genai-otel-instrument 0.1.7.dev0__py3-none-any.whl → 0.1.10.dev0__py3-none-any.whl

genai_otel/__version__.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.7.dev0'
-__version_tuple__ = version_tuple = (0, 1, 7, 'dev0')
+__version__ = version = '0.1.10.dev0'
+__version_tuple__ = version_tuple = (0, 1, 10, 'dev0')
 
 __commit_id__ = commit_id = None

genai_otel/auto_instrument.py

@@ -19,6 +19,7 @@ from opentelemetry.sdk.trace.export import BatchSpanProcessor, ConsoleSpanExport
 from .config import OTelConfig
 from .cost_calculator import CostCalculator
 from .cost_enrichment_processor import CostEnrichmentSpanProcessor
+from .cost_enriching_exporter import CostEnrichingSpanExporter
 from .gpu_metrics import GPUMetricsCollector
 from .mcp_instrumentors import MCPInstrumentorManager
 from .metrics import (
@@ -169,14 +170,17 @@ def setup_auto_instrumentation(config: OTelConfig):
 
     set_global_textmap(TraceContextTextMapPropagator())
 
-    # Add cost enrichment processor for OpenInference instrumentors
-    # This enriches spans from smolagents, litellm, mcp with cost attributes
+    # Add cost enrichment processor for custom instrumentors (OpenAI, Ollama, etc.)
+    # These instrumentors set cost attributes directly, so processor is mainly for logging
+    # Also attempts to enrich OpenInference spans (smolagents, litellm, mcp), though
+    # the processor can't modify ReadableSpan - the exporter below handles that
+    cost_calculator = None
     if config.enable_cost_tracking:
         try:
             cost_calculator = CostCalculator()
             cost_processor = CostEnrichmentSpanProcessor(cost_calculator)
             tracer_provider.add_span_processor(cost_processor)
-            logger.info("Cost enrichment processor added for OpenInference instrumentors")
+            logger.info("Cost enrichment processor added")
         except Exception as e:
             logger.warning(f"Failed to add cost enrichment processor: {e}", exc_info=True)
 

