ragaai-catalyst 2.1.5b8__py3-none-any.whl → 2.1.5b10__py3-none-any.whl

ragaai_catalyst/tracers/agentic_tracing/utils/model_costs.json

@@ -14,7 +14,8 @@
         "supports_audio_output": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD"
     },
     "omni-moderation-latest": {
         "max_tokens": 32768,
@@ -441,7 +442,8 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2025-06-06"
     },
     "gpt-4-32k": {
         "max_tokens": 4096,
@@ -540,7 +542,8 @@
         "mode": "chat",
         "supports_vision": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2024-12-06"
     },
     "gpt-4-1106-vision-preview": {
         "max_tokens": 4096,
@@ -552,7 +555,8 @@
         "mode": "chat",
         "supports_vision": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2024-12-06"
     },
     "gpt-3.5-turbo": {
         "max_tokens": 4097,
@@ -1223,7 +1227,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-03-31"
     },
     "azure/gpt-35-turbo-0613": {
         "max_tokens": 4097,
@@ -1234,7 +1239,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-02-13"
     },
     "azure/gpt-35-turbo-0301": {
         "max_tokens": 4097,
@@ -1245,7 +1251,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-02-13"
     },
     "azure/gpt-35-turbo-0125": {
         "max_tokens": 4096,
@@ -1256,7 +1263,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-03-31"
     },
     "azure/gpt-35-turbo-16k": {
         "max_tokens": 4096,
@@ -2042,6 +2050,84 @@
         "supports_function_calling": true,
         "supports_vision": true
     },
+    "xai/grok-2-vision-1212": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_image": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-vision-latest": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_image": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-vision": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_image": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-vision-beta": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 5e-06,
+        "input_cost_per_image": 5e-06,
+        "output_cost_per_token": 1.5e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-1212": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "xai/grok-2": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "xai/grok-2-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 2e-06,
+        "output_cost_per_token": 1e-05,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "deepseek/deepseek-coder": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
@@ -2353,7 +2439,8 @@
         "tool_use_system_prompt_tokens": 264,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-03-01"
     },
     "claude-3-5-haiku-20241022": {
         "max_tokens": 8192,
@@ -2369,7 +2456,8 @@
         "tool_use_system_prompt_tokens": 264,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01"
     },
     "claude-3-opus-20240229": {
         "max_tokens": 4096,
@@ -2386,7 +2474,8 @@
         "tool_use_system_prompt_tokens": 395,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-03-01"
     },
     "claude-3-sonnet-20240229": {
         "max_tokens": 4096,
@@ -2401,7 +2490,8 @@
         "tool_use_system_prompt_tokens": 159,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-07-21"
     },
     "claude-3-5-sonnet-20240620": {
         "max_tokens": 8192,
@@ -2418,7 +2508,8 @@
         "tool_use_system_prompt_tokens": 159,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-06-01"
     },
     "claude-3-5-sonnet-20241022": {
         "max_tokens": 8192,
@@ -2436,7 +2527,8 @@
         "supports_assistant_prefill": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01"
     },
     "text-bison": {
         "max_tokens": 2048,
@@ -2546,7 +2638,8 @@
         "output_cost_per_character": 5e-07,
         "litellm_provider": "vertex_ai-chat-models",
         "mode": "chat",
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "chat-bison-32k": {
         "max_tokens": 8192,
@@ -2787,7 +2880,8 @@
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_function_calling": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "gemini-1.0-ultra": {
         "max_tokens": 8192,
@@ -2832,7 +2926,8 @@
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_function_calling": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "gemini-1.5-pro": {
         "max_tokens": 8192,
@@ -2914,7 +3009,8 @@
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_response_schema": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-05-24"
     },
     "gemini-1.5-pro-preview-0514": {
         "max_tokens": 8192,
@@ -3119,7 +3215,8 @@
         "supports_function_calling": true,
         "supports_vision": true,
         "supports_response_schema": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-05-24"
     },
     "gemini-1.5-flash-preview-0514": {
         "max_tokens": 8192,
@@ -3223,7 +3320,8 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_vision": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "medlm-medium": {
         "max_tokens": 8192,
@@ -3929,7 +4027,8 @@
         "supports_prompt_caching": true,
         "tpm": 4000000,
         "rpm": 2000,
-        "source": "https://ai.google.dev/pricing"
+        "source": "https://ai.google.dev/pricing",
+        "deprecation_date": "2025-05-24"
     },
     "gemini/gemini-1.5-flash": {
         "max_tokens": 8192,
@@ -4205,7 +4304,8 @@
         "supports_prompt_caching": true,
         "tpm": 4000000,
         "rpm": 1000,
-        "source": "https://ai.google.dev/pricing"
+        "source": "https://ai.google.dev/pricing",
+        "deprecation_date": "2025-05-24"
     },
     "gemini/gemini-1.5-pro-exp-0801": {
         "max_tokens": 8192,
@@ -7341,7 +7441,8 @@
         "input_cost_per_token": 5e-06,
         "output_cost_per_token": 5e-06,
         "litellm_provider": "perplexity",
-        "mode": "chat"
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-online": {
         "max_tokens": 127072,
@@ -7350,7 +7451,8 @@
         "input_cost_per_token": 1e-06,
         "output_cost_per_token": 1e-06,
         "litellm_provider": "perplexity",
-        "mode": "chat"
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-chat": {
         "max_tokens": 131072,
@@ -7359,7 +7461,8 @@
         "input_cost_per_token": 1e-06,
         "output_cost_per_token": 1e-06,
         "litellm_provider": "perplexity",
-        "mode": "chat"
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-chat": {
         "max_tokens": 131072,
@@ -7368,7 +7471,8 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
         "litellm_provider": "perplexity",
-        "mode": "chat"
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-online": {
         "max_tokens": 127072,
@@ -7377,7 +7481,8 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
         "litellm_provider": "perplexity",
-        "mode": "chat"
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/pplx-7b-chat": {
         "max_tokens": 8192,

