 +1,7 @@
 import inspect
 import os
 from pathlib import Path
+from typing import Any, Callable, Dict
 
 import yaml
 from dotenv import load_dotenv
@@ -20,29 +21,166 @@ class WrappedClass(cls):
                 base_directory = Path(frame_info.filename).parent.resolve()
                 break
 
-        if base_directory is None:
-            raise Exception(
-                "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
-            )
-
         original_agents_config_path = getattr(
             cls, "agents_config", "config/agents.yaml"
         )
         original_tasks_config_path = getattr(cls, "tasks_config", "config/tasks.yaml")
 
         def __init__(self, *args, **kwargs):
             super().__init__(*args, **kwargs)
+
+            if self.base_directory is None:
+                raise Exception(
+                    "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
+                )
+
             self.agents_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_agents_config_path)
             )
             self.tasks_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_tasks_config_path)
             )
+            self.map_all_agent_variables()
+            self.map_all_task_variables()
 
         @staticmethod
         def load_yaml(config_path: str):
             with open(config_path, "r") as file:
                 # parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
                 return yaml.safe_load(file)
 
+        def _get_all_functions(self):
+            return {
+                name: getattr(self, name)
+                for name in dir(self)
+                if callable(getattr(self, name))
+            }
+
+        def _filter_functions(
+            self, functions: Dict[str, Callable], attribute: str
+        ) -> Dict[str, Callable]:
+            return {
+                name: func
+                for name, func in functions.items()
+                if hasattr(func, attribute)
+            }
+
+        def map_all_agent_variables(self) -> None:
+            all_functions = self._get_all_functions()
+            llms = self._filter_functions(all_functions, "is_llm")
+            tool_functions = self._filter_functions(all_functions, "is_tool")
+            cache_handler_functions = self._filter_functions(
+                all_functions, "is_cache_handler"
+            )
+            callbacks = self._filter_functions(all_functions, "is_callback")
+            agents = self._filter_functions(all_functions, "is_agent")
+
+            for agent_name, agent_info in self.agents_config.items():
+                self._map_agent_variables(
+                    agent_name,
+                    agent_info,
+                    agents,
+                    llms,
+                    tool_functions,
+                    cache_handler_functions,
+                    callbacks,
+                )
+
+        def _map_agent_variables(
+            self,
+            agent_name: str,
+            agent_info: Dict[str, Any],
+            agents: Dict[str, Callable],
+            llms: Dict[str, Callable],
+            tool_functions: Dict[str, Callable],
+            cache_handler_functions: Dict[str, Callable],
+            callbacks: Dict[str, Callable],
+        ) -> None:
+            if llm := agent_info.get("llm"):
+                self.agents_config[agent_name]["llm"] = llms[llm]()
+
+            if tools := agent_info.get("tools"):
+                self.agents_config[agent_name]["tools"] = [
+                    tool_functions[tool]() for tool in tools
+                ]
+
+            if function_calling_llm := agent_info.get("function_calling_llm"):
+                self.agents_config[agent_name]["function_calling_llm"] = agents[
+                    function_calling_llm
+                ]()
+
+            if step_callback := agent_info.get("step_callback"):
+                self.agents_config[agent_name]["step_callback"] = callbacks[
+                    step_callback
+                ]()
+
+            if cache_handler := agent_info.get("cache_handler"):
+                self.agents_config[agent_name]["cache_handler"] = (
+                    cache_handler_functions[cache_handler]()
+                )
+
+        def map_all_task_variables(self) -> None:
+            all_functions = self._get_all_functions()
+            agents = self._filter_functions(all_functions, "is_agent")
+            tasks = self._filter_functions(all_functions, "is_task")
+            output_json_functions = self._filter_functions(
+                all_functions, "is_output_json"
+            )
+            tool_functions = self._filter_functions(all_functions, "is_tool")
+            callback_functions = self._filter_functions(all_functions, "is_callback")
+            output_pydantic_functions = self._filter_functions(
+                all_functions, "is_output_pydantic"
+            )
+
+            for task_name, task_info in self.tasks_config.items():
+                self._map_task_variables(
+                    task_name,
+                    task_info,
+                    agents,
+                    tasks,
+                    output_json_functions,
+                    tool_functions,
+                    callback_functions,
+                    output_pydantic_functions,
+                )
+
+        def _map_task_variables(
+            self,
+            task_name: str,
+            task_info: Dict[str, Any],
+            agents: Dict[str, Callable],
+            tasks: Dict[str, Callable],
+            output_json_functions: Dict[str, Callable],
+            tool_functions: Dict[str, Callable],
+            callback_functions: Dict[str, Callable],
+            output_pydantic_functions: Dict[str, Callable],
+        ) -> None:
+            if context_list := task_info.get("context"):
+                self.tasks_config[task_name]["context"] = [
+                    tasks[context_task_name]() for context_task_name in context_list
+                ]
+
+            if tools := task_info.get("tools"):
+                self.tasks_config[task_name]["tools"] = [
+                    tool_functions[tool]() for tool in tools
+                ]
+
+            if agent_name := task_info.get("agent"):
+                self.tasks_config[task_name]["agent"] = agents[agent_name]()
+
+            if output_json := task_info.get("output_json"):
+                self.tasks_config[task_name]["output_json"] = output_json_functions[
+                    output_json
+                ]
+
+            if output_pydantic := task_info.get("output_pydantic"):
+                self.tasks_config[task_name]["output_pydantic"] = (
+                    output_pydantic_functions[output_pydantic]
+                )
+
+            if callbacks := task_info.get("callbacks"):
+                self.tasks_config[task_name]["callbacks"] = [
+                    callback_functions[callback]() for callback in callbacks
+                ]
+
     return WrappedClass