Browser support doesn't work

[adriaanbalt]

In the example:

import gradio as gr
import ai_gradio

# Create a browser automation interface
gr.load(
    name='browser:gpt-4-turbo',
    src=ai_gradio.registry,
    title='AI Browser Assistant',
    description='Let AI help with web tasks'
).launch()

The name='browser:gpt-4-turbo', doesn't work.

I get this error:

Traceback (most recent call last):
  File "/Users/adriaanbalt/PROJECTS/operator/ai_browser.py", line 5, in <module>
    gr.load(
  File "/usr/local/anaconda3/envs/operator/lib/python3.11/site-packages/ai_gradio/providers/__init__.py", line 16, in custom_load
    raise ValueError(f"Model {model_key} not found. Available models: {available_models}")
ValueError: Model browser:gpt-4-turbo not found. Available models: ['openai:gpt-4-turbo', 'openai:gpt-4', 'openai:gpt-3.5-turbo', 'gemini:gemini-pro', 'gemini:gemini-pro-vision', 'gemini:gemini-2.0-flash-exp', 'crewai:gpt-4-turbo', 'crewai:gpt-4', 'crewai:gpt-3.5-turbo']

When I go deeper into what is installed from pip I noticed that the provider folder only includes openai, crewai, gemini. None of the other providers that are within the provider folder are available. Maybe I am downloading the wrong version with pip install ai-gradio and pip install 'ai-gradio[all]'?

If instead of using the remote ai-gradio I fork this project to my local machine and reference the local version I get this error when using browser:gpt-4-turbo:

Traceback (most recent call last):
  File "/Users/adriaanbalt/PROJECTS/operator/ai_browser.py", line 5, in <module>
    gr.load(
  File "/usr/local/anaconda3/envs/operator/lib/python3.11/site-packages/ai_gradio/providers/__init__.py", line 12, in custom_load
    raise ValueError(f"Model {model_key} not found. Available models: {available_models}")
ValueError: Model browser:gpt-4-turbo not found. Available models: ['openai:gpt-4o-2024-11-20', 'openai:gpt-4o', 'openai:gpt-4o-2024-08-06', 'openai:gpt-4o-2024-05-13', 'openai:chatgpt-4o-latest', 'openai:gpt-4o-mini', 'openai:gpt-4o-mini-2024-07-18', 'openai:o1-preview', 'openai:o1-preview-2024-09-12', 'openai:o1-mini', 'openai:o1-mini-2024-09-12', 'openai:gpt-4-turbo', 'openai:gpt-4-turbo-2024-04-09', 'openai:gpt-4-turbo-preview', 'openai:gpt-4-0125-preview', 'openai:gpt-4-1106-preview', 'openai:gpt-4', 'openai:gpt-4-0613', 'openai:o1-2024-12-17', 'openai:gpt-4o-realtime-preview-2024-10-01', 'openai:gpt-4o-realtime-preview', 'openai:gpt-4o-realtime-preview-2024-12-17', 'openai:gpt-4o-mini-realtime-preview', 'openai:gpt-4o-mini-realtime-preview-2024-12-17', 'openai:o3-mini-2025-01-31', 'crewai:gpt-4-turbo', 'crewai:gpt-4', 'crewai:gpt-3.5-turbo', 'xai:grok-beta', 'xai:grok-vision-beta', 'cohere:command-r7b-12-2024', 'cohere:command-light', 'cohere:command-nightly', 'cohere:command-light-nightly', 'sambanova:Meta-Llama-3.1-405B-Instruct', 'sambanova:Meta-Llama-3.1-8B-Instruct', 'sambanova:Meta-Llama-3.1-70B-Instruct', 'sambanova:Meta-Llama-3.1-405B-Instruct-Preview', 'sambanova:Meta-Llama-3.1-8B-Instruct-Preview', 'sambanova:Meta-Llama-3.3-70B-Instruct', 'sambanova:Meta-Llama-3.2-3B-Instruct', 'hyperbolic:Qwen/Qwen2.5-Coder-32B-Instruct', 'hyperbolic:meta-llama/Llama-3.2-3B-Instruct', 'hyperbolic:meta-llama/Meta-Llama-3.1-8B-Instruct', 'hyperbolic:meta-llama/Meta-Llama-3.1-70B-Instruct', 'hyperbolic:meta-llama/Meta-Llama-3-70B-Instruct', 'hyperbolic:NousResearch/Hermes-3-Llama-3.1-70B', 'hyperbolic:Qwen/Qwen2.5-72B-Instruct', 'hyperbolic:deepseek-ai/DeepSeek-V2.5', 'hyperbolic:meta-llama/Meta-Llama-3.1-405B-Instruct', 'hyperbolic:Qwen/QwQ-32B-Preview', 'hyperbolic:meta-llama/Llama-3.3-70B-Instruct', 'hyperbolic:deepseek-ai/DeepSeek-V3', 'hyperbolic:deepseek-ai/DeepSeek-R1', 'hyperbolic:deepseek-ai/DeepSeek-R1-Zero', 'qwen:qwen-turbo-latest', 'qwen:qwen-turbo', 'qwen:qwen-plus', 'qwen:qwen-max', 'qwen:qwen1.5-110b-chat', 'qwen:qwen1.5-72b-chat', 'qwen:qwen1.5-32b-chat', 'qwen:qwen1.5-14b-chat', 'qwen:qwen1.5-7b-chat', 'qwen:qwq-32b-preview', 'qwen:qvq-72b-preview', 'qwen:qwen2.5-14b-instruct-1m', 'qwen:qwen2.5-7b-instruct-1m', 'qwen:qwen-max-0125', 'together:meta-llama/Llama-Vision-Free', 'together:meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo', 'together:meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3-8B-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3-70B-Instruct-Turbo', 'together:meta-llama/Llama-3.2-3B-Instruct-Turbo', 'together:meta-llama/Meta-Llama-3-8B-Instruct-Lite', 'together:meta-llama/Meta-Llama-3-70B-Instruct-Lite', 'together:meta-llama/Llama-3-8b-chat-hf', 'together:meta-llama/Llama-3-70b-chat-hf', 'together:meta-llama/Llama-3.3-70B-Instruct-Turbo', 'together:nvidia/Llama-3.1-Nemotron-70B-Instruct-HF', 'together:Qwen/Qwen2.5-Coder-32B-Instruct', 'together:microsoft/WizardLM-2-8x22B', 'together:databricks/dbrx-instruct', 'together:google/gemma-2-27b-it', 'together:google/gemma-2-9b-it', 'together:google/gemma-2b-it', 'together:mistralai/Mixtral-8x7B-Instruct-v0.1', 'together:mistralai/Mixtral-8x22B-Instruct-v0.1', 'together:Qwen/Qwen2.5-7B-Instruct-Turbo', 'together:Qwen/Qwen2.5-72B-Instruct-Turbo', 'together:Qwen/Qwen2-72B-Instruct', 'together:deepseek-ai/deepseek-llm-67b-chat', 'together:Gryphe/MythoMax-L2-13b', 'together:meta-llama/Llama-2-13b-chat-hf', 'together:mistralai/Mistral-7B-Instruct-v0.1', 'together:mistralai/Mistral-7B-Instruct-v0.2', 'together:mistralai/Mistral-7B-Instruct-v0.3', 'together:NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', 'together:togethercomputer/StripedHyena-Nous-7B', 'together:upstage/SOLAR-10.7B-Instruct-v1.0', 'together:deepseek-ai/DeepSeek-V3', 'together:deepseek-ai/DeepSeek-R1', 'together:mistralai/Mistral-Small-24B-Instruct-2501', 'deepseek:deepseek-chat', 'deepseek:deepseek-coder', 'deepseek:deepseek-vision', 'deepseek:deepseek-reasoner', 'groq:llama3-groq-8b-8192-tool-use-preview', 'groq:llama3-groq-70b-8192-tool-use-preview', 'groq:llama-3.2-1b-preview', 'groq:llama-3.2-3b-preview', 'groq:llama-3.2-11b-vision-preview', 'groq:llama-3.2-90b-vision-preview', 'groq:mixtral-8x7b-32768', 'groq:gemma2-9b-it', 'groq:gemma-7b-it', 'groq:llama-3.3-70b-versatile', 'groq:llama-3.3-70b-specdec', 'groq:deepseek-r1-distill-llama-70b', 'langchain:gpt-4-turbo', 'langchain:gpt-4', 'langchain:gpt-3.5-turbo', 'langchain:gpt-3.5-turbo-0125', 'nvidia:nvidia/llama3-chatqa-1.5-70b', 'nvidia:nvidia/cosmos-nemotron-34b', 'nvidia:nvidia/llama3-chatqa-1.5-8b', 'nvidia:nvidia-nemotron-4-340b-instruct', 'nvidia:meta/llama-3.1-70b-instruct', 'nvidia:meta/codellama-70b', 'nvidia:meta/llama2-70b', 'nvidia:meta/llama3-8b', 'nvidia:meta/llama3-70b', 'nvidia:mistralai/codestral-22b-instruct-v0.1', 'nvidia:mistralai/mathstral-7b-v0.1', 'nvidia:mistralai/mistral-large-2-instruct', 'nvidia:mistralai/mistral-7b-instruct', 'nvidia:mistralai/mistral-7b-instruct-v0.3', 'nvidia:mistralai/mixtral-8x7b-instruct', 'nvidia:mistralai/mixtral-8x22b-instruct', 'nvidia:mistralai/mistral-large', 'nvidia:google/gemma-2b', 'nvidia:google/gemma-7b', 'nvidia:google/gemma-2-2b-it', 'nvidia:google/gemma-2-9b-it', 'nvidia:google/gemma-2-27b-it', 'nvidia:google/codegemma-1.1-7b', 'nvidia:google/codegemma-7b', 'nvidia:google/recurrentgemma-2b', 'nvidia:google/shieldgemma-9b', 'nvidia:microsoft/phi-3-medium-128k-instruct', 'nvidia:microsoft/phi-3-medium-4k-instruct', 'nvidia:microsoft/phi-3-mini-128k-instruct', 'nvidia:microsoft/phi-3-mini-4k-instruct', 'nvidia:microsoft/phi-3-small-128k-instruct', 'nvidia:microsoft/phi-3-small-8k-instruct', 'nvidia:qwen/qwen2-7b-instruct', 'nvidia:databricks/dbrx-instruct', 'nvidia:deepseek-ai/deepseek-coder-6.7b-instruct', 'nvidia:upstage/solar-10.7b-instruct', 'nvidia:snowflake/arctic', 'nvidia:qwen/qwen2.5-7b-instruct', 'nvidia:deepseek-ai/deepseek-r1', 'minimax:MiniMax-Text-01', 'perplexity:sonar-pro', 'perplexity:sonar', 'perplexity:sonar-reasoning']

So it seems like even the version that is in Github isn't working.

I'm excited to mess around with the browser functionality of this project. Thanks so much for working on this!