ragaai_catalyst/tracers/langchain_callback.py

@@ -175,10 +175,12 @@ class LangchainTracer(BaseCallbackHandler):
                     kwargs_copy['callbacks'].append(self)
 
                 # Store model name if available
-                if component_name in ["OpenAI", "ChatOpenAI_LangchainOpenAI", "ChatOpenAI_ChatModels", 
-                                    "ChatVertexAI", "ChatGoogleGenerativeAI", "ChatAnthropic", "ChatLiteLLM"]:
+                if component_name in ["OpenAI", "ChatOpenAI_LangchainOpenAI", "ChatOpenAI_ChatModels",
+                                    "ChatVertexAI", "VertexAI", "ChatGoogleGenerativeAI", "ChatAnthropic", 
+                                    "ChatLiteLLM", "ChatBedrock"]:
                     instance = args[0] if args else None
-                    model_name = kwargs.get('model_name') or kwargs.get('model')
+                    model_name = kwargs.get('model_name') or kwargs.get('model') or kwargs.get('model_id')
+
                     if instance and model_name:
                         self.model_names[id(instance)] = model_name
                 
@@ -217,12 +219,19 @@ class LangchainTracer(BaseCallbackHandler):
             components_to_patch["OpenAI"] = (OpenAI, "__init__")
         except ImportError:
             logger.debug("OpenAI not available for patching")
+
+        try:
+            from langchain_aws import ChatBedrock
+            components_to_patch["ChatBedrock"] = (ChatBedrock, "__init__")
+        except ImportError:
+            logger.debug("ChatBedrock not available for patching")
             
         try:
-            from langchain_google_vertexai import ChatVertexAI
+            from langchain_google_vertexai import ChatVertexAI, VertexAI
             components_to_patch["ChatVertexAI"] = (ChatVertexAI, "__init__")
+            components_to_patch["VertexAI"] = (VertexAI, "__init__")
         except ImportError:
-            logger.debug("ChatVertexAI not available for patching")
+            logger.debug("ChatVertexAI/VertexAI not available for patching")
             
