Introduction
Quickstart
Get started with tracing sessions with HoneyHive
With HoneyHive, we allow users to track:
- Model inference calls as
model
events - External API calls (like retrieval) as
tool
events - Groups of inference & external API calls as
chains
events - An entire trace of requests as a
session
Logging a Trace
We use OpenTelemetry to automatically instrument your AI application.
Prerequisites
- You have already created a project in HoneyHive, as explained here.
- You have an API key for your project, as explained here.
Expected Time: 5 minutes
Steps
1
Installation
To install our SDKs, run the following commands in the shell.
2
Authenticate the SDK & initialize the tracer
To initialize the tracer, we require 3 key details:
- Your HoneyHive API Key
- Name of the project to log the trace to
- Name for this session - like “Chatbot Session” or “Customer RAG Session”.
View the trace
Now that you have successfully traced your session, you can review it in the platform.
- Navigate to the project in the platform via the projects page or the dropdown in the Header.
- Follow these steps after
Auto-instrumentation
Note that we do not currently support Colab or Jupyter notebook environments for our OTEL Python tracer or ES Modules for our OTEL TypeScript tracer. However, there are no such limitations for our LangChain and LlamaIndex callback methods.
We use OpenTelemetry along with a set of custom extensions that automatically instrument your LLM API and vector database requests in Python and Typescript.
Here’s our list of supported providers for auto-instrumentation:
LLM Providers | Vector DBs |
---|---|
OpenAI / Azure OpenAI | Chroma |
Anthropic | Pinecone |
Cohere | Qdrant |
Ollama | Weaviate |
Mistral AI | Milvus |
HuggingFace | |
Bedrock (AWS) | |
Replicate | |
Vertex AI (GCP) | |
IBM Watsonx AI | |
Together AI |