Upload 14 files

api_base.py

@@ -1,9 +1,3 @@
-"""
-Base API module for handling different API providers.
-This module provides a unified interface for interacting with various API providers
-like Anthropic, OpenAI, Google Gemini and Together AI.
-"""
-
 from abc import ABC, abstractmethod
 import logging
 import requests
@@ -226,13 +220,112 @@ class TogetherAPI(BaseAPI):
         except Exception as e:
             self._handle_error(e, "request or response processing")
 
+class DeepSeekAPI(BaseAPI):
+    """Class to handle interactions with the DeepSeek API"""
+    
+    def __init__(self, api_key: str, model: str = "deepseek-chat"):
+        super().__init__(api_key, model)
+        self.provider_name = "DeepSeek"
+        try:
+            self.client = OpenAI(api_key=api_key, base_url="https://api.deepseek.com")
+        except Exception as e:
+            self._handle_error(e, "initialization")
+
+    def generate_response(self, prompt: str, max_tokens: int = 1024, 
+                         prompt_format: Optional[str] = None) -> str:
+        """Generate a response using the DeepSeek API"""
+        try:
+            formatted_prompt = self._format_prompt(prompt, prompt_format)
+            
+            logger.info(f"Sending request to DeepSeek API with model {self.model}")
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[
+                    {"role": "user", "content": formatted_prompt}
+                ],
+                max_tokens=max_tokens
+            )
+            
+            return response.choices[0].message.content
+            
+        except Exception as e:
+            self._handle_error(e, "request or response processing")
+
+class QwenAPI(BaseAPI):
+    """Class to handle interactions with the Qwen API"""
+    
+    def __init__(self, api_key: str, model: str = "qwen-plus"):
+        super().__init__(api_key, model)
+        self.provider_name = "Qwen"
+        try:
+            self.client = OpenAI(
+                api_key=api_key,
+                base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
+            )
+        except Exception as e:
+            self._handle_error(e, "initialization")
+
+    def generate_response(self, prompt: str, max_tokens: int = 1024, 
+                         prompt_format: Optional[str] = None) -> str:
+        """Generate a response using the Qwen API"""
+        try:
+            formatted_prompt = self._format_prompt(prompt, prompt_format)
+            
+            logger.info(f"Sending request to Qwen API with model {self.model}")
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[
+                    {"role": "user", "content": formatted_prompt}
+                ],
+                max_tokens=max_tokens
+            )
+            
+            return response.choices[0].message.content
+            
+        except Exception as e:
+            self._handle_error(e, "request or response processing")
+
+class GrokAPI(BaseAPI):
+    """Class to handle interactions with the Grok API"""
+    
+    def __init__(self, api_key: str, model: str = "grok-2-latest"):
+        super().__init__(api_key, model)
+        self.provider_name = "Grok"
+        try:
+            self.client = OpenAI(
+                api_key=api_key,
+                base_url="https://api.x.ai/v1"
+            )
+        except Exception as e:
+            self._handle_error(e, "initialization")
+
+    def generate_response(self, prompt: str, max_tokens: int = 1024, 
+                         prompt_format: Optional[str] = None) -> str:
+        """Generate a response using the Grok API"""
+        try:
+            formatted_prompt = self._format_prompt(prompt, prompt_format)
+            
+            logger.info(f"Sending request to Grok API with model {self.model}")
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[
+                    {"role": "user", "content": formatted_prompt}
+                ],
+                max_tokens=max_tokens
+            )
+            
+            return response.choices[0].message.content
+            
+        except Exception as e:
+            self._handle_error(e, "request or response processing")
+
 class APIFactory:
     """Factory class for creating API instances"""
     
     _providers = {
         "anthropic": {
             "class": AnthropicAPI,
-            "default_model": "claude-3-opus-20240229"
+            "default_model": "claude-3-7-sonnet-20250219"
         },
         "openai": {
             "class": OpenAIAPI,
@@ -244,7 +337,19 @@ class APIFactory:
         },
         "together": {
             "class": TogetherAPI,
-            "default_model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
+            "default_model": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
+        },
+        "deepseek": {
+            "class": DeepSeekAPI,
+            "default_model": "deepseek-chat"
+        },
+        "qwen": {
+            "class": QwenAPI,
+            "default_model": "qwen-plus"
+        },
+        "grok": {
+            "class": GrokAPI,
+            "default_model": "grok-2-latest"
         }
     }
     

