diff --git a/cli/utils.py b/cli/utils.py index 17893a6f..c3c42bbd 100644 --- a/cli/utils.py +++ b/cli/utils.py @@ -122,38 +122,165 @@ def select_research_depth() -> int: return choice +# Centralized model definitions - single source of truth +SHALLOW_AGENT_OPTIONS = { + "openai": [ + ("GPT-4o-mini - Fast and efficient for quick tasks", "gpt-4o-mini"), + ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"), + ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"), + ("GPT-4o - Standard model with solid capabilities", "gpt-4o"), + ], + "anthropic": [ + ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"), + ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"), + ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"), + ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"), + ], + "google": [ + ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"), + ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"), + ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"), + ], + "openrouter": [ + ("Meta: Llama 4 Scout", "meta-llama/llama-4-scout:free"), + ("Meta: Llama 3.3 8B Instruct - A lightweight and ultra-fast variant of Llama 3.3 70B", "meta-llama/llama-3.3-8b-instruct:free"), + ("google/gemini-2.0-flash-exp:free - Gemini Flash 2.0 offers a significantly faster time to first token", "google/gemini-2.0-flash-exp:free"), + ], + "ollama": [ + ("llama3.1 local", "llama3.1"), + ("llama3.2 local", "llama3.2"), + ] +} + +DEEP_AGENT_OPTIONS = { + "openai": [ + ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"), + ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"), + ("GPT-4o - Standard model with solid capabilities", "gpt-4o"), + ("o4-mini - Specialized reasoning model (compact)", "o4-mini"), + ("o3-mini - Advanced reasoning model (lightweight)", "o3-mini"), + ("o3 - Full advanced reasoning model", "o3"), + ("o1 - Premier reasoning and problem-solving model", "o1"), + ], + "anthropic": [ + ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"), + ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"), + ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"), + ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"), + ("Claude Opus 4 - Most powerful Anthropic model", "claude-opus-4-0"), + ], + "google": [ + ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"), + ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"), + ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"), + ("Gemini 2.5 Pro", "gemini-2.5-pro-preview-06-05"), + ], + "openrouter": [ + ("DeepSeek V3 - a 685B-parameter, mixture-of-experts model", "deepseek/deepseek-chat-v3-0324:free"), + ("Deepseek - latest iteration of the flagship chat model family from the DeepSeek team.", "deepseek/deepseek-chat-v3-0324:free"), + ], + "ollama": [ + ("llama3.1 local", "llama3.1"), + ("qwen3", "qwen3"), + ] +} + + +def _get_all_models_for_custom_provider(model_type: str) -> list: + """Get unified model list for custom provider with all available models from all providers. + + Args: + model_type: Either 'shallow' or 'deep' to get the appropriate model set + + Returns: + List of (description, model_value) tuples + """ + # Use the centralized model definitions + if model_type == "shallow": + provider_models = SHALLOW_AGENT_OPTIONS + else: # deep + provider_models = DEEP_AGENT_OPTIONS + + # Combine all models with provider labels + all_models = [] + for provider_name, models in provider_models.items(): + provider_display_name = provider_name.title() + for description, model_value in models: + labeled_description = f"{description} ({provider_display_name})" + all_models.append((labeled_description, model_value)) + + # Add custom model option at the end + all_models.append(("Custom Model - Enter your own model name", "__CUSTOM_MODEL__")) + + return all_models + + +def _select_custom_provider_model(model_type: str, title: str, default_model: str) -> str: + """Handle model selection for custom provider with unified model list. + + Args: + model_type: Either 'shallow' or 'deep' + title: Title for the selection prompt + default_model: Default model name for custom input + + Returns: + Selected model name + """ + all_models = _get_all_models_for_custom_provider(model_type) + + choice = questionary.select( + title, + choices=[ + questionary.Choice(display, value=value) + for display, value in all_models + ], + instruction="\n- Use arrow keys to navigate\n- Press Enter to select\n- Your custom endpoint should support the selected model", + style=questionary.Style( + [ + ("selected", "fg:magenta noinherit"), + ("highlighted", "fg:magenta noinherit"), + ("pointer", "fg:magenta noinherit"), + ] + ), + ).ask() + + if choice is None: + from rich.console import Console + console = Console() + console.print(f"\n[red]No {model_type} thinking model selected. Exiting...[/red]") + exit(1) + + # Handle custom model input + if choice == "__CUSTOM_MODEL__": + custom_model = questionary.text( + f"Enter your custom {model_type} thinking model name:", + default=default_model, + instruction="\n- Enter the exact model name as supported by your custom endpoint\n- Press Enter to confirm" + ).ask() + + if not custom_model: + from rich.console import Console + console = Console() + console.print(f"\n[red]No custom {model_type} model name entered. Exiting...[/red]") + exit(1) + + return custom_model + + return choice + + def select_shallow_thinking_agent(provider) -> str: """Select shallow thinking llm engine using an interactive selection.""" - # Define shallow thinking llm engine options with their corresponding model names - SHALLOW_AGENT_OPTIONS = { - "openai": [ - ("GPT-4o-mini - Fast and efficient for quick tasks", "gpt-4o-mini"), - ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"), - ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"), - ("GPT-4o - Standard model with solid capabilities", "gpt-4o"), - ], - "anthropic": [ - ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"), - ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"), - ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"), - ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"), - ], - "google": [ - ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"), - ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"), - ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"), - ], - "openrouter": [ - ("Meta: Llama 4 Scout", "meta-llama/llama-4-scout:free"), - ("Meta: Llama 3.3 8B Instruct - A lightweight and ultra-fast variant of Llama 3.3 70B", "meta-llama/llama-3.3-8b-instruct:free"), - ("google/gemini-2.0-flash-exp:free - Gemini Flash 2.0 offers a significantly faster time to first token", "google/gemini-2.0-flash-exp:free"), - ], - "ollama": [ - ("llama3.1 local", "llama3.1"), - ("llama3.2 local", "llama3.2"), - ] - } + # Handle custom provider - use unified model selection + if provider.lower().startswith("custom"): + return _select_custom_provider_model( + model_type="shallow", + title="Select Your [Quick-Thinking LLM Engine] (Custom Provider - All Models Available):", + default_model="gpt-4o-mini" + ) + + # Use centralized shallow thinking model definitions choice = questionary.select( "Select Your [Quick-Thinking LLM Engine]:", @@ -172,6 +299,8 @@ def select_shallow_thinking_agent(provider) -> str: ).ask() if choice is None: + from rich.console import Console + console = Console() console.print( "\n[red]No shallow thinking llm engine selected. Exiting...[/red]" ) @@ -183,40 +312,16 @@ def select_shallow_thinking_agent(provider) -> str: def select_deep_thinking_agent(provider) -> str: """Select deep thinking llm engine using an interactive selection.""" - # Define deep thinking llm engine options with their corresponding model names - DEEP_AGENT_OPTIONS = { - "openai": [ - ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"), - ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"), - ("GPT-4o - Standard model with solid capabilities", "gpt-4o"), - ("o4-mini - Specialized reasoning model (compact)", "o4-mini"), - ("o3-mini - Advanced reasoning model (lightweight)", "o3-mini"), - ("o3 - Full advanced reasoning model", "o3"), - ("o1 - Premier reasoning and problem-solving model", "o1"), - ], - "anthropic": [ - ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"), - ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"), - ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"), - ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"), - ("Claude Opus 4 - Most powerful Anthropic model", " claude-opus-4-0"), - ], - "google": [ - ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"), - ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"), - ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"), - ("Gemini 2.5 Pro", "gemini-2.5-pro-preview-06-05"), - ], - "openrouter": [ - ("DeepSeek V3 - a 685B-parameter, mixture-of-experts model", "deepseek/deepseek-chat-v3-0324:free"), - ("Deepseek - latest iteration of the flagship chat model family from the DeepSeek team.", "deepseek/deepseek-chat-v3-0324:free"), - ], - "ollama": [ - ("llama3.1 local", "llama3.1"), - ("qwen3", "qwen3"), - ] - } - + # Handle custom provider - use unified model selection + if provider.lower().startswith("custom"): + return _select_custom_provider_model( + model_type="deep", + title="Select Your [Deep-Thinking LLM Engine] (Custom Provider - All Models Available):", + default_model="o4-mini" + ) + + # Use centralized deep thinking model definitions + choice = questionary.select( "Select Your [Deep-Thinking LLM Engine]:", choices=[ @@ -234,24 +339,83 @@ def select_deep_thinking_agent(provider) -> str: ).ask() if choice is None: + from rich.console import Console + console = Console() console.print("\n[red]No deep thinking llm engine selected. Exiting...[/red]") exit(1) return choice -def select_llm_provider() -> tuple[str, str]: - """Select the OpenAI api url using interactive selection.""" +def validate_custom_url(url: str) -> str: + """Validate that a custom URL is properly formatted and has a valid hostname.""" + import re + from urllib.parse import urlparse + from rich.console import Console + + if not url: + return "" + + console = Console() + + # Basic URL format validation + url_pattern = re.compile( + r'^https?://' # http:// or https:// + r'(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+[A-Z]{2,6}\.?|' # domain... + r'localhost|' # localhost... + r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})' # ...or ip + r'(?::\d+)?' # optional port + r'(?:/?|[/?]\S+)$', re.IGNORECASE) + + if not url_pattern.match(url): + console.print(f"[red]Error: Invalid CUSTOM_BASE_URL format: {url}[/red]") + console.print(f"[red]Please provide a valid URL (e.g., https://api.example.com/v1)[/red]") + exit(1) + + # Additional validation using urlparse + try: + parsed = urlparse(url) + if not parsed.netloc: + raise ValueError("No hostname found") + return url + except Exception as e: + console.print(f"[red]Error: Invalid CUSTOM_BASE_URL: {url}[/red]") + console.print(f"[red]URL parsing error: {e}[/red]") + exit(1) + + +def get_custom_provider_info() -> tuple[str, str] | None: + """Get custom provider info if both URL and API key are provided.""" import os - # Define OpenAI api options with their corresponding endpoints - # Use custom URL from environment if available, otherwise use default - openai_url = os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1") + from urllib.parse import urlparse + + custom_url = os.getenv("CUSTOM_BASE_URL") + custom_api_key = os.getenv("CUSTOM_API_KEY") + + if custom_url and custom_api_key: + validated_url = validate_custom_url(custom_url) + parsed = urlparse(validated_url) + hostname = parsed.netloc + return f"Custom ({hostname})", validated_url + + return None + + +def select_llm_provider() -> tuple[str, str]: + """Select the LLM provider with support for a custom OpenAI-compatible endpoint.""" + + # Define default providers BASE_URLS = [ - ("OpenAI", openai_url), + ("OpenAI", "https://api.openai.com/v1"), ("Anthropic", "https://api.anthropic.com/"), ("Google", "https://generativelanguage.googleapis.com/v1"), ("Openrouter", "https://openrouter.ai/api/v1"), ("Ollama", "http://localhost:11434/v1"), ] + + # Add custom provider at the beginning if available + custom_info = get_custom_provider_info() + if custom_info: + BASE_URLS.insert(0, custom_info) choice = questionary.select( "Select your LLM Provider:", @@ -270,10 +434,12 @@ def select_llm_provider() -> tuple[str, str]: ).ask() if choice is None: - console.print("\n[red]no OpenAI backend selected. Exiting...