         try:
             from langchain_google_genai import ChatGoogleGenerativeAI
@@ -298,6 +307,9 @@ class LangchainTracer(BaseCallbackHandler):
                     elif name == "ChatVertexAI":
                         from langchain_google_vertexai import ChatVertexAI
                         imported_components[name] = ChatVertexAI
+                    elif name == "VertexAI":
+                        from langchain_google_vertexai import VertexAI
+                        imported_components[name] = VertexAI
                     elif name == "ChatGoogleGenerativeAI":
                         from langchain_google_genai import ChatGoogleGenerativeAI
                         imported_components[name] = ChatGoogleGenerativeAI
@@ -487,9 +499,16 @@ class LangchainTracer(BaseCallbackHandler):
                     total_tokens = prompt_tokens + completion_tokens
                 except Exception as e:
                     # logger.debug(f"Error getting usage data: {e}")
-                    prompt_tokens = 0
-                    completion_tokens = 0
-                    total_tokens = 0
+                    try:
+                        usage_data = response.generations[0][0].generation_info['usage_metadata']
+                        prompt_tokens = usage_data.get("prompt_token_count", 0)
+                        completion_tokens = usage_data.get("candidates_token_count", 0)
+                        total_tokens = prompt_tokens + completion_tokens
+                    except Exception as e:
+                        # logger.debug(f"Error getting token usage: {e}")
+                        prompt_tokens = 0
+                        completion_tokens = 0
+                        total_tokens = 0
 
             # If no model name in llm_output, try to get it from stored model names
             try:
@@ -497,7 +516,7 @@ class LangchainTracer(BaseCallbackHandler):
                     model = list(self.model_names.values())[0]
             except Exception as e:
                 model=""
-            
+
             self.additional_metadata = {
                 'latency': latency,
                 'model_name': model,

{ragaai_catalyst-2.1.5b8.dist-info → ragaai_catalyst-2.1.5b10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ragaai_catalyst
-Version: 2.1.5b8
+Version: 2.1.5b10
 Summary: RAGA AI CATALYST
 Author-email: Kiran Scaria <kiran.scaria@raga.ai>, Kedar Gaikwad <kedar.gaikwad@raga.ai>, Dushyant Mahajan <dushyant.mahajan@raga.ai>, Siddhartha Kosti <siddhartha.kosti@raga.ai>, Ritika Goel <ritika.goel@raga.ai>, Vijay Chaurasia <vijay.chaurasia@raga.ai>
 Requires-Python: <3.13,>=3.9