genai_otel/cost_enriching_exporter.py

@@ -0,0 +1,207 @@
+"""Custom SpanExporter that enriches spans with cost attributes before export.
+
+This exporter wraps another exporter (like OTLPSpanExporter) and adds cost
+attributes to spans before passing them to the wrapped exporter.
+"""
+
+import logging
+from typing import Optional, Sequence
+
+from opentelemetry.sdk.trace import ReadableSpan
+from opentelemetry.sdk.trace.export import SpanExporter, SpanExportResult
+
+from .cost_calculator import CostCalculator
+
+logger = logging.getLogger(__name__)
+
+
+class CostEnrichingSpanExporter(SpanExporter):
+    """Wraps a SpanExporter and enriches spans with cost attributes before export.
+
+    This exporter:
+    1. Receives ReadableSpan objects from the SDK
+    2. Extracts model name and token usage from span attributes
+    3. Calculates cost using CostCalculator
+    4. Creates enriched span data with cost attributes
+    5. Exports to the wrapped exporter (e.g., OTLP)
+    """
+
+    def __init__(
+        self, wrapped_exporter: SpanExporter, cost_calculator: Optional[CostCalculator] = None
+    ):
+        """Initialize the cost enriching exporter.
+
+        Args:
+            wrapped_exporter: The underlying exporter to send enriched spans to.
+            cost_calculator: CostCalculator instance to use for cost calculations.
+                           If None, creates a new instance.
+        """
+        self.wrapped_exporter = wrapped_exporter
+        self.cost_calculator = cost_calculator or CostCalculator()
+        logger.info(
+            f"CostEnrichingSpanExporter initialized, wrapping {type(wrapped_exporter).__name__}"
+        )
+
+    def export(self, spans: Sequence[ReadableSpan]) -> SpanExportResult:
+        """Export spans after enriching them with cost attributes.
+
+        Args:
+            spans: Sequence of ReadableSpan objects to export.
+
+        Returns:
+            SpanExportResult from the wrapped exporter.
+        """
+        try:
+            # Enrich spans with cost attributes
+            enriched_spans = []
+            for span in spans:
+                enriched_span = self._enrich_span(span)
+                enriched_spans.append(enriched_span)
+
+            # Export to wrapped exporter
+            return self.wrapped_exporter.export(enriched_spans)
+
+        except Exception as e:
+            logger.error(f"Failed to export spans: {e}", exc_info=True)
+            return SpanExportResult.FAILURE
+
+    def _enrich_span(self, span: ReadableSpan) -> ReadableSpan:
+        """Enrich a span with cost attributes if applicable.
+
+        Args:
+            span: The original ReadableSpan.
+
+        Returns:
+            A new ReadableSpan with cost attributes added (or the original if not applicable).
+        """
+        try:
+            # Check if span has LLM-related attributes
+            if not span.attributes:
+                return span
+
+            attributes = dict(span.attributes)  # Make a mutable copy
+
+            # Check for model name - support both GenAI and OpenInference conventions
+            model = (
+                attributes.get("gen_ai.request.model")
+                or attributes.get("llm.model_name")
+                or attributes.get("embedding.model_name")
+            )
+            if not model:
+                return span
+
+            # Skip if cost attributes are already present
+            if "gen_ai.usage.cost.total" in attributes:
+                logger.debug(f"Span '{span.name}' already has cost attributes, skipping enrichment")
+                return span
+
+            # Extract token usage - support GenAI, OpenInference, and legacy conventions
+            prompt_tokens = (
+                attributes.get("gen_ai.usage.prompt_tokens")
+                or attributes.get("gen_ai.usage.input_tokens")
+                or attributes.get("llm.token_count.prompt")  # OpenInference
+                or 0
+            )
+            completion_tokens = (
+                attributes.get("gen_ai.usage.completion_tokens")
+                or attributes.get("gen_ai.usage.output_tokens")
+                or attributes.get("llm.token_count.completion")  # OpenInference
+                or 0
+            )
+
+            # Skip if no tokens recorded
+            if prompt_tokens == 0 and completion_tokens == 0:
+                return span
+
+            # Get call type - support both GenAI and OpenInference conventions
+            span_kind = attributes.get("openinference.span.kind", "").upper()
+            call_type = attributes.get("gen_ai.operation.name") or span_kind.lower() or "chat"
+
+            # Map operation names to call types
+            call_type_mapping = {
+                "chat": "chat",
+                "completion": "chat",
+                "embedding": "embedding",
+                "embeddings": "embedding",
+                "text_generation": "chat",
+                "image_generation": "image",
+                "audio": "audio",
+                "llm": "chat",
+                "chain": "chat",
+                "retriever": "embedding",
+                "reranker": "embedding",
+                "tool": "chat",
+                "agent": "chat",
+            }
+            normalized_call_type = call_type_mapping.get(str(call_type).lower(), "chat")
+
+            # Calculate cost
+            usage = {
+                "prompt_tokens": int(prompt_tokens),
+                "completion_tokens": int(completion_tokens),
+                "total_tokens": int(prompt_tokens) + int(completion_tokens),
+            }
+
+            cost_info = self.cost_calculator.calculate_granular_cost(
+                model=str(model),
+                usage=usage,
+                call_type=normalized_call_type,
+            )
+
+            if cost_info and cost_info.get("total", 0.0) > 0:
+                # Add cost attributes to the mutable copy
+                attributes["gen_ai.usage.cost.total"] = cost_info["total"]
+
+                if cost_info.get("prompt", 0.0) > 0:
+                    attributes["gen_ai.usage.cost.prompt"] = cost_info["prompt"]
+                if cost_info.get("completion", 0.0) > 0:
+                    attributes["gen_ai.usage.cost.completion"] = cost_info["completion"]
+
+                logger.info(
+                    f"Enriched span '{span.name}' with cost: {cost_info['total']:.6f} USD "
+                    f"for model {model} ({usage['total_tokens']} tokens)"
+                )
+
+                # Create a new ReadableSpan with enriched attributes
+                # ReadableSpan is a NamedTuple, so we need to replace it
+                from opentelemetry.sdk.trace import ReadableSpan as RS
+
+                enriched_span = RS(
+                    name=span.name,
+                    context=span.context,
+                    kind=span.kind,
+                    parent=span.parent,
+                    start_time=span.start_time,
+                    end_time=span.end_time,
+                    status=span.status,
+                    attributes=attributes,  # Use enriched attributes
+                    events=span.events,
+                    links=span.links,
+                    resource=span.resource,
+                    instrumentation_scope=span.instrumentation_scope,
+                )
+                return enriched_span
+
+        except Exception as e:
+            logger.warning(
+                f"Failed to enrich span '{getattr(span, 'name', 'unknown')}' with cost: {e}",
+                exc_info=True,
+            )
+
+        return span
+
+    def shutdown(self) -> None:
+        """Shutdown the wrapped exporter."""
+        logger.info("CostEnrichingSpanExporter shutting down")
+        self.wrapped_exporter.shutdown()
+
+    def force_flush(self, timeout_millis: int = 30000) -> bool:
+        """Force flush the wrapped exporter.
+
+        Args:
+            timeout_millis: Timeout in milliseconds.
+
+        Returns:
+            True if flush succeeded.
+        """
+        return self.wrapped_exporter.force_flush(timeout_millis)

genai_otel/cost_enrichment_processor.py

@@ -132,9 +132,8 @@ class CostEnrichmentSpanProcessor(SpanProcessor):
 
             if cost_info and cost_info.get("total", 0.0) > 0:
                 # Add cost attributes to the span
-                # Note: We can't modify ReadableSpan attributes directly,
-                # but we can if span is still a Span instance
-                if isinstance(span, Span):
+                # Use duck typing to check if span supports set_attribute
+                if hasattr(span, "set_attribute") and callable(getattr(span, "set_attribute")):
                     span.set_attribute("gen_ai.usage.cost.total", cost_info["total"])
 
                     if cost_info.get("prompt", 0.0) > 0:

genai_otel/instrumentors/huggingface_instrumentor.py

@@ -3,9 +3,11 @@
 This instrumentor automatically traces:
 1. HuggingFace Transformers pipelines (local model execution)
 2. HuggingFace Inference API calls via InferenceClient (used by smolagents)
+3. Direct model usage via AutoModelForCausalLM.generate() and forward()
 
 Note: Transformers runs models locally (no API costs), but InferenceClient makes
 API calls to HuggingFace endpoints which may have costs based on usage.
+Local model costs are estimated based on parameter count and token usage.
 """
 
 import logging
@@ -20,8 +22,10 @@ logger = logging.getLogger(__name__)
 class HuggingFaceInstrumentor(BaseInstrumentor):
     """Instrumentor for HuggingFace Transformers and Inference API.
 
