Integrate with Google AI

Note

Problem-solving guide for Google AI integration

This guide helps you solve specific problems when integrating HoneyHive with Google AI, with support for multiple instrumentor options.

This guide covers Google AI integration with HoneyHive’s BYOI architecture, supporting both OpenInference and Traceloop instrumentors.

Compatibility

Problem: I need to know if my Python version and Google AI SDK version are compatible with HoneyHive.

Solution: Check the compatibility information below before installation.

Python Version Support

Support Level	Python Versions
Fully Supported	3.11, 3.12, 3.13
Not Supported	3.10 and below

Provider SDK Requirements

Minimum: google-generativeai >= 0.3.0
Recommended: google-generativeai >= 0.4.0
Tested Versions: 0.4.0, 0.5.0, 0.6.0

Instrumentor Compatibility

Instrumentor	Status	Notes
OpenInference	Fully Supported	Gemini Pro and Pro Vision support with multimodal tracing
Traceloop	Experimental	Basic support available, some Gemini-specific features in development

Known Limitations

Streaming: Supported with manual span management required
Multimodal Input: Vision features traced but media content not captured
Function Calling: Supported in Gemini Pro models
Safety Settings: Not captured in traces by default

Note

For the complete compatibility matrix across all providers, see Multi-Provider Integration.

Choose Your Instrumentor

Problem: I need to choose between OpenInference and Traceloop for Google AI integration.

Solution: Choose the instrumentor that best fits your needs:

OpenInference: Open-source, lightweight, great for getting started
Traceloop: Enhanced LLM metrics, cost tracking, production optimizations

Best for: Open-source projects, simple tracing needs, getting started quickly

# Recommended: Install with Google AI integration
pip install honeyhive[openinference-google-ai]

# Alternative: Manual installation
pip install honeyhive openinference-instrumentation-google-generativeai google-generativeai>=0.3.0

from honeyhive import HoneyHiveTracer
from openinference.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
import google.generativeai
import os

# Environment variables (recommended for production)
# .env file:
# HH_API_KEY=your-honeyhive-key
# GOOGLE_API_KEY=your-google-ai-key

# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)  # Uses HH_API_KEY from environment

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

# Basic usage with error handling
try:
    import google.generativeai as genai
    genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
    model = genai.GenerativeModel('gemini-pro')
    response = model.generate_content("Hello!")
    print(response.text)
    # Automatically traced! ✨
except google.generativeai.types.GoogleGenerativeAIError as e:
    print(f"Google AI API error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")

from honeyhive import HoneyHiveTracer, trace, enrich_span
from honeyhive.models import EventType
from openinference.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
import google.generativeai

# Initialize with custom configuration
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    api_key="your-honeyhive-key",  # Or set HH_API_KEY environment variable
    project="your-project",        # Or set HH_PROJECT environment variable
    source="production"            # Or set HH_SOURCE environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

@trace(tracer=tracer, event_type=EventType.chain)
def generate_content_comparison(prompt: str) -> dict:
    """Advanced example with business context and multiple Google AI calls."""
    {{ADVANCED_USAGE_EXAMPLE}}

    # Add business context to the trace
    enrich_span({
        "business.input_type": type(prompt).__name__,
        "business.use_case": "content_generation",
        "google-ai.strategy": "multi_model_gemini",
        "instrumentor.type": "openinference"
    })

    try:
        {{ADVANCED_IMPLEMENTATION}}

        # Add result metadata
        enrich_span({
            "business.successful": True,
            "google-ai.models_used": ["gemini-pro", "gemini-pro-vision"],
            "business.result_confidence": "high"
        })

        return {{RETURN_VALUE}}

    except google.generativeai.types.GoogleGenerativeAIError as e:
        enrich_span({
            "error.type": "api_error",
            "error.message": str(e),
            "instrumentor.source": "openinference"
        })
        raise

Common OpenInference Issues:

Missing Traces

# Use correct initialization pattern
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

Performance for High Volume

# OpenInference uses efficient span processors automatically
# No additional configuration needed

Multiple Instrumentors

# You can combine OpenInference with other instrumentors
{{MULTIPLE_INSTRUMENTORS_EXAMPLE}}

Environment Configuration

# HoneyHive configuration
export HH_API_KEY="your-honeyhive-api-key"
export HH_SOURCE="production"

# Google AI configuration
export GOOGLE_API_KEY="your-google-ai-api-key"

Best for: Production deployments, cost tracking, enhanced LLM observability

# Recommended: Install with Traceloop Google AI integration
pip install honeyhive[traceloop-google-ai]

# Alternative: Manual installation
pip install honeyhive opentelemetry-instrumentation-google-generativeai google-generativeai>=0.3.0

from honeyhive import HoneyHiveTracer
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
import google.generativeai
import os

