openlit 1.33.1__tar.gz → 1.33.4__tar.gz

{openlit-1.33.1 → openlit-1.33.4}/PKG-INFO

@@ -1,8 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: openlit
-Version: 1.33.1
+Version: 1.33.4
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
-Home-page: https://github.com/openlit/openlit/tree/main/openlit/python
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu
 Author: OpenLIT
 Requires-Python: >=3.7.1,<4.0.0
@@ -26,6 +25,7 @@ Requires-Dist: requests (>=2.26.0,<3.0.0)
 Requires-Dist: schedule (>=1.2.2,<2.0.0)
 Requires-Dist: tiktoken (>=0.7.0,<0.8.0)
 Requires-Dist: xmltodict (>=0.13.0,<0.14.0)
+Project-URL: Homepage, https://github.com/openlit/openlit/tree/main/openlit/python
 Project-URL: Repository, https://github.com/openlit/openlit/tree/main/openlit/python
 Description-Content-Type: text/markdown
 
@@ -83,7 +83,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                          |                                                                          | [✅ Crawl4AI](https://docs.openlit.io/latest/integrations/crawl4ai)        |               |
 | [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                |                                                                          | [✅ FireCrawl](https://docs.openlit.io/latest/integrations/firecrawl)      |               |
 | [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          | [✅ Letta](https://docs.openlit.io/latest/integrations/letta)              |               |
-| [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                                |               |
+| [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          | [✅ SwarmZero](https://docs.openlit.io/latest/integrations/swarmzero)      |               |
 | [✅ Titan ML](https://docs.openlit.io/latest/integrations/titan-ml)                  |                                                                          |                                                |               |
 | [✅ Reka AI](https://docs.openlit.io/latest/integrations/reka)                       |                                                                          |                                                |               |
 | [✅ xAI](https://docs.openlit.io/latest/integrations/xai)                            |                                                                          |                                                |               |
@@ -106,6 +106,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 - [✅ Dynatrace](https://docs.openlit.io/latest/connections/dynatrace)
 - [✅ OpenObserve](https://docs.openlit.io/latest/connections/openobserve)
 - [✅ Highlight.io](https://docs.openlit.io/latest/connections/highlight)
+- [✅ SigLens](https://docs.openlit.io/latest/connections/siglens)
 
 ## 💿 Installation
 

{openlit-1.33.1 → openlit-1.33.4}/README.md

@@ -52,7 +52,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                          |                                                                          | [✅ Crawl4AI](https://docs.openlit.io/latest/integrations/crawl4ai)        |               |
 | [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                |                                                                          | [✅ FireCrawl](https://docs.openlit.io/latest/integrations/firecrawl)      |               |
 | [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          | [✅ Letta](https://docs.openlit.io/latest/integrations/letta)              |               |
-| [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                                |               |
+| [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          | [✅ SwarmZero](https://docs.openlit.io/latest/integrations/swarmzero)      |               |
 | [✅ Titan ML](https://docs.openlit.io/latest/integrations/titan-ml)                  |                                                                          |                                                |               |
 | [✅ Reka AI](https://docs.openlit.io/latest/integrations/reka)                       |                                                                          |                                                |               |
 | [✅ xAI](https://docs.openlit.io/latest/integrations/xai)                            |                                                                          |                                                |               |
@@ -75,6 +75,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 - [✅ Dynatrace](https://docs.openlit.io/latest/connections/dynatrace)
 - [✅ OpenObserve](https://docs.openlit.io/latest/connections/openobserve)
 - [✅ Highlight.io](https://docs.openlit.io/latest/connections/highlight)
+- [✅ SigLens](https://docs.openlit.io/latest/connections/siglens)
 
 ## 💿 Installation
 

{openlit-1.33.1 → openlit-1.33.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.33.1"
+version = "1.33.4"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 repository = "https://github.com/openlit/openlit/tree/main/openlit/python"

{openlit-1.33.1 → openlit-1.33.4}/src/openlit/instrumentation/astra/astra.py

@@ -87,7 +87,7 @@ def general_wrap(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.DB_INDEX_DIMENSION,
                                        kwargs.get("dimension", ""))
                     span.set_attribute(SemanticConvetion.DB_INDEX_METRIC,
-                                       kwargs.get("metric", ""))
+                                       str(kwargs.get("metric", "")))
                     span.set_attribute(SemanticConvetion.DB_OPERATION_API_ENDPOINT,
                                         instance.api_endpoint)
 