-    Instruments both:
-    - transformers.pipeline (local execution, no API costs)
+    Instruments:
+    - transformers.pipeline (local execution, estimated costs)
+    - transformers.AutoModelForCausalLM.generate() (local execution, estimated costs)
+    - transformers.AutoModelForCausalLM.forward() (local execution, estimated costs)
     - huggingface_hub.InferenceClient (API calls, may have costs)
     """
 
@@ -30,6 +34,7 @@ class HuggingFaceInstrumentor(BaseInstrumentor):
         super().__init__()
         self._transformers_available = False
         self._inference_client_available = False
+        self._model_classes_instrumented = False
         self._check_availability()
 
     def _check_availability(self):
@@ -55,13 +60,14 @@ class HuggingFaceInstrumentor(BaseInstrumentor):
             self._inference_client_available = False
 
     def instrument(self, config: OTelConfig):
-        """Instrument HuggingFace Transformers pipelines and InferenceClient."""
-        self.config = config
+        """Instrument HuggingFace Transformers pipelines, model classes, and InferenceClient."""
+        self._setup_config(config)
 
         instrumented_count = 0
 
-        # Instrument transformers.pipeline if available
+        # Instrument transformers components if available
         if self._transformers_available:
+            # Instrument pipeline
             try:
                 self._instrument_transformers()
                 instrumented_count += 1
@@ -70,6 +76,15 @@ class HuggingFaceInstrumentor(BaseInstrumentor):
                 if config.fail_on_error:
                     raise
 
+            # Instrument model classes (AutoModelForCausalLM, etc.)
+            try:
+                self._instrument_model_classes()
+                instrumented_count += 1
+            except Exception as e:
+                logger.error("Failed to instrument HuggingFace model classes: %s", e, exc_info=True)
+                if config.fail_on_error:
+                    raise
+
         # Instrument InferenceClient if available
         if self._inference_client_available:
             try:
@@ -166,6 +181,164 @@ class HuggingFaceInstrumentor(BaseInstrumentor):
         InferenceClient.text_generation = wrapped_text_generation
         logger.debug("HuggingFace InferenceClient instrumented")
 
+    def _instrument_model_classes(self):
+        """Instrument HuggingFace model classes for direct model usage."""
+        try:
+            import wrapt
+
+            # Import GenerationMixin - the base class that provides generate() method
+            # All generative models (AutoModelForCausalLM, AutoModelForSeq2SeqLM, etc.) inherit from it
+            try:
+                from transformers.generation.utils import GenerationMixin
+            except ImportError:
+                # Fallback for older transformers versions
+                from transformers.generation import GenerationMixin
+
+            # Store reference to instrumentor for use in wrapper
+            instrumentor = self
+
+            # Wrap the generate() method at GenerationMixin level (all models inherit from this)
+            original_generate = GenerationMixin.generate
+
+            @wrapt.decorator
+            def generate_wrapper(wrapped, instance, args, kwargs):
+                """Wrapper for model.generate() method."""
+                # Extract model info
+                model_name = getattr(instance, "name_or_path", "unknown")
+                if hasattr(instance.config, "_name_or_path"):
+                    model_name = instance.config._name_or_path
+
+                # Get input token count
+                input_ids = kwargs.get("input_ids") or (args[0] if args else None)
+                prompt_tokens = 0
+                if input_ids is not None:
+                    if hasattr(input_ids, "shape"):
+                        prompt_tokens = int(input_ids.shape[-1])
+                    elif isinstance(input_ids, (list, tuple)):
+                        prompt_tokens = len(input_ids[0]) if input_ids else 0
+
+                # Create span
+                with instrumentor.tracer.start_as_current_span(
+                    "huggingface.model.generate"
+                ) as span:
+                    # Set attributes
+                    span.set_attribute("gen_ai.system", "huggingface")
+                    span.set_attribute("gen_ai.request.model", model_name)
+                    span.set_attribute("gen_ai.operation.name", "text_generation")
+                    span.set_attribute("gen_ai.request.type", "chat")
+
+                    # Extract generation parameters
+                    if "max_length" in kwargs:
+                        span.set_attribute("gen_ai.request.max_tokens", kwargs["max_length"])
+                    if "max_new_tokens" in kwargs:
+                        span.set_attribute("gen_ai.request.max_tokens", kwargs["max_new_tokens"])
+                    if "temperature" in kwargs:
+                        span.set_attribute("gen_ai.request.temperature", kwargs["temperature"])
+                    if "top_p" in kwargs:
+                        span.set_attribute("gen_ai.request.top_p", kwargs["top_p"])
+
+                    # Call original generate
+                    import time
+
+                    start_time = time.time()
+                    result = wrapped(*args, **kwargs)
+                    duration = time.time() - start_time
+
+                    # Extract output token count
+                    completion_tokens = 0
+                    if hasattr(result, "shape"):
+                        # result is a tensor
+                        total_length = int(result.shape[-1])
+                        completion_tokens = max(0, total_length - prompt_tokens)
+                    elif isinstance(result, (list, tuple)):
+                        # result is a list of sequences
+                        if result and hasattr(result[0], "shape"):
+                            total_length = int(result[0].shape[-1])
+                            completion_tokens = max(0, total_length - prompt_tokens)
+
+                    total_tokens = prompt_tokens + completion_tokens
+
+                    # Set token usage attributes
+                    if prompt_tokens > 0:
+                        span.set_attribute("gen_ai.usage.prompt_tokens", prompt_tokens)
+                    if completion_tokens > 0:
+                        span.set_attribute("gen_ai.usage.completion_tokens", completion_tokens)
+                    if total_tokens > 0:
+                        span.set_attribute("gen_ai.usage.total_tokens", total_tokens)
+
+                    # Record metrics
+                    if instrumentor.request_counter:
+                        instrumentor.request_counter.add(
+                            1, {"model": model_name, "provider": "huggingface"}
+                        )
+
+                    if instrumentor.token_counter and total_tokens > 0:
+                        if prompt_tokens > 0:
+                            instrumentor.token_counter.add(
+                                prompt_tokens, {"token_type": "prompt", "operation": span.name}
+                            )
+                        if completion_tokens > 0:
+                            instrumentor.token_counter.add(
+                                completion_tokens,
+                                {"token_type": "completion", "operation": span.name},
+                            )
+
+                    if instrumentor.latency_histogram:
+                        instrumentor.latency_histogram.record(duration, {"operation": span.name})
+
+                    # Calculate and record cost if enabled
+                    if (
+                        instrumentor.config
+                        and instrumentor.config.enable_cost_tracking
+                        and total_tokens > 0
+                    ):
+                        try:
+                            usage = {
+                                "prompt_tokens": prompt_tokens,
+                                "completion_tokens": completion_tokens,
+                                "total_tokens": total_tokens,
+                            }
+
+                            costs = instrumentor.cost_calculator.calculate_granular_cost(
+                                model=model_name, usage=usage, call_type="chat"
+                            )
+
+                            if costs["total"] > 0:
+                                if instrumentor.cost_counter:
+                                    instrumentor.cost_counter.add(
+                                        costs["total"], {"model": model_name}
+                                    )
+                                span.set_attribute("gen_ai.usage.cost.total", costs["total"])
+                                if costs["prompt"] > 0:
+                                    span.set_attribute("gen_ai.usage.cost.prompt", costs["prompt"])
+                                if costs["completion"] > 0:
+                                    span.set_attribute(
+                                        "gen_ai.usage.cost.completion", costs["completion"]
+                                    )
+
+                                logger.debug(
+                                    f"HuggingFace model {model_name}: {total_tokens} tokens, "
+                                    f"cost: ${costs['total']:.6f}"
+                                )
+                        except Exception as e:
+                            logger.warning(f"Failed to calculate cost: {e}")
+
+                    return result
+
+            # Apply wrapper to GenerationMixin.generate (all models inherit this)
+            GenerationMixin.generate = generate_wrapper(original_generate)
+
+            self._model_classes_instrumented = True
+            logger.debug(
+                "HuggingFace GenerationMixin.generate() instrumented "
+                "(covers all models: AutoModelForCausalLM, AutoModelForSeq2SeqLM, etc.)"
+            )
+
+        except ImportError as e:
+            logger.debug(f"Could not import model classes for instrumentation: {e}")
+        except Exception as e:
+            raise  # Re-raise to be caught by instrument() method
+
     def _extract_inference_client_attributes(self, instance, args, kwargs) -> Dict[str, str]:
         """Extract attributes from Inference API call."""
         attrs = {}

