1 line
24 KiB
JSON
1 line
24 KiB
JSON
{"repo": "agno-agi/docs", "files": {"examples/reasoning/agents/trolley-problem.mdx": {"2c5a11695c8a13de4b8cf1be164317854a9642de": {"t": 1785746500.5485957, "n": 3151, "h": "c9822f25d9a3ef9a", "c": "---\ntitle: \"Trolley Problem Analysis\"\ndescription: \"Solve the trolley problem with ASCII diagrams using a built-in chain-of-thought agent and a deepseek-reasoner-backed agent.\"\nsource: cookbook/10_reasoning/agents/trolley_problem.py\n---\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\n```python trolley_problem.py\n\"\"\"\nTrolley Problem Analysis\n========================\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ncot_prompt = (\n \"Solve the trolley problem. Evaluate multiple ethical frameworks. \"\n \"Include an ASCII diagram of your solution.\"\n)\n\ndeepseek_prompt = (\n \"You are a philosopher tasked with analyzing the classic 'Trolley Problem'. In this scenario, a runaway trolley \"\n \"is barreling down the tracks towards five people who are tied up and unable to move. You are standing next to \"\n \"a large stranger on a footbridge above the tracks. The only way to save the five people is to push this stranger \"\n \"off the bridge onto the tracks below. This will kill the stranger, but save the five people on the tracks. \"\n \"Should you push the stranger to save the five people? Provide a well-reasoned answer considering utilitarian, \"\n \"deontological, and virtue ethics frameworks. \"\n \"Include a simple ASCII art diagram to illustrate the scenario.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(cot_prompt, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(deepseek_prompt, stream=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `trolley_problem.py`, then run:\n ```bash\n python trolley_problem.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/trolley_problem.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/trolley_problem.py)\n"}, "6917c89afd1df7aa2a58b9b9c63f9c8cc19a354e": {"t": 1785764992.515693, "n": 3151, "h": "c9822f25d9a3ef9a", "c": "---\ntitle: \"Trolley Problem Analysis\"\ndescription: \"Solve the trolley problem with ASCII diagrams using a built-in chain-of-thought agent and a deepseek-reasoner-backed agent.\"\nsource: cookbook/10_reasoning/agents/trolley_problem.py\n---\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\n```python trolley_problem.py\n\"\"\"\nTrolley Problem Analysis\n========================\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ncot_prompt = (\n \"Solve the trolley problem. Evaluate multiple ethical frameworks. \"\n \"Include an ASCII diagram of your solution.\"\n)\n\ndeepseek_prompt = (\n \"You are a philosopher tasked with analyzing the classic 'Trolley Problem'. In this scenario, a runaway trolley \"\n \"is barreling down the tracks towards five people who are tied up and unable to move. You are standing next to \"\n \"a large stranger on a footbridge above the tracks. The only way to save the five people is to push this stranger \"\n \"off the bridge onto the tracks below. This will kill the stranger, but save the five people on the tracks. \"\n \"Should you push the stranger to save the five people? Provide a well-reasoned answer considering utilitarian, \"\n \"deontological, and virtue ethics frameworks. \"\n \"Include a simple ASCII art diagram to illustrate the scenario.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(cot_prompt, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(deepseek_prompt, stream=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `trolley_problem.py`, then run:\n ```bash\n python trolley_problem.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/trolley_problem.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/trolley_problem.py)\n"}, "2f2cceffa84d4e0c2e6fca0e69ca010b6c29d67e": {"t": 1785764993.98493, "n": 3026, "h": "bdc32281ea54a6e2", "c": "---\ntitle: \"Trolley Problem Analysis\"\ndescription: \"Demonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\"\nsource: cookbook/10_reasoning/agents/trolley_problem.py\n---\n\n```python trolley_problem.py\n\"\"\"\nTrolley Problem Analysis\n========================\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ncot_prompt = (\n \"Solve the trolley problem. Evaluate multiple ethical frameworks. \"\n \"Include an ASCII diagram of your solution.\"\n)\n\ndeepseek_prompt = (\n \"You are a philosopher tasked with analyzing the classic 'Trolley Problem'. In this scenario, a runaway trolley \"\n \"is barreling down the tracks towards five people who are tied up and unable to move. You are standing next to \"\n \"a large stranger on a footbridge above the tracks. The only way to save the five people is to push this stranger \"\n \"off the bridge onto the tracks below. This will kill the stranger, but save the five people on the tracks. \"\n \"Should you push the stranger to save the five people? Provide a well-reasoned answer considering utilitarian, \"\n \"deontological, and virtue ethics frameworks. \"\n \"Include a simple ASCII art diagram to illustrate the scenario.