Eval models

Author: MagMueller

eval/deepseek-r1.py

@@ -0,0 +1,24 @@
+import os
+
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from pydantic import SecretStr
+
+from browser_use import Agent
+
+load_dotenv()
+
+api_key_deepseek = os.getenv('DEEPSEEK_API_KEY', '')
+if not api_key_deepseek:
+	raise ValueError('DEEPSEEK_API_KEY is not set')
+
+
+async def run_agent(task: str, max_steps: int = 38):
+	llm = ChatOpenAI(
+		base_url='https://api.deepseek.com/v1',
+		model='deepseek-reasoner',
+		api_key=SecretStr(api_key_deepseek),
+	)
+	agent = Agent(task=task, llm=llm, use_vision=False)
+	result = await agent.run(max_steps=max_steps)
+	return result

eval/deepseek.py

@@ -0,0 +1,24 @@
+import os
+
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from pydantic import SecretStr
+
+from browser_use import Agent
+
+load_dotenv()
+
+api_key_deepseek = os.getenv('DEEPSEEK_API_KEY', '')
+if not api_key_deepseek:
+	raise ValueError('DEEPSEEK_API_KEY is not set')
+
+
+async def run_agent(task: str, max_steps: int = 38):
+	llm = ChatOpenAI(
+		base_url='https://api.deepseek.com/v1',
+		model='deepseek-chat',
+		api_key=SecretStr(api_key_deepseek),
+	)
+	agent = Agent(task=task, llm=llm, use_vision=False)
+	result = await agent.run(max_steps=max_steps)
+	return result

eval/gemini-1.5-flash.py

@@ -0,0 +1,20 @@
+import os
+
+from dotenv import load_dotenv
+from langchain_google_genai import ChatGoogleGenerativeAI
+from pydantic import SecretStr
+
+from browser_use import Agent
+
+load_dotenv()
+
+api_key = os.getenv('GEMINI_API_KEY', '')
+if not api_key:
+	raise ValueError('GEMINI_API_KEY is not set')
+
+
+async def run_agent(task: str, max_steps: int = 38):
+	llm = ChatGoogleGenerativeAI(model='gemini-1.5-flash-latest', api_key=SecretStr(api_key))
+	agent = Agent(task=task, llm=llm)
+	result = await agent.run(max_steps=max_steps)
+	return result

eval/gemini-2.0-flash.py

@@ -0,0 +1,20 @@
+import os
+
+from dotenv import load_dotenv
+from langchain_google_genai import ChatGoogleGenerativeAI
+from pydantic import SecretStr
+
+from browser_use import Agent
+
+load_dotenv()
+
+api_key = os.getenv('GEMINI_API_KEY', '')
+if not api_key:
+	raise ValueError('GEMINI_API_KEY is not set')
+
+
+async def run_agent(task: str, max_steps: int = 38):
+	llm = ChatGoogleGenerativeAI(model='gemini-2.0-flash-exp', api_key=SecretStr(api_key))
+	agent = Agent(task=task, llm=llm)
+	result = await agent.run(max_steps=max_steps)
+	return result