# Environment variables (recommended for production)
# .env file:
# HH_API_KEY=your-honeyhive-key
# GOOGLE_API_KEY=your-google-ai-key

# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)  # Uses HH_API_KEY from environment

# Step 2: Initialize Traceloop instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

# Basic usage with automatic tracing
try:
    import google.generativeai as genai
    genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
    model = genai.GenerativeModel('gemini-pro')
    response = model.generate_content("Hello!")
    print(response.text)
    # Automatically traced by Traceloop with enhanced metrics! ✨
except google.generativeai.types.GoogleGenerativeAIError as e:
    print(f"Google AI API error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")

from honeyhive import HoneyHiveTracer, trace, enrich_span
from honeyhive.models import EventType
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
import google.generativeai

# Initialize HoneyHive with Traceloop instrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    api_key="your-honeyhive-key",  # Or set HH_API_KEY environment variable
    project="your-project",        # Or set HH_PROJECT environment variable
    source="production"            # Or set HH_SOURCE environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

@trace(tracer=tracer, event_type=EventType.chain)
def generate_content_comparison(prompt: str) -> dict:
    """Advanced example with business context and enhanced LLM metrics."""
    {{ADVANCED_USAGE_EXAMPLE}}

    # Add business context to the trace
    enrich_span({
        "business.input_type": type(prompt).__name__,
        "business.use_case": "content_generation",
        "google-ai.strategy": "cost_optimized_multi_model_gemini",
        "instrumentor.type": "openllmetry",
        "observability.enhanced": True
    })

    try:
        {{ADVANCED_IMPLEMENTATION}}

        # Add result metadata
        enrich_span({
            "business.successful": True,
            "google-ai.models_used": ["gemini-pro", "gemini-pro-vision"],
            "business.result_confidence": "high",
            "openllmetry.cost_tracking": "enabled",
            "openllmetry.token_metrics": "captured"
        })

        return {{RETURN_VALUE}}

    except google.generativeai.types.GoogleGenerativeAIError as e:
        enrich_span({
            "error.type": "api_error",
            "error.message": str(e),
            "instrumentor.error_handling": "openllmetry"
        })
        raise

Common Traceloop Issues:

Missing Traces

# Ensure Traceloop instrumentor is passed to tracer
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor

# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

Enhanced Metrics Not Showing

# Ensure you're using the latest version
# pip install --upgrade opentelemetry-instrumentation-google-generativeai

# The instrumentor automatically captures enhanced metrics
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

Multiple Traceloop Instrumentors

# You can combine multiple Traceloop instrumentors
{{MULTIPLE_TRACELOOP_INSTRUMENTORS_EXAMPLE}}

Performance Optimization

# Traceloop instrumentors handle batching automatically
# No additional configuration needed for performance

Environment Configuration

# HoneyHive configuration
export HH_API_KEY="your-honeyhive-api-key"
export HH_SOURCE="production"

# Google AI configuration
export GOOGLE_API_KEY="your-google-ai-api-key"

# Optional: Traceloop cloud features
export TRACELOOP_API_KEY="your-traceloop-key"
export TRACELOOP_BASE_URL="https://api.traceloop.com"

Comparison: OpenInference vs Traceloop for Google AI

Feature Comparison
Feature	OpenInference	Traceloop
Setup Complexity	Simple, single instrumentor	Single instrumentor setup
Token Tracking	Basic span attributes	Detailed token metrics + costs
Model Metrics	Model name, basic timing	Cost per model, latency analysis
Performance	Lightweight, fast	Optimized with smart batching
Cost Analysis	Manual calculation needed	Automatic cost per request
Production Ready	✅ Yes	✅ Yes, with cost insights
Debugging	Standard OpenTelemetry	Enhanced LLM-specific debug
Best For	Simple integrations, dev	Production, cost optimization

Migration Between Instrumentors

From OpenInference to Traceloop:

# Before (OpenInference)
from openinference.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

# After (Traceloop) - different instrumentor package
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

From Traceloop to OpenInference:

# Before (Traceloop)
from opentelemetry.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)

# After (OpenInference)
from openinference.instrumentation.google_generativeai import GoogleGenerativeAIInstrumentor
# Step 1: Initialize HoneyHive tracer first (without instrumentors)
tracer = HoneyHiveTracer.init(
    project="your-project"  # Or set HH_PROJECT environment variable
)

# Step 2: Initialize instrumentor separately with tracer_provider
instrumentor = GoogleGenerativeAIInstrumentor()
instrumentor.instrument(tracer_provider=tracer.provider)