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(cot_prompt, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(deepseek_prompt, stream=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `trolley_problem.py`, then run:\n ```bash\n python trolley_problem.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/trolley_problem.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/trolley_problem.py)\n"}, "b635e4aba367b4e756cc95854f6313a093210041": {"t": 1785764995.4520795, "n": 2366, "h": "47bffe8d5c31a604", "c": "---\ntitle: \"Trolley Problem Analysis\"\ndescription: \"Demonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\"\n---\n```python\n\"\"\"\nTrolley Problem Analysis\n========================\n\nDemonstrates built-in and DeepSeek-backed reasoning for ethical analysis.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ncot_prompt = (\n \"Solve the trolley problem. Evaluate multiple ethical frameworks. \"\n \"Include an ASCII diagram of your solution.\"\n)\n\ndeepseek_prompt = (\n \"You are a philosopher tasked with analyzing the classic 'Trolley Problem'. In this scenario, a runaway trolley \"\n \"is barreling down the tracks towards five people who are tied up and unable to move. You are standing next to \"\n \"a large stranger on a footbridge above the tracks. The only way to save the five people is to push this stranger \"\n \"off the bridge onto the tracks below. This will kill the stranger, but save the five people on the tracks. \"\n \"Should you push the stranger to save the five people? Provide a well-reasoned answer considering utilitarian, \"\n \"deontological, and virtue ethics frameworks. \"\n \"Include a simple ASCII art diagram to illustrate the scenario.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(cot_prompt, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(deepseek_prompt, stream=True)\n```\n\n## Run the Example\n```bash\n# Clone and setup repo\ngit clone https://github.com/agno-agi/agno.git\ncd agno/cookbook/10_reasoning/agents\n\n# Create and activate virtual environment\n./scripts/demo_setup.sh\nsource .venvs/demo/bin/activate\n\npython trolley_problem.py\n```\n"}}, "examples/reasoning/agents/scientific-research.mdx": {"2c5a11695c8a13de4b8cf1be164317854a9642de": {"t": 1785746505.656262, "n": 3020, "h": "1a0f5674066a5dbb", "c": "---\ntitle: \"Scientific Abstract Critique\"\ndescription: \"Critique a small-sample teaching-method abstract for bias and flawed conclusions, comparing gpt-4o built-in chain-of-thought with a deepseek-reasoner reasoning model.\"\nsource: cookbook/10_reasoning/agents/scientific_research.py\n---\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\n```python scientific_research.py\n\"\"\"\nScientific Abstract Critique\n============================\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ntask = (\n \"Read the following abstract of a scientific paper and provide a critical evaluation of its methodology,\"\n \"results, conclusions, and any potential biases or flaws:\\n\\n\"\n \"Abstract: This study examines the effect of a new teaching method on student performance in mathematics. \"\n \"A sample of 30 students was selected from a single school and taught using the new method over one semester. \"\n \"The results showed a 15% increase in test scores compared to the previous semester. \"\n \"The study concludes that the new teaching method is effective in improving mathematical performance among high school students.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(task, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(task, stream=True, show_full_reasoning=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `scientific_research.py`, then run:\n ```bash\n python scientific_research.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/scientific_research.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/scientific_research.py)\n"}, "6917c89afd1df7aa2a58b9b9c63f9c8cc19a354e": {"t": 1785764992.526958, "n": 3020, "h": "1a0f5674066a5dbb", "c": "---\ntitle: \"Scientific Abstract Critique\"\ndescription: \"Critique a small-sample teaching-method abstract for bias and flawed conclusions, comparing gpt-4o built-in chain-of-thought with a deepseek-reasoner reasoning model.\"\nsource: cookbook/10_reasoning/agents/scientific_research.py\n---\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\n```python scientific_research.py\n\"\"\"\nScientific Abstract Critique\n============================\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ntask = (\n \"Read the following abstract of a scientific paper and provide a critical evaluation of its methodology,\"\n \"results, conclusions, and any potential biases or flaws:\\n\\n\"\n \"Abstract: This study examines the effect of a new teaching method on student performance in mathematics. \"\n \"A sample of 30 students was selected from a single school and taught using the new method over one semester. \"\n \"The results showed a 15% increase in test scores compared to the previous semester. \"\n \"The study concludes that the new teaching method is effective in improving mathematical performance among high school students.