genai_otel/llm_pricing.json

@@ -109,6 +109,16 @@
         "512x512": 0.01,
         "1024x1024": 0.012
       }
+    },
+    "grok-image": {
+      "standard": {
+        "per_image": 0.07
+      }
+    },
+    "xai-grok-image": {
+      "standard": {
+        "per_image": 0.07
+      }
     }
   },
   "audio": {
@@ -149,6 +159,22 @@
       "promptPrice": 0.002,
       "completionPrice": 0.008
     },
+    "gpt-5": {
+      "promptPrice": 0.00125,
+      "completionPrice": 0.01
+    },
+    "gpt-5-2025-08-07": {
+      "promptPrice": 0.00125,
+      "completionPrice": 0.01
+    },
+    "gpt-5-mini": {
+      "promptPrice": 0.00025,
+      "completionPrice": 0.002
+    },
+    "gpt-5-nano": {
+      "promptPrice": 0.0001,
+      "completionPrice": 0.0004
+    },
     "gpt-4o": {
       "promptPrice": 0.0005,
       "completionPrice": 0.0015
@@ -249,6 +275,22 @@
       "promptPrice": 0.015,
       "completionPrice": 0.075
     },
+    "claude-4-opus": {
+      "promptPrice": 0.015,
+      "completionPrice": 0.075
+    },
+    "claude-opus-4": {
+      "promptPrice": 0.015,
+      "completionPrice": 0.075
+    },
+    "claude-opus-4-1": {
+      "promptPrice": 0.015,
+      "completionPrice": 0.075
+    },
+    "claude-opus-4.1": {
+      "promptPrice": 0.015,
+      "completionPrice": 0.075
+    },
     "claude-3-sonnet-20240229": {
       "promptPrice": 0.003,
       "completionPrice": 0.015
@@ -257,6 +299,34 @@
       "promptPrice": 0.00025,
       "completionPrice": 0.00125
     },
+    "claude-3-5-sonnet-20240620": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "claude-3-5-sonnet-20241022": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "claude-3-5-haiku-20241022": {
+      "promptPrice": 0.0008,
+      "completionPrice": 0.004
+    },
+    "claude-sonnet-4-5": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "claude-sonnet-4-5-20250929": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "claude-3-7-sonnet": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "claude-haiku-4-5": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.005
+    },
     "command": {
       "promptPrice": 0.001,
       "completionPrice": 0.002
@@ -441,6 +511,14 @@
       "promptPrice": 0.00125,
       "completionPrice": 0.01
     },
+    "gemini-2-5-flash-image": {
+      "promptPrice": 0.0003,
+      "completionPrice": 0.03
+    },
+    "nano-banana": {
+      "promptPrice": 0.0003,
+      "completionPrice": 0.03
+    },
     "text-bison": {
       "promptPrice": 0.001,
       "completionPrice": 0.002
@@ -537,6 +615,38 @@
       "promptPrice": 0.0005,
       "completionPrice": 0.0015
     },
+    "grok-2-1212": {
+      "promptPrice": 0.002,
+      "completionPrice": 0.01
+    },
+    "grok-2-vision-1212": {
+      "promptPrice": 0.002,
+      "completionPrice": 0.01
+    },
+    "grok-3": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "grok-3-mini": {
+      "promptPrice": 0.0003,
+      "completionPrice": 0.0005
+    },
+    "grok-3-fast": {
+      "promptPrice": 0.005,
+      "completionPrice": 0.025
+    },
+    "grok-3-mini-fast": {
+      "promptPrice": 0.0006,
+      "completionPrice": 0.004
+    },
+    "grok-4": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.015
+    },
+    "grok-4-fast": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0005
+    },
     "jamba-1.5-mini": {
       "promptPrice": 0.0002,
       "completionPrice": 0.0004
@@ -565,6 +675,26 @@
       "promptPrice": 0.0012,
       "completionPrice": 0.0012
     },
+    "qwen3-next-80b-a3b-instruct": {
+      "promptPrice": 0.000525,
+      "completionPrice": 0.0021
+    },
+    "qwen3-next-80b-a3b-thinking": {
+      "promptPrice": 0.000525,
+      "completionPrice": 0.0063
+    },
+    "qwen3-coder-480b-a35b-instruct": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.005
+    },
+    "qwen3-max": {
+      "promptPrice": 0.0012,
+      "completionPrice": 0.006
+    },
+    "qwen-qwen3-max": {
+      "promptPrice": 0.0012,
+      "completionPrice": 0.006
+    },
     "codellama/CodeLlama-34b-Instruct-hf": {
       "promptPrice": 0.0008,
       "completionPrice": 0.0008
@@ -613,13 +743,29 @@
       "promptPrice": 0.00059,
       "completionPrice": 0.00079
     },
+    "llama-4-scout": {
+      "promptPrice": 0.00015,
+      "completionPrice": 0.0005
+    },
     "llama-4-scout-17bx16e-128k": {
-      "promptPrice": 0.00011,
-      "completionPrice": 0.00034
+      "promptPrice": 0.00015,
+      "completionPrice": 0.0005
+    },
+    "llama-4-maverick": {
