genai-otel-instrument 0.1.1.dev0__py3-none-any.whl → 0.1.2.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 = '0.1.1.dev0'
-__version_tuple__ = version_tuple = (0, 1, 1, 'dev0')
+__version__ = version = '0.1.2.dev0'
+__version_tuple__ = version_tuple = (0, 1, 2, 'dev0')
 
 __commit_id__ = commit_id = None

genai_otel/gpu_metrics.py

@@ -43,6 +43,7 @@ class GPUMetricsCollector:
         self.gpu_utilization_counter: Optional[ObservableCounter] = None
         self.gpu_memory_used_gauge: Optional[ObservableGauge] = None
         self.gpu_temperature_gauge: Optional[ObservableGauge] = None
+        self.gpu_power_gauge: Optional[ObservableGauge] = None
         self.config = config
         self.interval = interval  # seconds
         self.gpu_available = False
@@ -93,6 +94,12 @@ class GPUMetricsCollector:
                 description="GPU temperature in Celsius",
                 unit="Cel",
             )
+            self.gpu_power_gauge = self.meter.create_observable_gauge(
+                "gen_ai.gpu.power",  # Fixed metric name
+                callbacks=[self._observe_gpu_power],
+                description="GPU power consumption in Watts",
+                unit="W",
+            )
         except Exception as e:
             logger.error("Failed to create GPU metrics instruments: %s", e, exc_info=True)
 
@@ -185,6 +192,33 @@ class GPUMetricsCollector:
         except Exception as e:
             logger.error("Error observing GPU temperature: %s", e)
 
+    def _observe_gpu_power(self, options):
+        """Observable callback for GPU power consumption."""
+        if not NVML_AVAILABLE or not self.gpu_available:
+            return
+
+        try:
+            pynvml.nvmlInit()
+            device_count = pynvml.nvmlDeviceGetCount()
+
+            for i in range(device_count):
+                handle = pynvml.nvmlDeviceGetHandleByIndex(i)
+                device_name = self._get_device_name(handle, i)
+
+                try:
+                    # Power usage is returned in milliwatts, convert to watts
+                    power_mw = pynvml.nvmlDeviceGetPowerUsage(handle)
+                    power_w = power_mw / 1000.0
+                    yield Observation(
+                        value=power_w, attributes={"gpu_id": str(i), "gpu_name": device_name}
+                    )
+                except Exception as e:
+                    logger.debug("Failed to get GPU power for GPU %d: %s", i, e)
+
+            pynvml.nvmlShutdown()
+        except Exception as e:
+            logger.error("Error observing GPU power: %s", e)
+
     def start(self):
         """Starts the GPU metrics collection.
 

{genai_otel_instrument-0.1.1.dev0.dist-info → genai_otel_instrument-0.1.2.dev0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: genai-otel-instrument
-Version: 0.1.1.dev0
+Version: 0.1.2.dev0
 Summary: Comprehensive OpenTelemetry auto-instrumentation for LLM/GenAI applications
 Author-email: Kshitij Thakkar <kshitijthakkar@rocketmail.com>
 License: Apache-2.0
@@ -180,6 +180,26 @@ Dynamic: license-file
 
 # GenAI OpenTelemetry Auto-Instrumentation
 
+[![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)
+[![Downloads](https://static.pepy.tech/badge/genai-otel-instrument)](https://pepy.tech/project/genai-otel-instrument)
+[![Downloads/Month](https://static.pepy.tech/badge/genai-otel-instrument/month)](https://pepy.tech/project/genai-otel-instrument)
+
+[![GitHub Stars](https://img.shields.io/github/stars/Mandark-droid/genai_otel_instrument?style=social)](https://github.com/Mandark-droid/genai_otel_instrument)
+[![GitHub Forks](https://img.shields.io/github/forks/Mandark-droid/genai_otel_instrument?style=social)](https://github.com/Mandark-droid/genai_otel_instrument)
+[![GitHub Issues](https://img.shields.io/github/issues/Mandark-droid/genai_otel_instrument)](https://github.com/Mandark-droid/genai_otel_instrument/issues)
+[![GitHub Pull Requests](https://img.shields.io/github/issues-pr/Mandark-droid/genai_otel_instrument)](https://github.com/Mandark-droid/genai_otel_instrument/pulls)
+
+[![Code Coverage](https://img.shields.io/badge/coverage-95%25-brightgreen.svg)](https://github.com/Mandark-droid/genai_otel_instrument)
+[![Code Style: Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![Type Checked: mypy](https://img.shields.io/badge/type%20checked-mypy-blue.svg)](http://mypy-lang.org/)
+
+[![OpenTelemetry](https://img.shields.io/badge/OpenTelemetry-1.20%2B-blueviolet)](https://opentelemetry.io/)
+[![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)
+
 Production-ready OpenTelemetry instrumentation for GenAI/LLM applications with zero-code setup.
 
