WIP

docs/concepts/flows.mdx

@@ -48,6 +48,8 @@ class ExampleFlow(Flow):
             ],
         )
 
+        #TODO: NEED TO ADD AN EXAMPLE AGENT IN HERE AS WELL.
+
         random_city = response["choices"][0]["message"]["content"]
         # Store the city in our state
         self.state["city"] = random_city

examples/lite_agent_example.py

@@ -25,7 +25,7 @@ class WebSearchTool(BaseTool):
         """Search the web for information about a topic."""
         # This is a mock implementation
         if "tokyo" in query.lower():
-            return "Tokyo's population in 2023 was approximately 14 million people in the city proper, and 37 million in the greater metropolitan area."
+            return "Tokyo's population in 2023 was approximately 21 million people in the city proper, and 37 million in the greater metropolitan area."
         elif "climate change" in query.lower() and "coral" in query.lower():
             return "Climate change severely impacts coral reefs through: 1) Ocean warming causing coral bleaching, 2) Ocean acidification reducing calcification, 3) Sea level rise affecting light availability, 4) Increased storm frequency damaging reef structures. Sources: NOAA Coral Reef Conservation Program, Global Coral Reef Alliance."
         else:
@@ -80,8 +80,8 @@ async def main():
     # print(f"Raw response: {result.raw}")
 
     # Example 2: Query with structured output
-    # print("\n=== Example 2: Structured Output ===")
-    # structured_query = """
+    print("\n=== Example 2: Structured Output ===")
+    structured_query = """
     # Research the impact of climate change on coral reefs.
 
     # YOU MUST format your response as a valid JSON object with the following structure:
@@ -94,48 +94,48 @@ async def main():
     # Include at least 3 key points and 2 sources. Wrap your JSON in ```json and ``` tags.
     # """
 
-    # result = await agent.kickoff_async(structured_query)
+    result = await agent.kickoff_async(structured_query)
 
-    # if result.pydantic:
-    #     # Cast to the specific type for better IDE support
-    #     research_result = cast(ResearchResult, result.pydantic)
-    #     print(f"Main findings: {research_result.main_findings}")
-    #     print("\nKey points:")
-    #     for i, point in enumerate(research_result.key_points, 1):
-    #         print(f"{i}. {point}")
-    #     print("\nSources:")
-    #     for i, source in enumerate(research_result.sources, 1):
-    #         print(f"{i}. {source}")
-    # else:
-    #     print(f"Raw response: {result.raw}")
-    #     print(
-    #         "\nNote: Structured output was not generated. The LLM may need more explicit instructions to format the response as JSON."
-    #     )
-    # print("Usage metrics:")
-    # print(result.usage_metrics)
+    if result.pydantic:
+        # Cast to the specific type for better IDE support
+        research_result = cast(ResearchResult, result.pydantic)
+        print(f"Main findings: {research_result.main_findings}")
+        print("\nKey points:")
+        for i, point in enumerate(research_result.key_points, 1):
+            print(f"{i}. {point}")
+        print("\nSources:")
+        for i, source in enumerate(research_result.sources, 1):
+            print(f"{i}. {source}")
+    else:
+        print(f"Raw response: {result.raw}")
+        print(
+            "\nNote: Structured output was not generated. The LLM may need more explicit instructions to format the response as JSON."
+        )
+    print("Usage metrics:")
+    print(result.usage_metrics)
 
-    # Example 3: Multi-turn conversation
-    print("\n=== Example 3: Multi-turn Conversation ===")
-    messages = [
-        {"role": "user", "content": "I'm planning a trip to Japan."},
-        {
-            "role": "assistant",
-            "content": "That sounds exciting! Japan is a beautiful country with rich culture, delicious food, and stunning landscapes. What would you like to know about Japan to help with your trip planning?",
-        },
-        {
-            "role": "user",
-            "content": "What are the best times to visit Tokyo and Kyoto?",
-        },
-    ]
+    # # Example 3: Multi-turn conversation
+    # print("\n=== Example 3: Multi-turn Conversation ===")
+    # messages = [
+    #     {"role": "user", "content": "I'm planning a trip to Japan."},
+    #     {
+    #         "role": "assistant",
+    #         "content": "That sounds exciting! Japan is a beautiful country with rich culture, delicious food, and stunning landscapes. What would you like to know about Japan to help with your trip planning?",
+    #     },
+    #     {
+    #         "role": "user",
+    #         "content": "What are the best times to visit Tokyo and Kyoto?",
+    #     },
+    # ]
 
-    result = await agent.kickoff_async(messages)
-    print(f"Response: {result.raw}")
+    # result = await agent.kickoff_async(messages)
+    # print(f"Response: {result.raw}")
 
-    # Print usage metrics if available
-    if result.usage_metrics:
-        print("\nUsage metrics:")
-        for key, value in result.usage_metrics.items():
-            print(f"{key}: {value}")
+    # # Print usage metrics if available
+    # if result.usage_metrics:
+    #     print("\nUsage metrics:")
+    #     for key, value in result.usage_metrics.items():
+    #         print(f"{key}: {value}")
 
 
 if __name__ == "__main__":

src/crewai/lite_agent.py

@@ -14,12 +14,10 @@ from crewai.agents.parser import (
     AgentFinish,
     OutputParserException,
 )
-from crewai.agents.tools_handler import ToolsHandler
 from crewai.llm import LLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
-from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N
 from crewai.utilities.agent_utils import (
     enforce_rpm_limit,
@@ -230,8 +228,6 @@ class LiteAgent(BaseModel):
                 response_format=schema
             )
 
-        print("BASE PROMPT:", base_prompt)
-
         return base_prompt
 
     def _format_messages(
@@ -310,7 +306,7 @@ class LiteAgent(BaseModel):
             )
 
             # Execute the agent using invoke loop
-            agent_finish = await self._invoke()
+            agent_finish = await self._invoke_loop()
 
             formatted_result: Optional[BaseModel] = None
             if self.response_format:
@@ -350,16 +346,13 @@ class LiteAgent(BaseModel):
                 raise e
             raise e
 
-    async def _invoke(self) -> AgentFinish:
+    async def _invoke_loop(self) -> AgentFinish:
         """
         Run the agent's thought process until it reaches a conclusion or max iterations.
-        Similar to _invoke_loop in CrewAgentExecutor.
 
         Returns:
             str: The final result of the agent execution.
         """
-        # Use the stored callbacks
-        callbacks = self._callbacks
 
         # Execute the agent loop
         formatted_answer = None
@@ -372,7 +365,7 @@ class LiteAgent(BaseModel):
                         i18n=self.i18n,
                         messages=self._messages,
                         llm=cast(LLM, self.llm),
-                        callbacks=callbacks,
+                        callbacks=self._callbacks,
                     )
 
                 enforce_rpm_limit(self.request_within_rpm_limit)
@@ -380,7 +373,7 @@ class LiteAgent(BaseModel):
                 answer = get_llm_response(
                     llm=cast(LLM, self.llm),
                     messages=self._messages,
-                    callbacks=callbacks,
+                    callbacks=self._callbacks,
                     printer=self._printer,
                 )
                 formatted_answer = process_llm_response(answer, self.use_stop_words)