{ragaai_catalyst-2.1.5b8.dist-info → ragaai_catalyst-2.1.5b10.dist-info}/RECORD

@@ -13,7 +13,7 @@ ragaai_catalyst/synthetic_data_generation.py,sha256=uDV9tNwto2xSkWg5XHXUvjErW-4P
 ragaai_catalyst/utils.py,sha256=TlhEFwLyRU690HvANbyoRycR3nQ67lxVUQoUOfTPYQ0,3772
 ragaai_catalyst/tracers/__init__.py,sha256=LfgTes-nHpazssbGKnn8kyLZNr49kIPrlkrqqoTFTfc,301
 ragaai_catalyst/tracers/distributed.py,sha256=AIRvS5Ur4jbFDXsUkYuCTmtGoHHx3LOG4n5tWOh610U,10330
-ragaai_catalyst/tracers/langchain_callback.py,sha256=lLeED0Eg2kT4-_O9IUw3pAyi_Hm4AaX57VfeSiOwaUw,28134
+ragaai_catalyst/tracers/langchain_callback.py,sha256=t5s9JD6HdzJRnAd9Zp8qLppCY6azz11hqHAykkNq9zw,29204
 ragaai_catalyst/tracers/llamaindex_callback.py,sha256=ZY0BJrrlz-P9Mg2dX-ZkVKG3gSvzwqBtk7JL_05MiYA,14028
 ragaai_catalyst/tracers/tracer.py,sha256=Yq2HhgT4785t9573kksJ7ngM3qCLPgZbZ0IpgOHdTTo,19223
 ragaai_catalyst/tracers/upload_traces.py,sha256=2TWdRTN6FMaX-dqDv8BJWQS0xrCGYKkXEYOi2kK3Z3Y,5487
@@ -48,7 +48,7 @@ ragaai_catalyst/tracers/agentic_tracing/utils/file_name_tracker.py,sha256=515NND
 ragaai_catalyst/tracers/agentic_tracing/utils/generic.py,sha256=WwXT01xmp8MSr7KinuDCSK9a1ifpLcT7ajFkvYviG_A,1190
 ragaai_catalyst/tracers/agentic_tracing/utils/get_user_trace_metrics.py,sha256=vPZ4dn4EHFW0kqd1GyRpsYXbfrRrd0DXCmh-pzsDBNE,1109
 ragaai_catalyst/tracers/agentic_tracing/utils/llm_utils.py,sha256=wlXCuaRe81s-7FWdJ_MquXFGRZZfNrZxLIIxl-Ohbqk,15541
-ragaai_catalyst/tracers/agentic_tracing/utils/model_costs.json,sha256=E_uKa1SSrigaorCiAShZr4inKNMc54jcEy4B_7pT4DA,295002
+ragaai_catalyst/tracers/agentic_tracing/utils/model_costs.json,sha256=kQwC8AYTfJCqPm1F_heR7FoEhIpEZgBRWvkHRncfhzU,298689
 ragaai_catalyst/tracers/agentic_tracing/utils/span_attributes.py,sha256=MqeRNGxzeuh9qTK0NbYMftl9V9Z0V7gMgBoHkrXP56k,1592
 ragaai_catalyst/tracers/agentic_tracing/utils/system_monitor.py,sha256=H8WNsk4v_5T6OUw4TFOzlDLjQhJwjh1nAMyMAoqMEi4,6946
 ragaai_catalyst/tracers/agentic_tracing/utils/trace_utils.py,sha256=RciiDdo2riibEoM8X0FKHaXi78y3bWwNkV8U0leqigk,3508
@@ -65,8 +65,8 @@ ragaai_catalyst/tracers/utils/__init__.py,sha256=KeMaZtYaTojilpLv65qH08QmpYclfpa
 ragaai_catalyst/tracers/utils/convert_langchain_callbacks_output.py,sha256=ofrNrxf2b1hpjDh_zeaxiYq86azn1MF3kW8-ViYPEg0,1641
 ragaai_catalyst/tracers/utils/langchain_tracer_extraction_logic.py,sha256=cghjCuUe8w-2MZdh9xgtRGe3y219u26GGzpnuY4Wt6Q,3047
 ragaai_catalyst/tracers/utils/utils.py,sha256=ViygfJ7vZ7U0CTSA1lbxVloHp4NSlmfDzBRNCJuMhis,2374
-ragaai_catalyst-2.1.5b8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-ragaai_catalyst-2.1.5b8.dist-info/METADATA,sha256=OaiEW7uA1wnQO562QbKGgtlZuue1PTGTjK9-AW5gkLQ,12764
-ragaai_catalyst-2.1.5b8.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ragaai_catalyst-2.1.5b8.dist-info/top_level.txt,sha256=HpgsdRgEJMk8nqrU6qdCYk3di7MJkDL0B19lkc7dLfM,16
-ragaai_catalyst-2.1.5b8.dist-info/RECORD,,
+ragaai_catalyst-2.1.5b10.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+ragaai_catalyst-2.1.5b10.dist-info/METADATA,sha256=DVGyoXWxgwks82eTOMYm_eNKxwcIvvbnuiRMA_f5EkU,12765
+ragaai_catalyst-2.1.5b10.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ragaai_catalyst-2.1.5b10.dist-info/top_level.txt,sha256=HpgsdRgEJMk8nqrU6qdCYk3di7MJkDL0B19lkc7dLfM,16
+ragaai_catalyst-2.1.5b10.dist-info/RECORD,,