[/red]") + from rich.console import Console + console = Console() + console.print("\n[red]No LLM provider selected. Exiting...[/red]") exit(1) - + display_name, url = choice print(f"You selected: {display_name}\tURL: {url}") - + return display_name, url diff --git a/example.env b/example.env new file mode 100644 index 00000000..46c84d80 --- /dev/null +++ b/example.env @@ -0,0 +1,20 @@ +# Copy this to your .env file and modify the URLs and API keys as needed + +# Custom OpenAI-Compatible Provider (optional) +# If provided, a "Custom" option will appear first in the provider list +# The custom endpoint must be OpenAI-compatible (REST API, not gRPC) +# CUSTOM_BASE_URL=https://www.example.com/v1 +# CUSTOM_API_KEY=sk-your-custom-api-key-here + +# Standard Provider API Keys, please replace with your own keys to use the corresponding provider +OPENAI_API_KEY=sk-your-openai-api-key-here +ANTHROPIC_API_KEY=sk-ant-your-anthropic-api-key-here +GOOGLE_API_KEY=your-google-api-key-here +OPENROUTER_API_KEY=sk-or-your-openrouter-api-key-here +# OLLAMA_API_KEY is usually not needed for local Ollama instances + +# Other Configuration +FINNHUB_API_KEY=your-finnhub-api-key-here + +# Optional, uncomment to modify +# TRADINGAGENTS_RESULTS_DIR=./results diff --git a/tradingagents/agents/utils/memory.py b/tradingagents/agents/utils/memory.py index 69b8ab8c..5e14c2ef 100644 --- a/tradingagents/agents/utils/memory.py +++ b/tradingagents/agents/utils/memory.py @@ -1,6 +1,7 @@ import chromadb from chromadb.config import Settings from openai import OpenAI +import os class FinancialSituationMemory: @@ -9,7 +10,15 @@ class FinancialSituationMemory: self.embedding = "nomic-embed-text" else: self.embedding = "text-embedding-3-small" - self.client = OpenAI(base_url=config["backend_url"]) + + # Use CUSTOM_API_KEY if provider is custom, otherwise use OPENAI_API_KEY + provider = config.get("llm_provider", "openai").lower() + if provider.startswith("custom"): + api_key = os.getenv("CUSTOM_API_KEY") + else: + api_key = os.getenv("OPENAI_API_KEY") + + self.client = OpenAI(base_url=config["backend_url"], api_key=api_key) self.chroma_client = chromadb.Client(Settings(allow_reset=True)) self.situation_collection = self.chroma_client.create_collection(name=name) diff --git a/tradingagents/dataflows/interface.py b/tradingagents/dataflows/interface.py index dfb4b742..2c73baf0 100644 --- a/tradingagents/dataflows/interface.py +++ b/tradingagents/dataflows/interface.py @@ -704,7 +704,14 @@ def get_YFin_data( def get_stock_news_openai(ticker, curr_date): config = get_config() - client = OpenAI(base_url=config["backend_url"], api_key=os.getenv("OPENAI_API_KEY")) + # Use CUSTOM_API_KEY if provider is custom, otherwise use OPENAI_API_KEY + provider = config.get("llm_provider", "openai").lower() + if provider.startswith("custom"): + api_key = os.getenv("CUSTOM_API_KEY") + else: + api_key = os.getenv("OPENAI_API_KEY") + + client = OpenAI(base_url=config["backend_url"], api_key=api_key) response = client.responses.create( model=config["quick_think_llm"], @@ -739,7 +746,14 @@ def get_stock_news_openai(ticker, curr_date): def get_global_news_openai(curr_date): config = get_config() - client = OpenAI(base_url=config["backend_url"], api_key=os.getenv("OPENAI_API_KEY")) + # Use CUSTOM_API_KEY if provider is custom, otherwise use OPENAI_API_KEY + provider = config.get("llm_provider", "openai").lower() + if provider.startswith("custom"): + api_key = os.getenv("CUSTOM_API_KEY") + else: + api_key = os.getenv("OPENAI_API_KEY") + + client = OpenAI(base_url=config["backend_url"], api_key=api_key) response = client.responses.create( model=config["quick_think_llm"], @@ -774,7 +788,14 @@ def get_global_news_openai(curr_date): def get_fundamentals_openai(ticker, curr_date): config = get_config() - client = OpenAI(base_url=config["backend_url"], api_key=os.getenv("OPENAI_API_KEY")) + # Use CUSTOM_API_KEY if provider is custom, otherwise use OPENAI_API_KEY + provider = config.get("llm_provider", "openai").lower() + if provider.startswith("custom"): + api_key = os.getenv("CUSTOM_API_KEY") + else: + api_key = os.getenv("OPENAI_API_KEY") + + client = OpenAI(base_url=config["backend_url"], api_key=api_key) response = client.responses.create( model=config["quick_think_llm"], diff --git a/tradingagents/default_config.py b/tradingagents/default_config.py index b72e82f0..be6ccf26 100644 --- a/tradingagents/default_config.py +++ b/tradingagents/default_config.py @@ -12,7 +12,7 @@ DEFAULT_CONFIG = { "llm_provider": "openai", "deep_think_llm": "o4-mini", "quick_think_llm": "gpt-4o-mini", - "backend_url": os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1"), + "backend_url": "https://api.openai.com/v1", # Will be updated based on selected provider # Debate and discussion settings "max_debate_rounds": 1, "max_risk_discuss_rounds": 1, diff --git a/tradingagents/graph/trading_graph.py b/tradingagents/graph/trading_graph.py index 6b157b65..dfb662b9 100644 --- a/tradingagents/graph/trading_graph.py +++ b/tradingagents/graph/trading_graph.py @@ -58,13 +58,22 @@ class TradingAgentsGraph: ) # Initialize LLMs - if self.config["llm_provider"].lower() == "openai" or self.config["llm_provider"] == "ollama" or self.config["llm_provider"] == "openrouter": - self.deep_thinking_llm = ChatOpenAI(model=self.config["deep_think_llm"], openai_api_base=self.config["backend_url"]) - self.quick_thinking_llm = ChatOpenAI(model=self.config["quick_think_llm"], openai_api_base=self.config["backend_url"]) - elif self.config["llm_provider"].lower() == "anthropic": + provider = self.config["llm_provider"].lower() + + if provider == "openai" or provider == "ollama" or provider == "openrouter": + from tradingagents.utils.provider_utils import get_api_key_for_provider + api_key = get_api_key_for_provider(self.config) + self.deep_thinking_llm = ChatOpenAI(model=self.config["deep_think_llm"], openai_api_base=self.config["backend_url"], openai_api_key=api_key) + self.quick_thinking_llm = ChatOpenAI(model=self.config["quick_think_llm"], openai_api_base=self.config["backend_url"], openai_api_key=api_key) + elif provider.startswith("custom"): + # Custom provider uses OpenAI-compatible interface + custom_api_key = os.getenv("CUSTOM_API_KEY") + self.deep_thinking_llm = ChatOpenAI(model=self.config["deep_think_llm"], openai_api_base=self.config["backend_url"], openai_api_key=custom_api_key) + self.quick_thinking_llm = ChatOpenAI(model=self.config["quick_think_llm"], openai_api_base=self.config["backend_url"], openai_api_key=custom_api_key) + elif provider == "anthropic": self.deep_thinking_llm = ChatAnthropic(model=self.config["deep_think_llm"], base_url=self.config["backend_url"]) self.quick_thinking_llm = ChatAnthropic(model=self.config["quick_think_llm"], base_url=self.config["backend_url"]) - elif self.config["llm_provider"].lower() == "google": + elif provider == "google": self.deep_thinking_llm = ChatGoogleGenerativeAI(model=self.config["deep_think_llm"]) self.quick_thinking_llm = ChatGoogleGenerativeAI(model=self.config["quick_think_llm"]) else: diff --git a/tradingagents/utils/provider_utils.py b/tradingagents/utils/provider_utils.py new file mode 100644 index 00000000..426a0a39 --- /dev/null +++ b/tradingagents/utils/provider_utils.py @@ -0,0 +1,34 @@ +""" +Utility functions for LLM provider configuration and API key management. +""" + +import os + + +def get_api_key_for_provider(config): + """Get the appropriate API key based on the provider. + + Args: + config (dict): Configuration dictionary containing llm_provider + + Returns: + str: The API key for the provider, or None if not found + """ + provider = config.get("llm_provider", "openai").lower() + + # Map providers to their environment variables + api_key_mapping = { + "openai": "OPENAI_API_KEY", + "anthropic": "ANTHROPIC_API_KEY", + "google": "GOOGLE_API_KEY", + "openrouter": "OPENROUTER_API_KEY", + "ollama": "OLLAMA_API_KEY", + } + + env_var = api_key_mapping.get(provider, "OPENAI_API_KEY") + api_key = os.getenv(env_var) + + if not api_key and provider != "ollama": # Ollama typically doesn't need API keys + print(f"Warning: {env_var} not found in environment variables") + + return api_key