added knowledge to agent level (#1655)

* added knowledge to agent level

* linted

* added doc

* added from suggestions

* added test

* fixes from discussion

* fix docs

* fix test

* rm cassette for knowledge_sources test as its a mock and update agent doc string

* fix test

* rm unused

* linted

src/crewai/agent.py

@@ -1,7 +1,7 @@
 import os
 import shutil
 import subprocess
-from typing import Any, List, Literal, Optional, Union
+from typing import Any, List, Literal, Optional, Union, Dict
 
 from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 
@@ -10,6 +10,8 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.cli.constants import ENV_VARS
 from crewai.llm import LLM
+from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.task import Task
 from crewai.tools import BaseTool
@@ -19,6 +21,7 @@ from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_F
 from crewai.utilities.converter import generate_model_description
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
+from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
 
 
 def mock_agent_ops_provider():
@@ -65,6 +68,7 @@ class Agent(BaseAgent):
             allow_delegation: Whether the agent is allowed to delegate tasks to other agents.
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
+            knowledge_sources: Knowledge sources for the agent.
     """
 
     _times_executed: int = PrivateAttr(default=0)
@@ -122,9 +126,21 @@ class Agent(BaseAgent):
         default="safe",
         description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
     )
+    embedder_config: Optional[Dict[str, Any]] = Field(
+        default=None,
+        description="Embedder configuration for the agent.",
+    )
+    knowledge_sources: Optional[List[BaseKnowledgeSource]] = Field(
+        default=None,
+        description="Knowledge sources for the agent.",
+    )
+    _knowledge: Optional[Knowledge] = PrivateAttr(
+        default=None,
+    )
 
     @model_validator(mode="after")
     def post_init_setup(self):
+        self._set_knowledge()
         self.agent_ops_agent_name = self.role
         unaccepted_attributes = [
             "AWS_ACCESS_KEY_ID",
@@ -232,6 +248,21 @@ class Agent(BaseAgent):
             self.cache_handler = CacheHandler()
         self.set_cache_handler(self.cache_handler)
 
+    def _set_knowledge(self):
+        try:
+            if self.knowledge_sources:
+                knowledge_agent_name = f"{self.role.replace(' ', '_')}"
+                if isinstance(self.knowledge_sources, list) and all(
+                    isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources
+                ):
+                    self._knowledge = Knowledge(
+                        sources=self.knowledge_sources,
+                        embedder_config=self.embedder_config,
+                        collection_name=knowledge_agent_name,
+                    )
+        except (TypeError, ValueError) as e:
+            raise ValueError(f"Invalid Knowledge Configuration: {str(e)}")
+
     def execute_task(
         self,
         task: Task,
@@ -286,17 +317,21 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-        # Integrate the knowledge base
-        if self.crew and self.crew.knowledge:
-            knowledge_snippets = self.crew.knowledge.query([task.prompt()])
-            valid_snippets = [
-                result["context"]
-                for result in knowledge_snippets
-                if result and result.get("context")
-            ]
-            if valid_snippets:
-                formatted_knowledge = "\n".join(valid_snippets)
-                task_prompt += f"\n\nAdditional Information:\n{formatted_knowledge}"
+        if self._knowledge:
+            agent_knowledge_snippets = self._knowledge.query([task.prompt()])
+            if agent_knowledge_snippets:
+                agent_knowledge_context = extract_knowledge_context(
+                    agent_knowledge_snippets
+                )
+                if agent_knowledge_context:
+                    task_prompt += agent_knowledge_context
+
+        if self.crew:
+            knowledge_snippets = self.crew.query_knowledge([task.prompt()])
+            if knowledge_snippets:
+                crew_knowledge_context = extract_knowledge_context(knowledge_snippets)
+                if crew_knowledge_context:
+                    task_prompt += crew_knowledge_context
 
         tools = tools or self.tools or []
         self.create_agent_executor(tools=tools, task=task)