+      "promptPrice": 0.00022,
+      "completionPrice": 0.00085
     },
     "llama-4-maverick-17bx128e-128k": {
-      "promptPrice": 0.0002,
-      "completionPrice": 0.0006
+      "promptPrice": 0.00022,
+      "completionPrice": 0.00085
+    },
+    "meta-llama/Llama-4-Scout": {
+      "promptPrice": 0.00015,
+      "completionPrice": 0.0005
+    },
+    "meta-llama/Llama-4-Maverick": {
+      "promptPrice": 0.00022,
+      "completionPrice": 0.00085
     },
     "llama-guard-4-12b": {
       "promptPrice": 0.0002,
@@ -773,7 +919,7 @@
       "promptPrice": 0.0003,
       "completionPrice": 0.0006
     },
-    "qwen3:3b": {
+    "qwen3:4b": {
       "promptPrice": 0.0003,
       "completionPrice": 0.0006
     },
@@ -857,9 +1003,161 @@
       "promptPrice": 0.0008,
       "completionPrice": 0.0008
     },
+    "ibm-granite-3-1-8b-instruct": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "ibm-granite-3-8b-instruct": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite-3-8b-instruct": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite-embedding-107m-multilingual": {
+      "promptPrice": 0.0001,
+      "completionPrice": 0.0001
+    },
+    "granite-embedding-278m-multilingual": {
+      "promptPrice": 0.0001,
+      "completionPrice": 0.0001
+    },
     "deepseek-v3.1": {
-      "promptPrice": 0.0012,
-      "completionPrice": 0.0012
+      "promptPrice": 0.00056,
+      "completionPrice": 0.00168
+    },
+    "sarvam-m": {
+      "promptPrice": 0,
+      "completionPrice": 0
+    },
+    "sarvamai/sarvam-m": {
+      "promptPrice": 0,
+      "completionPrice": 0
+    },
+    "sarvam-chat": {
+      "promptPrice": 0,
+      "completionPrice": 0
+    },
+    "granite-4-0-h-small": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite-4-0-h-tiny": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite-4-0-h-micro": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite-4-0-micro": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "ibm-granite/granite-4.0-h-small": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "ibm-granite/granite-4.0-h-tiny": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "ibm-granite/granite-4.0-h-micro": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite:3b": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "granite:8b": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0002
+    },
+    "mistral-large-24-11": {
+      "promptPrice": 0.008,
+      "completionPrice": 0.024
+    },
+    "mistral-large-2411": {
+      "promptPrice": 0.008,
+      "completionPrice": 0.024
+    },
+    "mistral-small-3-1": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
+    },
+    "mistral-small-3.1": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
+    },
+    "mistral-medium-3": {
+      "promptPrice": 0.0004,
+      "completionPrice": 0.002
+    },
+    "mistral-medium-2025": {
+      "promptPrice": 0.0004,
+      "completionPrice": 0.002
+    },
+    "magistral-small": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
+    },
+    "magistral-medium": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.009
+    },
+    "codestral-25-01": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
+    },
+    "codestral-2501": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
+    },
+    "lfm-7b": {
+      "promptPrice": 0.0003,
+      "completionPrice": 0.0006
+    },
+    "liquid/lfm-7b": {
+      "promptPrice": 0.0003,
+      "completionPrice": 0.0006
+    },
+    "snowflake-arctic": {
+      "promptPrice": 0.0008,
+      "completionPrice": 0.0024
+    },
+    "snowflake-arctic-instruct": {
+      "promptPrice": 0.0008,
+      "completionPrice": 0.0024
+    },
+    "snowflake/snowflake-arctic-instruct": {
+      "promptPrice": 0.0008,
+      "completionPrice": 0.0024
+    },
+    "snowflake-arctic-embed-l-v2.0": {
+      "promptPrice": 0.00005,
+      "completionPrice": 0.00005
+    },
+    "nvidia-nemotron-4-340b-instruct": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.009
+    },
+    "nvidia/nemotron-4-340b-instruct": {
+      "promptPrice": 0.003,
+      "completionPrice": 0.009
+    },
+    "nvidia-nemotron-mini": {
+      "promptPrice": 0.0002,
+      "completionPrice": 0.0004
+    },
+    "nvidia/llama-3.1-nemotron-70b-instruct": {
+      "promptPrice": 0.0008,
+      "completionPrice": 0.0008
+    },
+    "servicenow-now-assist": {
+      "promptPrice": 0.001,
+      "completionPrice": 0.003
     },
     "llama3.1:405b": {
       "promptPrice": 0.0012,

