add 13 options of LLM support

workflows/.env.example

@@ -1,2 +1,42 @@
 # We support all langchain models, openai only for demo purposes
-OPENAI_API_KEY=
+LLM_PROVIDER="openai"
+MODEL_NAME="gpt-4o"
+
+OPENAI_ENDPOINT=https://api.openai.com/v1
+OPENAI_API_KEY=
+
+ANTHROPIC_API_KEY=
+ANTHROPIC_ENDPOINT=https://api.anthropic.com
+
+GOOGLE_API_KEY=
+
+AZURE_OPENAI_ENDPOINT=
+AZURE_OPENAI_API_KEY=
+AZURE_OPENAI_API_VERSION=2025-01-01-preview
+
+DEEPSEEK_ENDPOINT=https://api.deepseek.com
+DEEPSEEK_API_KEY=
+
+MISTRAL_API_KEY=
+MISTRAL_ENDPOINT=https://api.mistral.ai/v1
+
+OLLAMA_ENDPOINT=http://localhost:11434
+
+ALIBABA_ENDPOINT=https://dashscope.aliyuncs.com/compatible-mode/v1
+ALIBABA_API_KEY=
+
+MOONSHOT_ENDPOINT=https://api.moonshot.cn/v1
+MOONSHOT_API_KEY=
+
+UNBOUND_ENDPOINT=https://api.getunbound.ai
+UNBOUND_API_KEY=
+
+SiliconFLOW_ENDPOINT=https://api.siliconflow.cn/v1/
+SiliconFLOW_API_KEY=
+
+IBM_ENDPOINT=https://us-south.ml.cloud.ibm.com
+IBM_API_KEY=
+IBM_PROJECT_ID=
+
+GROK_ENDPOINT="https://api.x.ai/v1"
+GROK_API_KEY=

workflows/cli.py

@@ -1,22 +1,24 @@
+from dotenv import load_dotenv
+load_dotenv()
 import asyncio
 import json
 import os
 import subprocess
 import tempfile  # For temporary file handling
 import webbrowser
 from pathlib import Path
+import os
 
 import typer
 from browser_use.browser.browser import Browser
 
-# Assuming OPENAI_API_KEY is set in the environment
-from langchain_openai import ChatOpenAI
-
 from workflow_use.builder.service import BuilderService
 from workflow_use.controller.service import WorkflowController
 from workflow_use.mcp.service import get_mcp_server
 from workflow_use.recorder.service import RecordingService  # Added import
 from workflow_use.workflow.service import Workflow
+from workflow_use.llm.llm_provider import get_llm_model
+from workflow_use.llm.config import model_names
 
 # Placeholder for recorder functionality
 # from src.recorder.service import RecorderService
@@ -31,15 +33,27 @@
 # Default LLM instance to None
 llm_instance = None
 try:
-	llm_instance = ChatOpenAI(model='gpt-4o')
-	page_extraction_llm = ChatOpenAI(model='gpt-4o-mini')
+    # Get provider and model name from environment or default to openai
+    provider = os.getenv("LLM_PROVIDER", "openai").lower()
+    model_name = os.getenv("MODEL_NAME", "")
+
+    # If no model name specified, prompt user
+    if not model_name:
+        typer.echo(f"Available models for {provider}:")
+        typer.echo(f"{model_names[provider]}")
+
+        model_name = typer.prompt(f"model name for {provider}, default=", default=model_names[provider][0])
+        os.environ["MODEL_NAME"] = model_name
+
+    # Initialize LLM with selected provider and model
+    llm_instance = get_llm_model(provider, model_name=model_name)
+    page_extraction_llm = get_llm_model(provider, model_name=model_name)
+
 except Exception as e:
-	typer.secho(f'Error initializing LLM: {e}. Would you like to set your OPENAI_API_KEY?', fg=typer.colors.RED)
-	set_openai_api_key = input('Set OPENAI_API_KEY? (y/n): ')
-	if set_openai_api_key.lower() == 'y':
-		os.environ['OPENAI_API_KEY'] = input('Enter your OPENAI_API_KEY: ')
-		llm_instance = ChatOpenAI(model='gpt-4o')
-		page_extraction_llm = ChatOpenAI(model='gpt-4o-mini')
+    typer.secho(
+        f"Error initializing LLM: {e}. Would you like to set your API key?",
+        fg=typer.colors.RED,
+    )
 
 builder_service = BuilderService(llm=llm_instance) if llm_instance else None
 # recorder_service = RecorderService() # Placeholder

