Merge pull request #8 from warmshao/dev

Dev

Author: warmshao

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

@@ -1,4 +1,5 @@
 browser-use
 langchain-google-genai
 pyperclip
-gradio
+gradio
+langchain-ollama

src/utils/utils.py

@@ -11,6 +11,7 @@
 from langchain_openai import ChatOpenAI, AzureChatOpenAI
 from langchain_anthropic import ChatAnthropic
 from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_ollama import ChatOllama
 
 
 def get_llm_model(provider: str, **kwargs):
@@ -39,7 +40,7 @@ def get_llm_model(provider: str, **kwargs):
         )
     elif provider == 'openai':
         if not kwargs.get("base_url", ""):
-            base_url = "https://api.openai.com/v1"
+            base_url = os.getenv("OPENAI_ENDPOINT", "https://api.openai.com/v1")
         else:
             base_url = kwargs.get("base_url")
 
@@ -66,7 +67,7 @@ def get_llm_model(provider: str, **kwargs):
             api_key = kwargs.get("api_key")
 
         return ChatOpenAI(
-            model=kwargs.get("model_name", 'gpt-4o'),
+            model=kwargs.get("model_name", 'deepseek-chat'),
             temperature=kwargs.get("temperature", 0.0),
             base_url=base_url,
             api_key=api_key
@@ -81,6 +82,11 @@ def get_llm_model(provider: str, **kwargs):
             temperature=kwargs.get("temperature", 0.0),
             google_api_key=api_key,
         )
+    elif provider == 'ollama':
+        return ChatOllama(
+            model=kwargs.get("model_name", 'qwen2.5:7b'),
+            temperature=kwargs.get("temperature", 0.0),
+        )
     elif provider == "azure_openai":
         if not kwargs.get("base_url", ""):
             base_url = os.getenv("AZURE_OPENAI_ENDPOINT", "")

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

@@ -255,7 +255,8 @@ def main():
             use_vision = gr.Checkbox(label="use vision", value=True)
         with gr.Row():
             llm_provider = gr.Dropdown(
-                ["anthropic", "openai", "gemini", "azure_openai", "deepseek"], label="LLM Provider", value="gemini"
+                ["anthropic", "openai", "gemini", "azure_openai", "deepseek", "ollama"], label="LLM Provider",
+                value="gemini"
             )
             llm_model_name = gr.Textbox(label="LLM Model Name", value="gemini-2.0-flash-exp")
             llm_temperature = gr.Number(label="LLM Temperature", value=1.0)