 ## Features
@@ -188,7 +208,7 @@ Production-ready OpenTelemetry instrumentation for GenAI/LLM applications with z
 🤖 **15+ LLM Providers** - OpenAI, Anthropic, Google, AWS, Azure, and more
 🔧 **MCP Tool Support** - Auto-instrument databases, APIs, caches, vector DBs
 💰 **Cost Tracking** - Automatic cost calculation per request
-🎮 **GPU Metrics** - Real-time GPU utilization, memory, temperature
+🎮 **GPU Metrics** - Real-time GPU utilization, memory, temperature, power
 📊 **Complete Observability** - Traces, metrics, and rich span attributes
 ➕ **Service Instance ID & Environment** - Identify your services and environments
 ⏱️ **Configurable Exporter Timeout** - Set timeout for OTLP exporter
@@ -268,7 +288,7 @@ Every LLM call, database query, API request, and vector search is traced with fu
 ### Metrics
 
 **GenAI Metrics:**
-- `gen_ai.requests` - Request counts by provider/model
+- `gen_ai.requests` - Request counts by provider and model
 - `gen_ai.client.token.usage` - Token usage (prompt/completion)
 - `gen_ai.client.operation.duration` - Request latency histogram (optimized buckets for LLM workloads)
 - `gen_ai.usage.cost` - Total estimated costs in USD
@@ -278,7 +298,7 @@ Every LLM call, database query, API request, and vector search is traced with fu
 - `gen_ai.usage.cost.cache_read` - Cache read cost (Anthropic)
 - `gen_ai.usage.cost.cache_write` - Cache write cost (Anthropic)
 - `gen_ai.client.errors` - Error counts by operation and type
-- `gen_ai.gpu.*` - GPU utilization, memory, temperature (ObservableGauges)
+- `gen_ai.gpu.*` - GPU utilization, memory, temperature, power (ObservableGauges)
 - `gen_ai.co2.emissions` - CO2 emissions tracking (opt-in)
 - `gen_ai.server.ttft` - Time to First Token for streaming responses (histogram, 1ms-10s buckets)
 - `gen_ai.server.tbt` - Time Between Tokens for streaming responses (histogram, 10ms-2.5s buckets)
@@ -459,5 +479,168 @@ genai-otel-instrument/
         └── (other mcp files)
 ```
 
+## Roadmap
+
+### Next Release (v0.2.0) - Q1 2026
+
+We're planning significant enhancements for the next major release, focusing on evaluation metrics and safety guardrails alongside completing OpenTelemetry semantic convention compliance.
+
+#### 🎯 Evaluation & Monitoring
+
+**LLM Output Quality Metrics**
+- **Bias Detection** - Automatically detect and measure bias in LLM responses
+  - Gender, racial, political, and cultural bias detection
+  - Bias score metrics with configurable thresholds
+  - Integration with fairness libraries (e.g., Fairlearn, AIF360)
+
+- **Toxicity Detection** - Monitor and alert on toxic or harmful content
+  - Perspective API integration for toxicity scoring
+  - Custom toxicity models support
+  - Real-time toxicity metrics and alerts
+  - Configurable severity levels
+
+- **Hallucination Detection** - Track factual accuracy and groundedness
+  - Fact-checking against provided context
+  - Citation validation for RAG applications
+  - Confidence scoring for generated claims
+  - Hallucination rate metrics by model and use case
+
+**Implementation:**
+```python
+import genai_otel
+
+# Enable evaluation metrics
+genai_otel.instrument(
+    enable_bias_detection=True,
+    enable_toxicity_detection=True,
+    enable_hallucination_detection=True,
+
+    # Configure thresholds