{genai_otel_instrument-0.1.7.dev0.dist-info → genai_otel_instrument-0.1.10.dev0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: genai-otel-instrument
-Version: 0.1.7.dev0
+Version: 0.1.10.dev0
 Summary: Comprehensive OpenTelemetry auto-instrumentation for LLM/GenAI applications
 Author-email: Kshitij Thakkar <kshitijthakkar@rocketmail.com>
 License: Apache-2.0
@@ -180,6 +180,12 @@ Dynamic: license-file
 
 # GenAI OpenTelemetry Auto-Instrumentation
 
+<div align="center">
+  <img src=".github/images/Logo.jpg" alt="GenAI OpenTelemetry Instrumentation Logo" width="400"/>
+</div>
+
+<br/>
+
 [![PyPI version](https://badge.fury.io/py/genai-otel-instrument.svg)](https://badge.fury.io/py/genai-otel-instrument)
 [![Python Versions](https://img.shields.io/pypi/pyversions/genai-otel-instrument.svg)](https://pypi.org/project/genai-otel-instrument/)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
@@ -200,6 +206,14 @@ Dynamic: license-file
 [![Semantic Conventions](https://img.shields.io/badge/OTel%20Semconv-GenAI%20v1.28-orange)](https://opentelemetry.io/docs/specs/semconv/gen-ai/)
 [![CI/CD](https://img.shields.io/badge/CI%2FCD-GitHub%20Actions-2088FF?logo=github-actions&logoColor=white)](https://github.com/Mandark-droid/genai_otel_instrument/actions)
 
+---
+
+<div align="center">
+  <img src=".github/images/Landing_Page.jpg" alt="GenAI OpenTelemetry Instrumentation Overview" width="800"/>
+</div>
+
+---
+
 Production-ready OpenTelemetry instrumentation for GenAI/LLM applications with zero-code setup.
 
 ## Features
@@ -257,7 +271,8 @@ For a more comprehensive demonstration of various LLM providers and MCP tools, r
 
 ### LLM Providers (Auto-detected)
 - **With Full Cost Tracking**: OpenAI, Anthropic, Google AI, AWS Bedrock, Azure OpenAI, Cohere, Mistral AI, Together AI, Groq, Ollama, Vertex AI
-- **Hardware/Local Pricing**: Replicate (hardware-based $/second), HuggingFace (local execution, free)
+- **Hardware/Local Pricing**: Replicate (hardware-based $/second), HuggingFace (local execution with estimated costs)
+  - **HuggingFace Support**: `pipeline()`, `AutoModelForCausalLM.generate()`, `AutoModelForSeq2SeqLM.generate()`, `InferenceClient` API calls
 - **Other Providers**: Anyscale
 
