BeeAI | Opik Documentation

BeeAI is an agent framework designed to simplify the development of AI agents with a focus on simplicity and performance. It provides a clean API for building agents with built-in support for tool usage, conversation management, and extensible architecture.

BeeAI’s primary advantage is its lightweight design that makes it easy to create and deploy AI agents without unnecessary complexity, while maintaining powerful capabilities for production use.

Getting started

To use the BeeAI integration with Opik, you will need to have BeeAI and the required OpenTelemetry packages installed:

$ pip install beeai-framework openinference-instrumentation-beeai "beeai-framework[wikipedia]" opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp

Environment configuration

Configure your environment variables based on your Opik deployment:

Opik Cloud

Enterprise deployment

Self-hosted instance

If you are using Opik Cloud, you will need to set the following environment variables:

$ export OTEL_EXPORTER_OTLP_ENDPOINT=https://www.comet.com/opik/api/v1/private/otel
> export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default'

To log the traces to a specific project, you can add the projectName parameter to the OTEL_EXPORTER_OTLP_HEADERS environment variable:

$ export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default,projectName=<your-project-name>'

You can also update the Comet-Workspace parameter to a different value if you would like to log the data to a different workspace.

Using Opik with BeeAI

Set up OpenTelemetry instrumentation for BeeAI:

1 from opentelemetry import trace
2 from opentelemetry.sdk.trace import TracerProvider
3 from opentelemetry.sdk.trace.export import BatchSpanProcessor
4 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
5 from openinference.instrumentation.beeai import (
6     BeeAIInstrumentor,
7 )  # or SemanticKernelInstrumentor
8 
9 # Configure the OTLP exporter for Opik
10 otlp_exporter = OTLPSpanExporter()
11 
12 
13 # Set up the tracer provider
14 trace.set_tracer_provider(TracerProvider())
15 
16 trace.get_tracer_provider().add_span_processor(
17     BatchSpanProcessor(otlp_exporter)  # OTLP for sending to Opik
18 )
19 
20 # Instrument your framework
21 BeeAIInstrumentor().instrument()  # or SemanticKernelInstrumentor().instrument()
22 
23 import asyncio
24 from beeai_framework.agents.react import ReActAgent
25 from beeai_framework.agents.types import AgentExecutionConfig
26 from beeai_framework.backend.chat import ChatModel
27 from beeai_framework.backend.types import ChatModelParameters
28 from beeai_framework.memory import TokenMemory
29 from beeai_framework.tools.search.wikipedia import WikipediaTool
30 from beeai_framework.tools.weather.openmeteo import OpenMeteoTool
31 
32 # Initialize the language model
33 llm = ChatModel.from_name(
34     "openai:gpt-4o-mini",  # or "ollama:granite3.3:8b" for local Ollama
35     ChatModelParameters(temperature=0.7),
36 )
37 
38 # Create tools for the agent
39 tools = [
40     WikipediaTool(),
41     OpenMeteoTool(),
42 ]
43 
44 # Create a ReAct agent with memory
45 agent = ReActAgent(llm=llm, tools=tools, memory=TokenMemory(llm))
46 
47 
48 # Run the agent
49 async def main():
50     response = await agent.run(
51         prompt="I'm planning a trip to Barcelona, Spain. Can you research key attractions and landmarks I should visit, and also tell me what the current weather conditions are like there?",
52         execution=AgentExecutionConfig(
53             max_retries_per_step=3, total_max_retries=10, max_iterations=5
54         ),
55     )
56     print("Agent Response:", response.result.text)
57     return response
58 
59 
60 # Run the example
61 if __name__ == "__main__":
62     asyncio.run(main())

Further improvements

If you have any questions or suggestions for improving the BeeAI integration, please open an issue on our GitHub repository.