+    bias_threshold=0.7,
+    toxicity_threshold=0.5,
+    hallucination_threshold=0.8
+)
+```
+
+**Metrics Added:**
+- `gen_ai.eval.bias_score` - Bias detection scores (histogram)
+- `gen_ai.eval.toxicity_score` - Toxicity scores (histogram)
+- `gen_ai.eval.hallucination_score` - Hallucination probability (histogram)
+- `gen_ai.eval.violations` - Count of threshold violations by type
+
+#### 🛡️ Safety Guardrails
+
+**Input/Output Filtering**
+- **Prompt Injection Detection** - Protect against prompt injection attacks
+  - Pattern-based detection (jailbreaking attempts)
+  - ML-based classifier for sophisticated attacks
+  - Real-time blocking with configurable policies
+  - Attack attempt metrics and logging
+
+- **Restricted Topics** - Block sensitive or inappropriate topics
+  - Configurable topic blacklists (legal, medical, financial advice)
+  - Industry-specific content filters
+  - Topic detection with confidence scoring
+  - Custom topic definition support
+
+- **Sensitive Information Protection** - Prevent PII leakage
+  - PII detection (emails, phone numbers, SSN, credit cards)
+  - Automatic redaction or blocking
+  - Compliance mode (GDPR, HIPAA, PCI-DSS)
+  - Data leak prevention metrics
+
+**Implementation:**
+```python
+import genai_otel
+
+# Configure guardrails
+genai_otel.instrument(
+    enable_prompt_injection_detection=True,
+    enable_restricted_topics=True,
+    enable_sensitive_info_detection=True,
+
+    # Custom configuration
+    restricted_topics=["medical_advice", "legal_advice", "financial_advice"],
+    pii_detection_mode="block",  # or "redact", "warn"
+
+    # Callbacks for custom handling
+    on_guardrail_violation=my_violation_handler
+)
+```
+
+**Metrics Added:**
+- `gen_ai.guardrail.prompt_injection_detected` - Injection attempts blocked
+- `gen_ai.guardrail.restricted_topic_blocked` - Restricted topic violations
+- `gen_ai.guardrail.pii_detected` - PII detection events
+- `gen_ai.guardrail.violations` - Total guardrail violations by type
+
+**Span Attributes:**
+- `gen_ai.guardrail.violation_type` - Type of violation detected
+- `gen_ai.guardrail.violation_severity` - Severity level (low, medium, high, critical)
+- `gen_ai.guardrail.blocked` - Whether request was blocked (boolean)
+- `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**
+- ✅ Session & User Tracking - Track sessions and users across requests
+  ```python
+  genai_otel.instrument(
+      session_id_extractor=lambda ctx: ctx.get("session_id"),
+      user_id_extractor=lambda ctx: ctx.get("user_id")
+  )
+  ```
+
+- ✅ RAG/Embedding Attributes - Enhanced observability for retrieval-augmented generation
+  - `embedding.model_name` - Embedding model used
+  - `embedding.vector_dimensions` - Vector dimensions
+  - `retrieval.documents.{i}.document.id` - Retrieved document IDs
+  - `retrieval.documents.{i}.document.score` - Relevance scores
+  - `retrieval.documents.{i}.document.content` - Document content (truncated)
+
+- ✅ Agent Workflow Tracking - Better support for agentic workflows
+  - `agent.name` - Agent identifier
+  - `agent.iteration` - Current iteration number
+  - `agent.action` - Action taken
+  - `agent.observation` - Observation received
+
+#### 🔄 Migration Support
+
+**Backward Compatibility:**
+- All new features are opt-in via configuration