 ### Frameworks
@@ -288,6 +303,65 @@ The processor supports OpenInference semantic conventions:
 pip install genai-otel-instrument[openinference]
 ```
 
+## Screenshots
+
+See the instrumentation in action across different LLM providers and observability backends.
+
+### OpenAI Instrumentation
+Full trace capture for OpenAI API calls with token usage, costs, and latency metrics.
+
+<div align="center">
+  <img src=".github/images/Screenshots/Traces_OpenAI.png" alt="OpenAI Traces" width="900"/>
+</div>
+
+### Ollama (Local LLM) Instrumentation
+Zero-code instrumentation for local models running on Ollama with comprehensive observability.
+
+<div align="center">
+  <img src=".github/images/Screenshots/Traces_Ollama.png" alt="Ollama Traces" width="900"/>
+</div>
+
+### HuggingFace Transformers
+Direct instrumentation of HuggingFace Transformers with automatic token counting and cost estimation.
+
+<div align="center">
+  <img src=".github/images/Screenshots/Trace_HuggingFace_Transformer_Models.png" alt="HuggingFace Transformer Traces" width="900"/>
+</div>
+
+### SmolAgents Framework
+Complete agent workflow tracing with tool calls, iterations, and cost breakdown.
+
+<div align="center">
+  <img src=".github/images/Screenshots/Traces_SmolAgent_with_tool_calls.png" alt="SmolAgent Traces with Tool Calls" width="900"/>
+</div>
+
+### GPU Metrics Collection
+Real-time GPU utilization, memory, temperature, and power consumption metrics.
+
+<div align="center">
+  <img src=".github/images/Screenshots/GPU_Metrics.png" alt="GPU Metrics Dashboard" width="900"/>
+</div>
+
+### Additional Screenshots
+
+- **[Token Cost Breakdown](.github/images/Screenshots/Traces_SmolAgent_Token_Cost_breakdown.png)** - Detailed token usage and cost analysis for SmolAgent workflows
+- **[OpenSearch Dashboard](.github/images/Screenshots/GENAI_OpenSearch_output.png)** - GenAI metrics visualization in OpenSearch/Kibana
+
+---
+
+## Demo Video
+
+Watch a comprehensive walkthrough of GenAI OpenTelemetry Auto-Instrumentation in action, demonstrating setup, configuration, and real-time observability across multiple LLM providers.
+
+<div align="center">
+
+  **🎥 [Watch Demo Video](https://youtu.be/YOUR_VIDEO_ID_HERE)**
+  *(Coming Soon)*
+
+</div>
+
+---
+
 ## Cost Tracking Coverage
 
 The library includes comprehensive cost tracking with pricing data for **145+ models** across **11 providers**:
@@ -307,7 +381,10 @@ The library includes comprehensive cost tracking with pricing data for **145+ mo
 
 ### Special Pricing Models
 - **Replicate**: Hardware-based pricing ($/second of GPU/CPU time) - not token-based
-- **HuggingFace Transformers**: Local execution - no API costs
+- **HuggingFace Transformers**: Local model execution with estimated costs based on parameter count
+  - Supports `pipeline()`, `AutoModelForCausalLM.generate()`, `AutoModelForSeq2SeqLM.generate()`
+  - Cost estimation uses GPU/compute resource pricing tiers (tiny/small/medium/large)
+  - Automatic token counting from tensor shapes
 
 ### Pricing Features
 - **Differential Pricing**: Separate rates for prompt tokens vs. completion tokens
@@ -836,38 +913,6 @@ genai_otel.instrument(
 - `gen_ai.eval.bias_categories` - Detected bias types (array)
 - `gen_ai.eval.toxicity_categories` - Toxicity categories (array)
 
-#### 📊 Enhanced OpenTelemetry Compliance
-
-Completing remaining items from [OTEL_SEMANTIC_GAP_ANALYSIS_AND_IMPLEMENTATION_PLAN.md](OTEL_SEMANTIC_GAP_ANALYSIS_AND_IMPLEMENTATION_PLAN.md):
-
-**Phase 4: Optional Enhancements (✅ COMPLETED)**
-
-All Phase 4 features are now available! See the [Advanced Features](#advanced-features) section for detailed documentation.
-
-- ✅ **Session & User Tracking** - Track sessions and users across requests with custom extractor functions
-  - Configurable via `session_id_extractor` and `user_id_extractor` in `OTelConfig`
-  - Automatically adds `session.id` and `user.id` span attributes
-  - See [Session and User Tracking](#session-and-user-tracking) for usage examples
-
-- ✅ **RAG/Embedding Attributes** - Enhanced observability for retrieval-augmented generation
-  - Helper methods: `add_embedding_attributes()` and `add_retrieval_attributes()`
-  - Embedding attributes: `embedding.model_name`, `embedding.text`, `embedding.vector.dimension`
-  - Retrieval attributes: `retrieval.query`, `retrieval.document_count`, `retrieval.documents.{i}.document.*`
-  - See [RAG and Embedding Attributes](#rag-and-embedding-attributes) for usage examples
-  - Complete example: `examples/phase4_session_rag_tracking.py`
-
-**Note on Agent Workflow Tracking:**
-
-Agent workflow observability is already provided by the OpenInference Smolagents instrumentor (included when `smolagents` is in `enabled_instrumentors`). This is not a new Phase 4 feature, but an existing capability:
-
-- `openinference.span.kind: "AGENT"` - Identifies agent spans
-- `agent.name` - Agent identifier (via OpenInference)
-- `agent.iteration` - Current iteration number (via OpenInference)
-- `agent.action` - Action taken (via OpenInference)
-- `agent.observation` - Observation received (via OpenInference)
-
-Agent tracking requires Python >= 3.10 and the `smolagents` library. See [OpenInference Integration](#openinference-optional---python-310-only) for details.
-
 #### 🔄 Migration Support
 
 **Backward Compatibility:**

{genai_otel_instrument-0.1.7.dev0.dist-info → genai_otel_instrument-0.1.10.dev0.dist-info}/RECORD

@@ -1,13 +1,14 @@
 genai_otel/__init__.py,sha256=OWgm1dihRkwBQU8fUPnVhE5XCZeF5f15UyH4w6LqGZU,4469
-genai_otel/__version__.py,sha256=amWIeki4bm5YbDNKNBNcQKLS8IoAVLPuipySazUun7Y,751
-genai_otel/auto_instrument.py,sha256=NF0Bo_sFMynSmXNh5KFxdsJQPKuPE2NI_bel1i-CtxU,16260
+genai_otel/__version__.py,sha256=TXc4a_5Wlqj1sa6bOI4rf0g8ARueANgrhEv_5PaXbcs,753
+genai_otel/auto_instrument.py,sha256=uHJGTlSI4UO-sdFtWgxSmNkhd1_GTWvr3S-rY8MQ4E4,16513
 genai_otel/cli.py,sha256=mbhaTU0WIAkvPKdIing-guIxPDjEKQftChWQUtPFzkY,3170
 genai_otel/config.py,sha256=2CIbZH8WKkVzr73y9AOWmscvEW-kUwMLSAyOy9BFqGI,7871
 genai_otel/cost_calculator.py,sha256=BOW-TC41lJ1GcL4hIGZ4NySyV8aro4_juMOe2IqtJ-A,18115
-genai_otel/cost_enrichment_processor.py,sha256=07T7q2gBbB7b-L0Dt5VDsVuxB3XSfnpbtFjcV3ZTpk0,7099
+genai_otel/cost_enriching_exporter.py,sha256=iED7njK21UBKlxRElGfqSs66gMkzDCr8fm-4ZkJBiLU,7874
+genai_otel/cost_enrichment_processor.py,sha256=fQoVosBUgshD9ZRxWpwqqPWYnyhrvKBTJAW0S2H7t1E,7090
 genai_otel/exceptions.py,sha256=gIRvbI7c4V-M-PG9jS0o4ESRwHUWCm6DVihjfyJI1yg,429
 genai_otel/gpu_metrics.py,sha256=hBawkm-NErviwiLzb7z92INstFHec2pREn945rYgrT4,13408
-genai_otel/llm_pricing.json,sha256=ZQ1uILEdQ_yNzenvlPpKazo9NnYqEZgbL_tzQ6Mw2oc,20825
+genai_otel/llm_pricing.json,sha256=f3WNQwiby6rLOQaPX_jJharftHgclNQM3bzibnDiiEQ,27879
 genai_otel/logging_config.py,sha256=S8apGf93nBjoi_Bhce-LxwTwGTaJUeduPXKiWZ5SIa8,1418
 genai_otel/metrics.py,sha256=Vngwtc1MAMAE7JVpbT_KfiCQ5TdIAKIs_0oztjJdDTg,2671
 genai_otel/py.typed,sha256=WJtVGe64tcQSssSo4RD7zCf_3u7X2BmFCWDCroWOcaQ,88
@@ -20,7 +21,7 @@ genai_otel/instrumentors/base.py,sha256=5N0eMDoPT49PedhoDM0EGu8NE9UvseaiWhqfb9UH
 genai_otel/instrumentors/cohere_instrumentor.py,sha256=fsKvHaWvMRAGRbOtybVJVVz-FS_-wmgTJo3Q_F86BOY,5074
 genai_otel/instrumentors/google_ai_instrumentor.py,sha256=ExNo0_OxfCxaRpuUXYU8UZ-ClQRHRLUvf7-kMC6zdc8,2984
 genai_otel/instrumentors/groq_instrumentor.py,sha256=bCm7IDmDyvg0-XuzcCSO5xf9QvDlQGwb7bdQ_ooS6QI,3398
-genai_otel/instrumentors/huggingface_instrumentor.py,sha256=XlSuHEkxEWu0dAXtw1pAFE3n-M8WFRfKUsgbUSV_Arw,9204
+genai_otel/instrumentors/huggingface_instrumentor.py,sha256=wvolJZnq9YKfJsvNvUnoOpL1tbeGy0DuxVmmmI1_BoA,17815
 genai_otel/instrumentors/langchain_instrumentor.py,sha256=002ZrKP04l7VaYxo7nAAwl-uvMVwpzVehO2oS23ed-o,2685
 genai_otel/instrumentors/llamaindex_instrumentor.py,sha256=zZ1J7W4yQo1Ur6Y5y0UXpDdEx9oDnmsqNIin5Jrv9os,1206
 genai_otel/instrumentors/mistralai_instrumentor.py,sha256=Blo8X4WV-xQe-xF-jhkaGPavkgayANf1F3zCTzuhuL0,12478
@@ -37,9 +38,9 @@ genai_otel/mcp_instrumentors/kafka_instrumentor.py,sha256=QJYJC1rvo_zZAIaw-cp_Ic
 genai_otel/mcp_instrumentors/manager.py,sha256=1Pj5lkEOL8Yq1Oeud4ZExN6k6NLIVtTzKnFLNiFdJvw,5895
 genai_otel/mcp_instrumentors/redis_instrumentor.py,sha256=KUbs0dMyfMzU4T0SS8u43I5fvr09lcBBM92I3KCsYUw,943
 genai_otel/mcp_instrumentors/vector_db_instrumentor.py,sha256=2vhnk4PGpfYKr-XlRbnCIOap4BPKHOn--fh-ai2YXlM,9994
-genai_otel_instrument-0.1.7.dev0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-genai_otel_instrument-0.1.7.dev0.dist-info/METADATA,sha256=ogiTaS3MknTz1tAq51JbpZzpxozuLnkD-f2Z4iu57vk,39184
-genai_otel_instrument-0.1.7.dev0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-genai_otel_instrument-0.1.7.dev0.dist-info/entry_points.txt,sha256=E9UqoHA_fq69yNGAY3SRYf5HH94sZT5DiDueiU1v0KM,57
-genai_otel_instrument-0.1.7.dev0.dist-info/top_level.txt,sha256=cvCm8PUwvYUSQKruk-x6S-_YuDyhOBk8gD910XICcbg,11
-genai_otel_instrument-0.1.7.dev0.dist-info/RECORD,,
+genai_otel_instrument-0.1.10.dev0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+genai_otel_instrument-0.1.10.dev0.dist-info/METADATA,sha256=kg9GntpKyP9CarQ53N3RJuzDIcdk2Gtp2Bbb2NC1LVQ,40024
+genai_otel_instrument-0.1.10.dev0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+genai_otel_instrument-0.1.10.dev0.dist-info/entry_points.txt,sha256=E9UqoHA_fq69yNGAY3SRYf5HH94sZT5DiDueiU1v0KM,57
+genai_otel_instrument-0.1.10.dev0.dist-info/top_level.txt,sha256=cvCm8PUwvYUSQKruk-x6S-_YuDyhOBk8gD910XICcbg,11
+genai_otel_instrument-0.1.10.dev0.dist-info/RECORD,,