api_keys.json

@@ -2,5 +2,8 @@
     "anthropic": "",
     "openai": "",
     "google": "",
-    "together": ""
+    "together": "",
+    "deepseek": "",
+    "qwen": "",
+    "grok": ""
 }

bs_reasoning.py

@@ -175,13 +175,7 @@ def wrap_text(text: str, config: VisualizationConfig) -> str:
     wrapped_lines = textwrap.wrap(text, width=config.max_chars_per_line)
     
     if len(wrapped_lines) > config.max_lines:
-        # Option 1: Simply truncate and add ellipsis to the last line
         wrapped_lines = wrapped_lines[:config.max_lines]
         wrapped_lines[-1] = wrapped_lines[-1][:config.max_chars_per_line-3] + "..."
-        
-        # Option 2 (alternative): Include part of the next line to show continuity
-        # original_next_line = wrapped_lines[config.max_lines] if len(wrapped_lines) > config.max_lines else ""
-        # wrapped_lines = wrapped_lines[:config.max_lines-1]
-        # wrapped_lines.append(original_next_line[:config.max_chars_per_line-3] + "...")
-    
+            
     return "<br>".join(wrapped_lines)

configs.py

@@ -29,47 +29,134 @@ class GeneralConfig:
     """General configuration parameters that are method-independent"""
     available_models: List[str] = field(default_factory=lambda: [
         # Anthropic Models
+        "claude-3-7-sonnet-20250219",
+        "claude-3-5-sonnet-20241022",
+        "claude-3-5-haiku-20241022",
         "claude-3-haiku-20240307",
         "claude-3-sonnet-20240229",
         "claude-3-opus-20240229",
         # OpenAI Models
-        "gpt-4-turbo-preview",
         "gpt-4",
+        "gpt-4-turbo", 
+        "gpt-4-turbo-preview",
+        "chatgpt-4o-latest",
+        #"gpt-4o-mini",
         "gpt-3.5-turbo",
         # Gemini Models
         "gemini-2.0-flash",
+        "gemini-2.0-flash-lite",
+        "gemini-2.0-pro-exp-02-05",
+        "gemini-1.5-flash",
+        "gemini-1.5-flash-8b",
+        "gemini-1.5-pro",
         # Together AI Models
-        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
         "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+        #"meta-llama/Llama-3.2-3B-Instruct-Turbo", 
         "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro",
+        "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", 
+        #"meta-llama/Meta-Llama-3.1-70B-Instruct-Reference", 
+        "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", 
+        "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", 
+        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Reference", 
+        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+        "meta-llama/Llama-3-70b-chat-hf", 
+        "meta-llama/Meta-Llama-3-70B-Instruct", 
+        "meta-llama/Meta-Llama-3-70B-Instruct-Turbo", 
+        "meta-llama/Meta-Llama-3-70B-Instruct-Lite", 
+        #"meta-llama/Llama-3-8b-chat-hf", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct-Turbo", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct-Lite", 
         "deepseek-ai/DeepSeek-V3",
         "mistralai/Mixtral-8x22B-Instruct-v0.1",
         "Qwen/Qwen2.5-72B-Instruct-Turbo",
         #"microsoft/WizardLM-2-8x22B",
         #"databricks/dbrx-instruct",
         #"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
-
+        # DeepSeek Models
+        "deepseek-chat",
+        # Qwen Models
+        "qwen-max",
+        "qwen-max-latest",
+        "qwen-max-2025-01-25",
+        "qwen-plus",
+        "qwen-plus-latest",
+        "qwen-plus-2025-01-25",
+        "qwen-turbo",
+        "qwen-turbo-latest",
+        "qwen-turbo-2024-11-01",
+        #"qwen2.5-14b-instruct-1m",
+        #"qwen2.5-7b-instruct-1m",
+        "qwen2.5-72b-instruct",
+        "qwen2.5-32b-instruct",
+        #"qwen2.5-14b-instruct",
+        #"qwen2.5-7b-instruct",
+        # Grok Models
+        "grok-2",
+        "grok-2-latest",
     ])
     model_providers: Dict[str, str] = field(default_factory=lambda: {
+        "claude-3-7-sonnet-20250219": "anthropic",
+        "claude-3-5-sonnet-20241022": "anthropic",
+        "claude-3-5-haiku-20241022": "anthropic",
         "claude-3-haiku-20240307": "anthropic",