{openlit-1.33.1 → openlit-1.33.4}/src/openlit/instrumentation/astra/async_astra.py

@@ -87,7 +87,7 @@ def general_wrap(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.DB_INDEX_DIMENSION,
                                        kwargs.get("dimension", ""))
                     span.set_attribute(SemanticConvetion.DB_INDEX_METRIC,
-                                       kwargs.get("metric", ""))
+                                       str(kwargs.get("metric", "")))
                     span.set_attribute(SemanticConvetion.DB_OPERATION_API_ENDPOINT,
                                         instance.api_endpoint)
 

{openlit-1.33.1 → openlit-1.33.4}/src/openlit/instrumentation/langchain/langchain.py

@@ -508,11 +508,11 @@ def chat(gen_ai_endpoint, version, environment, application_name,
 
             try:
                 prompt = ""
-                if hasattr(response, 'response_metadata') and response.response_metadata:
-                    token_usage = response.response_metadata.get("token_usage", {})
-                    input_tokens = token_usage.get("prompt_tokens", 0)
-                    output_tokens = token_usage.get("completion_tokens", 0)
-                    model = response.response_metadata.get("model_name", "gpt-4")
+                if hasattr(response, 'usage_metadata') and response.usage_metadata:
+                    token_usage = response.usage_metadata
+                    input_tokens = token_usage.get("input_tokens", 0)
+                    output_tokens = token_usage.get("output_tokens", 0)
+                    model = instance.model_id
                     prompt = "" if isinstance(args[0], list) else args[0]
                 else:
                     if not isinstance(response, dict) or "output_text" not in response:
@@ -661,12 +661,27 @@ def achat(gen_ai_endpoint, version, environment, application_name,
             response = await wrapped(*args, **kwargs)
 
             try:
-                token_usage = response.response_metadata.get("token_usage", {})
-                input_tokens = token_usage.get("prompt_tokens", 0)
-                output_tokens = token_usage.get("completion_tokens", 0)
-                model = response.response_metadata.get("model_name", "gpt-4")
+                prompt = ""
+                if hasattr(response, 'usage_metadata') and response.usage_metadata:
+                    token_usage = response.usage_metadata
+                    input_tokens = token_usage.get("input_tokens", 0)
+                    output_tokens = token_usage.get("output_tokens", 0)
+                    model = instance.model_id
+                    prompt = "" if isinstance(args[0], list) else args[0]
+
+                else:
+                    if not isinstance(response, dict) or "output_text" not in response:
+                        return response
+                    # Fallback: Calculate tokens manually if response_metadata is missing
+                    model = "gpt-4o-mini"  # Fallback model
+                    input_texts = [
+                    doc.page_content for doc in response.get("input_documents", [])
+                    if isinstance(doc.page_content, str)
+                    ]
+                    input_tokens = sum(general_tokens(text) for text in input_texts)
+                    output_text = response.get("output_text", "")
+                    output_tokens = general_tokens(output_text)
 
-                prompt = "" if isinstance(args[0], list) else args[0]
                 # Calculate cost of the operation
                 cost = get_chat_model_cost(
                     model,

{openlit-1.33.1 → openlit-1.33.4}/src/openlit/instrumentation/openai/async_openai.py

@@ -478,11 +478,12 @@ def async_embedding(gen_ai_endpoint, version, environment, application_name,
                                     response_dict.get('usage').get('total_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
+
                 if trace_content:
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
                         attributes={
-                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("input", ""),
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: str(kwargs.get("input", "")),
                         },
                     )
 

{openlit-1.33.1 → openlit-1.33.4}/src/openlit/instrumentation/openai/openai.py

@@ -481,11 +481,12 @@ def embedding(gen_ai_endpoint, version, environment, application_name,
                                     response_dict.get('usage').get('total_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
+
                 if trace_content:
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
                         attributes={
-                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("input", ""),
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: str(kwargs.get("input", "")),
                         },
                     )