Observability for Chroma with Honeycomb

OpenLLMetry lets you trace queries and indexing of documents in Chroma. With 5 minutes of work you can get complete view of your system directly into Honeycomb. See how below.

Step 1

Install the Traceloop SDK and initialize it. It will automatically log all calls to Chroma using its SDK - both query calls and index calls.

import chromadb
from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import workflow

Traceloop.init()

chroma_client = chromadb.Client()
collection = chroma_client.create_collection(
    name="my_collection", embedding_function=embedding_function
)

claim_query_result = collection.query(
  query_texts=query, include=["documents", "distances"], n_results=3
 )

TYPESCRIPT

TRACELOOP_BASE_URL=https://api.honeycomb.io
TRACELOOP_HEADERS="x-honeycomb-team=<YOUR_API_KEY>"

Step 2

Route the traces to Honeycomb’s endpoint and set the API key

TRACELOOP_BASE_URL=https://api.honeycomb.io
TRACELOOP_HEADERS="x-honeycomb-team=<YOUR_API_KEY>"

Docs

Discover use cases

Trace Indexing pipelines with Chroma

Build an indexing pipeline and save documents to Chroma. See how your documents are indexed and detect errors.

See Code Example

Trace your RAG retrieval pipeline

Build a RAG pipeline with Chroma and OpenAI. See vectors returned from Chroma, full prompt in OpenAI and responses

See Code Example

Observability for Chroma with Honeycomb

Step 1

Step 2

Discover use cases

Trace Indexing pipelines with Chroma

Trace your RAG retrieval pipeline

More things you can connect to {platform}

Cohere

OpenAI

Bedrock

Watsonx

Anthropic

LangChain

LlamaIndex