+- Existing instrumentation continues to work unchanged
+- Gradual migration path for new semantic conventions
+
+**Version Support:**
+- Python 3.9+ (evaluation features require 3.10+)
+- OpenTelemetry SDK 1.20.0+
+- Backward compatible with existing dashboards
+
+### Future Releases
+
+**v0.3.0 - Advanced Analytics**
+- Custom metric aggregations
+- Cost optimization recommendations
+- Automated performance regression detection
+- A/B testing support for prompts
+
+**v0.4.0 - Enterprise Features**
+- Multi-tenancy support
+- Role-based access control for telemetry
+- Advanced compliance reporting
+- SLA monitoring and alerting
+
+**Community Feedback**
+
+We welcome feedback on our roadmap! Please:
+- Open issues for feature requests
+- Join discussions on prioritization
+- Share your use cases and requirements
+
+See [Contributing.md](Contributing.md) for how to get involved.
+
 ## License
 Apache-2.0 license

{genai_otel_instrument-0.1.1.dev0.dist-info → genai_otel_instrument-0.1.2.dev0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 genai_otel/__init__.py,sha256=OWgm1dihRkwBQU8fUPnVhE5XCZeF5f15UyH4w6LqGZU,4469
-genai_otel/__version__.py,sha256=zZ8gTCIyqP1ayOMOGPrtjRAYol1rcsahyb0_47c1grk,751
+genai_otel/__version__.py,sha256=eqjW0HD_fPOqOyADJFBWSMmbfbnb7cqTc_62GX2lDJU,751
 genai_otel/auto_instrument.py,sha256=bLOR_9y2gSB4VfwRrYI7YX_et-NwrpIzbOnmkNqbDHE,15343
 genai_otel/cli.py,sha256=mbhaTU0WIAkvPKdIing-guIxPDjEKQftChWQUtPFzkY,3170
 genai_otel/config.py,sha256=GSJZApBNKKXm5rp5jQsDk91qcHYzCrhmf06DHbpZMBE,6685
 genai_otel/cost_calculator.py,sha256=Jlp-UPO8vcfWy5u46ib1I_6w0bvVrMsz1kWi1Vn6QX4,10588
 genai_otel/exceptions.py,sha256=gIRvbI7c4V-M-PG9jS0o4ESRwHUWCm6DVihjfyJI1yg,429
-genai_otel/gpu_metrics.py,sha256=MLQTyeGwd8Zxwev_iUddl91lfj2me6CPMOjGRnxM2Cs,9754
+genai_otel/gpu_metrics.py,sha256=gHqV17mJ59VscilR_Bcd1ccBDdDiUs5w0bE1hNk7NqI,11168
 genai_otel/llm_pricing.json,sha256=fFajtjXvcNfuz_JOblz4BXpiliZvtL1Fybpa9hJv-v4,17733
 genai_otel/logging_config.py,sha256=XSBeslTqeHUBBadKJV2W8JFIOXorEVZ6W0xqNKjiPlA,1463
 genai_otel/metrics.py,sha256=Vngwtc1MAMAE7JVpbT_KfiCQ5TdIAKIs_0oztjJdDTg,2671
@@ -36,9 +36,9 @@ 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-0.1.1.dev0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-genai_otel_instrument-0.1.1.dev0.dist-info/METADATA,sha256=NMd0W0AbdmVc5seUf_trkhlFimd5UVq_F1XxeNd7YBk,19215
-genai_otel_instrument-0.1.1.dev0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-genai_otel_instrument-0.1.1.dev0.dist-info/entry_points.txt,sha256=E9UqoHA_fq69yNGAY3SRYf5HH94sZT5DiDueiU1v0KM,57
-genai_otel_instrument-0.1.1.dev0.dist-info/top_level.txt,sha256=cvCm8PUwvYUSQKruk-x6S-_YuDyhOBk8gD910XICcbg,11
-genai_otel_instrument-0.1.1.dev0.dist-info/RECORD,,
+genai_otel_instrument-0.1.2.dev0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+genai_otel_instrument-0.1.2.dev0.dist-info/METADATA,sha256=xx-j-EJnh9GTQe-LUtTanUregUyEQrBY3ZgY2SCGWZg,27296
+genai_otel_instrument-0.1.2.dev0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+genai_otel_instrument-0.1.2.dev0.dist-info/entry_points.txt,sha256=E9UqoHA_fq69yNGAY3SRYf5HH94sZT5DiDueiU1v0KM,57
+genai_otel_instrument-0.1.2.dev0.dist-info/top_level.txt,sha256=cvCm8PUwvYUSQKruk-x6S-_YuDyhOBk8gD910XICcbg,11
+genai_otel_instrument-0.1.2.dev0.dist-info/RECORD,,