         "claude-3-sonnet-20240229": "anthropic",
         "claude-3-opus-20240229": "anthropic",
-        "gpt-4-turbo-preview": "openai",
         "gpt-4": "openai",
+        "gpt-4-turbo": "openai", 
+        "gpt-4-turbo-preview": "openai",
+        "chatgpt-4o-latest": "openai",
+        #"gpt-4o-mini": "openai",
         "gpt-3.5-turbo": "openai",
         "gemini-2.0-flash": "google",
-        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": "together",
+        "gemini-2.0-flash-lite": "google",
+        "gemini-2.0-pro-exp-02-05": "google",
+        "gemini-1.5-flash": "google",
+        "gemini-1.5-flash-8b": "google",
+        "gemini-1.5-pro": "google",
         "meta-llama/Llama-3.3-70B-Instruct-Turbo": "together",
+        #"meta-llama/Llama-3.2-3B-Instruct-Turbo": "together", 
         "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro": "together",
+        "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": "together", 
+        #"meta-llama/Meta-Llama-3.1-70B-Instruct-Reference": "together", 
+        "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": "together", 
+        "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": "together", 
+        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Reference": "together", 
+        #"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": "together",
+        "meta-llama/Llama-3-70b-chat-hf": "together", 
+        "meta-llama/Meta-Llama-3-70B-Instruct": "together", 
+        "meta-llama/Meta-Llama-3-70B-Instruct-Turbo": "together", 
+        "meta-llama/Meta-Llama-3-70B-Instruct-Lite": "together", 
+        #"meta-llama/Llama-3-8b-chat-hf": "together", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct": "together", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct-Turbo": "together", 
+        #"meta-llama/Meta-Llama-3-8B-Instruct-Lite": "together", 
         "deepseek-ai/DeepSeek-V3": "together",
         "mistralai/Mixtral-8x22B-Instruct-v0.1": "together",
         "Qwen/Qwen2.5-72B-Instruct-Turbo": "together",
         #"microsoft/WizardLM-2-8x22B": "together",
         #"databricks/dbrx-instruct": "together",
         #"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": "together",
-
+        "deepseek-chat": "deepseek",
+        "qwen-max": "qwen",
+        "qwen-max-latest": "qwen",
+        "qwen-max-2025-01-25": "qwen",
+        "qwen-plus": "qwen",
+        "qwen-plus-latest": "qwen",
+        "qwen-plus-2025-01-25": "qwen",
+        "qwen-turbo": "qwen",
+        "qwen-turbo-latest": "qwen",
+        "qwen-turbo-2024-11-01": "qwen",
+        #"qwen2.5-14b-instruct-1m": "qwen",
+        #"qwen2.5-7b-instruct-1m": "qwen",
+        "qwen2.5-72b-instruct": "qwen",
+        "qwen2.5-32b-instruct": "qwen",
+        #"qwen2.5-14b-instruct": "qwen",
+        #"qwen2.5-7b-instruct": "qwen",
+        "grok-2": "grok",
+        "grok-2-latest": "grok",
     })
-    providers: List[str] = field(default_factory=lambda: ["anthropic", "openai", "google", "together"])
+    providers: List[str] = field(default_factory=lambda: ["anthropic", "openai", "google", "together", "deepseek", "qwen", "grok"])
     max_tokens: int = 2048
     chars_per_line: int = 40
     max_lines: int = 8

tot_reasoning.py

@@ -125,13 +125,7 @@ def wrap_text(text: str, config: VisualizationConfig) -> str:
     wrapped_lines = textwrap.wrap(text, width=config.max_chars_per_line)
     
     if len(wrapped_lines) > config.max_lines:
-        # Option 1: Simply truncate and add ellipsis to the last line
         wrapped_lines = wrapped_lines[:config.max_lines]
         wrapped_lines[-1] = wrapped_lines[-1][:config.max_chars_per_line-3] + "..."
-        
-        # Option 2 (alternative): Include part of the next line to show continuity
-        # original_next_line = wrapped_lines[config.max_lines] if len(wrapped_lines) > config.max_lines else ""
-        # wrapped_lines = wrapped_lines[:config.max_lines-1]
-        # wrapped_lines.append(original_next_line[:config.max_chars_per_line-3] + "...")
-    
+            
     return "<br>".join(wrapped_lines)