​
Initializing HoneyHive Tracer

Use the following code to initialize HoneyHive tracing in your project:

For Python projects, use the HoneyHiveTracer class to initialize tracing:

from honeyhive import HoneyHiveTracer
import os

HoneyHiveTracer.init(api_key=os.environ["HH_API_KEY"], project=os.environ["HH_PROJECT"])

This initializes auto-tracing for your entire Python application.

If you’re using these code examples verbatim, then make sure to set the appropriate environment variables (HH_API_KEY and HH_PROJECT) before running your application.

​
Supported LlamaIndex Versions/Interfaces

Compatible with LlamaIndex versions ^0.10.0 and above.

For the most up-to-date compatibility information, please refer to the HoneyHive documentation.

​
Nesting

Nesting is handled automatically by the HoneyHive tracing system. When you use traced components within other traced components, the system will create a hierarchical structure of spans, reflecting the nested nature of your LlamaIndex operations.

​
Enriching Properties

For information on how to enrich your traces and spans with additional context, see our enrichment documentation.

​
Adding Evaluators

Once traces have been logged in the HoneyHive platform, you can then run evaluations with either Python or TypeScript.

​
Cookbook Examples

​
Python Example

import os
from llama_index.core import (
    GPTVectorStoreIndex,
    SimpleDirectoryReader,
    Settings
)
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.core.query_engine import RetrieverQueryEngine
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from honeyhive import HoneyHiveTracer

# Initialize HoneyHiveTracer
HoneyHiveTracer.init(api_key=os.environ["HH_API_KEY"], project=os.environ["HH_PROJECT"])

# Load the document
documents = SimpleDirectoryReader(input_files=['state_of_the_union.txt']).load_data()

# Initialize the OpenAI LLM using LlamaIndex's OpenAI wrapper
llm = OpenAI(temperature=0)

# Create the embedding model
embedding_model = OpenAIEmbedding()

# Add the LLM predictor and embedding model to the Settings object
Settings.llm = llm
Settings.embed_model = embedding_model

# Create a vector index from the documents
index = GPTVectorStoreIndex.from_documents(
    documents,
)

# Ask a question
query = "What did the president say about Ketanji Brown Jackson?"
retriever = VectorIndexRetriever(index=index)
query_engine = RetrieverQueryEngine.from_args(retriever)
response = query_engine.query(query)

print(response)

These examples demonstrate how to integrate HoneyHive tracing with LlamaIndex in Python environments, covering document loading, text splitting, embedding creation, vector store operations, and question-answering chains.

LangChainVercel AI SDK