Merge branch 'main' into main

README.md

@@ -6,7 +6,7 @@ This project builds upon the foundation of the [browser-use](https://github.com/
 
 1.  **A Brand New WebUI:** We offer a comprehensive web interface that supports a wide range of `browser-use` functionalities. This UI is designed to be user-friendly and enables easy interaction with the browser agent.
 
-2.  **Expanded LLM Support:** We've integrated support for various Large Language Models (LLMs), including: Gemini, OpenAI, Azure OpenAI, Anthropic, DeepSeek etc. And we plan to add support for even more models in the future.
+2.  **Expanded LLM Support:** We've integrated support for various Large Language Models (LLMs), including: Gemini, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama etc. And we plan to add support for even more models in the future.
 
 3.  **Custom Browser Support:** You can use your own browser with our tool, eliminating the need to re-login to sites or deal with other authentication challenges. This feature also supports high-definition screen recording.
 

requirements.txt

@@ -3,3 +3,4 @@ langchain-google-genai
 pyperclip
 gradio
 langchain-ollama
+

tests/test_browser_use.py

@@ -105,9 +105,15 @@ async def test_browser_use_custom():
     #     api_key=os.getenv("GOOGLE_API_KEY", "")
     # )
 
+    # llm = utils.get_llm_model(
+    #     provider="deepseek",
+    #     model_name="deepseek-chat",
+    #     temperature=0.8
+    # )
+
     llm = utils.get_llm_model(
-        provider="deepseek",
-        model_name="deepseek-chat",
+        provider="ollama",
+        model_name="qwen2.5:7b",
         temperature=0.8
     )
 

tests/test_llm_api.py

@@ -106,7 +106,6 @@ def test_deepseek_model():
         base_url=os.getenv("DEEPSEEK_ENDPOINT", ""),
         api_key=os.getenv("DEEPSEEK_API_KEY", "")
     )
-    pdb.set_trace()
     message = HumanMessage(
         content=[
             {"type": "text", "text": "who are you?"}
@@ -116,8 +115,17 @@ def test_deepseek_model():
     print(ai_msg.content)
 
 
+def test_ollama_model():
+    from langchain_ollama import ChatOllama
+
+    llm = ChatOllama(model="qwen2.5:7b")
+    ai_msg = llm.invoke("Sing a ballad of LangChain.")
+    print(ai_msg.content)
+
+
 if __name__ == '__main__':
     # test_openai_model()
     # test_gemini_model()
     # test_azure_openai_model()
-    test_deepseek_model()
+    # test_deepseek_model()
+    test_ollama_model()

webui.py

@@ -260,6 +260,7 @@ def create_ui(theme_name="Ocean"):
     
     with gr.Blocks(title="Browser Use WebUI", theme=theme_map[theme_name], css=css) as demo:
         with gr.Row():
+
             gr.Markdown(
                 """
                 # 🌐 Browser Use WebUI
@@ -303,7 +304,7 @@ def create_ui(theme_name="Ocean"):
             with gr.TabItem("🔧 LLM Configuration", id=2):
                 with gr.Group():
                     llm_provider = gr.Dropdown(
-                        ["anthropic", "openai", "gemini", "azure_openai", "deepseek"],
+                        ["anthropic", "openai", "gemini", "azure_openai", "deepseek", "ollama"],
                         label="LLM Provider",
                         value="gemini",
                         info="Select your preferred language model provider"