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(task, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(task, stream=True, show_full_reasoning=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `scientific_research.py`, then run:\n ```bash\n python scientific_research.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/scientific_research.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/scientific_research.py)\n"}, "2f2cceffa84d4e0c2e6fca0e69ca010b6c29d67e": {"t": 1785764993.9534636, "n": 2852, "h": "f5253da0b883c4f0", "c": "---\ntitle: \"Scientific Abstract Critique\"\ndescription: \"Demonstrates built-in and DeepSeek-backed reasoning for methodology critique.\"\nsource: cookbook/10_reasoning/agents/scientific_research.py\n---\n\n```python scientific_research.py\n\"\"\"\nScientific Abstract Critique\n============================\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ntask = (\n \"Read the following abstract of a scientific paper and provide a critical evaluation of its methodology,\"\n \"results, conclusions, and any potential biases or flaws:\\n\\n\"\n \"Abstract: This study examines the effect of a new teaching method on student performance in mathematics. \"\n \"A sample of 30 students was selected from a single school and taught using the new method over one semester. \"\n \"The results showed a 15% increase in test scores compared to the previous semester. \"\n \"The study concludes that the new teaching method is effective in improving mathematical performance among high school students.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(task, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(task, stream=True, show_full_reasoning=True)\n```\n\n## Run the Example\n\n<Steps>\n <Snippet file=\"create-venv-step.mdx\" />\n\n <Step title=\"Install dependencies\">\n ```bash\n uv pip install -U agno openai\n ```\n </Step>\n\n <Step title=\"Export your API keys\">\n <CodeGroup>\n ```bash Mac/Linux\n export DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n export OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n\n ```bash Windows\n $Env:DEEPSEEK_API_KEY=\"your_deepseek_api_key_here\"\n $Env:OPENAI_API_KEY=\"your_openai_api_key_here\"\n ```\n </CodeGroup>\n </Step>\n\n <Step title=\"Run the example\">\n Save the code above as `scientific_research.py`, then run:\n ```bash\n python scientific_research.py\n ```\n </Step>\n</Steps>\n\nFull source: [cookbook/10_reasoning/agents/scientific_research.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/scientific_research.py)\n"}, "b635e4aba367b4e756cc95854f6313a093210041": {"t": 1785764995.3619556, "n": 2172, "h": "6d63f111ffcb8f13", "c": "---\ntitle: \"Scientific Abstract Critique\"\ndescription: \"Demonstrates built-in and DeepSeek-backed reasoning for methodology critique.\"\n---\n```python\n\"\"\"\nScientific Abstract Critique\n============================\n\nDemonstrates built-in and DeepSeek-backed reasoning for methodology critique.\n\"\"\"\n\nfrom agno.agent import Agent\nfrom agno.models.deepseek import DeepSeek\nfrom agno.models.openai import OpenAIChat\n\n# ---------------------------------------------------------------------------\n# Create Agents\n# ---------------------------------------------------------------------------\ntask = (\n \"Read the following abstract of a scientific paper and provide a critical evaluation of its methodology,\"\n \"results, conclusions, and any potential biases or flaws:\\n\\n\"\n \"Abstract: This study examines the effect of a new teaching method on student performance in mathematics. \"\n \"A sample of 30 students was selected from a single school and taught using the new method over one semester. \"\n \"The results showed a 15% increase in test scores compared to the previous semester. \"\n \"The study concludes that the new teaching method is effective in improving mathematical performance among high school students.\"\n)\n\ncot_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning=True,\n markdown=True,\n)\n\ndeepseek_agent = Agent(\n model=OpenAIChat(id=\"gpt-4o\"),\n reasoning_model=DeepSeek(id=\"deepseek-reasoner\"),\n markdown=True,\n)\n\n# ---------------------------------------------------------------------------\n# Run Agents\n# ---------------------------------------------------------------------------\nif __name__ == \"__main__\":\n print(\"=== Built-in Chain Of Thought ===\")\n cot_agent.print_response(task, stream=True, show_full_reasoning=True)\n\n print(\"\\n=== DeepSeek Reasoning Model ===\")\n deepseek_agent.print_response(task, stream=True, show_full_reasoning=True)\n```\n\n## Run the Example\n```bash\n# Clone and setup repo\ngit clone https://github.com/agno-agi/agno.git\ncd agno/cookbook/10_reasoning/agents\n\n# Create and activate virtual environment\n./scripts/demo_setup.sh\nsource .venvs/demo/bin/activate\n\npython scientific_research.py\n```\n"}}}} |