workflows/workflow_use/llm/config.py

@@ -0,0 +1,87 @@
+# Predefined model names for common providers
+model_names = {
+    "anthropic": ["claude-3-5-sonnet-20241022", "claude-3-5-sonnet-20240620", "claude-3-opus-20240229"],
+    "openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo", "o3-mini"],
+    "deepseek": ["deepseek-chat", "deepseek-reasoner"],
+    "google": ["gemini-2.0-flash", "gemini-2.0-flash-thinking-exp", "gemini-1.5-flash-latest",
+               "gemini-1.5-flash-8b-latest", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-pro-exp-02-05",
+               "gemini-2.5-pro-preview-03-25", "gemini-2.5-flash-preview-04-17"],
+    "ollama": ["qwen2.5:7b", "qwen2.5:14b", "qwen2.5:32b", "qwen2.5-coder:14b", "qwen2.5-coder:32b", "llama2:7b",
+               "deepseek-r1:14b", "deepseek-r1:32b"],
+    "azure_openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo"],
+    "mistral": ["pixtral-large-latest", "mistral-large-latest", "mistral-small-latest", "ministral-8b-latest"],
+    "alibaba": ["qwen-plus", "qwen-max", "qwen-vl-max", "qwen-vl-plus", "qwen-turbo", "qwen-long"],
+    "moonshot": ["moonshot-v1-32k-vision-preview", "moonshot-v1-8k-vision-preview"],
+    "unbound": ["gemini-2.0-flash", "gpt-4o-mini", "gpt-4o", "gpt-4.5-preview"],
+    "grok": [
+        "grok-3",
+        "grok-3-fast",
+        "grok-3-mini",
+        "grok-3-mini-fast",
+        "grok-2-vision",
+        "grok-2-image",
+        "grok-2",
+    ],
+    "siliconflow": [
+        "deepseek-ai/DeepSeek-R1",
+        "deepseek-ai/DeepSeek-V3",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+        "deepseek-ai/DeepSeek-V2.5",
+        "deepseek-ai/deepseek-vl2",
+        "Qwen/Qwen2.5-72B-Instruct-128K",
+        "Qwen/Qwen2.5-72B-Instruct",
+        "Qwen/Qwen2.5-32B-Instruct",
+        "Qwen/Qwen2.5-14B-Instruct",
+        "Qwen/Qwen2.5-7B-Instruct",
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Qwen/Qwen2.5-Coder-7B-Instruct",
+        "Qwen/Qwen2-7B-Instruct",
+        "Qwen/Qwen2-1.5B-Instruct",
+        "Qwen/QwQ-32B-Preview",
+        "Qwen/Qwen2-VL-72B-Instruct",
+        "Qwen/Qwen2.5-VL-32B-Instruct",
+        "Qwen/Qwen2.5-VL-72B-Instruct",
+        "TeleAI/TeleChat2",
+        "THUDM/glm-4-9b-chat",
+        "Vendor-A/Qwen/Qwen2.5-72B-Instruct",
+        "internlm/internlm2_5-7b-chat",
+        "internlm/internlm2_5-20b-chat",
+        "Pro/Qwen/Qwen2.5-7B-Instruct",
+        "Pro/Qwen/Qwen2-7B-Instruct",
+        "Pro/Qwen/Qwen2-1.5B-Instruct",
+        "Pro/THUDM/chatglm3-6b",
+        "Pro/THUDM/glm-4-9b-chat",
+    ],
+    "ibm": ["ibm/granite-vision-3.1-2b-preview", "meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
+            "meta-llama/llama-3-2-90b-vision-instruct"],
+    "modelscope":[
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Qwen/Qwen2.5-Coder-14B-Instruct",
+        "Qwen/Qwen2.5-Coder-7B-Instruct",
+        "Qwen/Qwen2.5-72B-Instruct",
+        "Qwen/Qwen2.5-32B-Instruct",
+        "Qwen/Qwen2.5-14B-Instruct",
+        "Qwen/Qwen2.5-7B-Instruct",
+        "Qwen/QwQ-32B-Preview",
+        "Qwen/Qwen2.5-VL-3B-Instruct",
+        "Qwen/Qwen2.5-VL-7B-Instruct",
+        "Qwen/Qwen2.5-VL-32B-Instruct",
+        "Qwen/Qwen2.5-VL-72B-Instruct",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+        "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+        "deepseek-ai/DeepSeek-R1",
+        "deepseek-ai/DeepSeek-V3",
+        "Qwen/Qwen3-1.7B",
+        "Qwen/Qwen3-4B",
+        "Qwen/Qwen3-8B",
+        "Qwen/Qwen3-14B",
+        "Qwen/Qwen3-30B-A3B",
+        "Qwen/Qwen3-32B",
+        "Qwen/Qwen3-235B-A22B",
+    ],
+}