Observability for LlamaIndex with Dynatrace

Step 1

Install and initialize the SDK in your code. It will automatically detect the workflow structure in build traces.

import asyncio

import chromadb
import os

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from traceloop.sdk import Traceloop

os.environ["TOKENIZERS_PARALLELISM"] = "false"

Traceloop.init(app_name="llama_index_example")

chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# define embedding function
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5")

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# set up ChromaVectorStore and load in data
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)


async def main():
    # Query Data
    query_engine = index.as_query_engine()
    response = await query_engine.aquery("What did the author do growing up?")

    print(response)


if __name__ == "__main__":
    asyncio.run(main())

import * as traceloop from "@traceloop/node-server-sdk";
import {
  OpenAIEmbedding,
  SimpleDirectoryReader,
  SimpleVectorStore,
  VectorStoreIndex,
  serviceContextFromDefaults,
  storageContextFromDefaults,
} from "llamaindex";

traceloop.initialize({
  appName: "sample_llamaindex",
  apiKey: process.env.TRACELOOP_API_KEY,
  disableBatch: true,
});


const documents = await new SimpleDirectoryReader().loadData({
  // Download from:
  // https://github.com/traceloop/openllmetry-js/tree/main/packages/sample-app/data/paul_graham
  directoryPath: "data/paul_graham", 
});

const serviceContext = serviceContextFromDefaults({ embedModel });
const storageContext = await storageContextFromDefaults({ vectorStore });

const index = await VectorStoreIndex.fromDocuments(documents, {
  storageContext,
  serviceContext,
});

const queryEngine = index.asQueryEngine();

const res = await queryEngine.query("What did the author do growing up?");
console.log(res)

Step 2

Go to your Dynatrace environment and create a new access token under Manage Access Tokens. The access token needs the following permission scopes that allow the ingest of OpenTelemetry spans, metrics and logs (openTelemetryTrace.ingest, metrics.ingest, logs.ingest). Set the following environment variables.

TRACELOOP_BASE_URL=https://<YOUR_ENV>.live.dynatrace.com\api\v2\otlp
TRACELOOP_HEADERS=Authorization=Api-Token%20<YOUR_ACCESS_TOKEN>

Docs

Observability for LlamaIndex with Dynatrace

Step 1

Step 2

Discover use cases

Trace a LlamaIndex-based RAG pipeline

Trace a LlamaIndex-based Agent

More things you can connect to {platform}

Anthropic

Watsonx

Ollama

Bedrock

Gemini

Mistral AI

OpenAI

together.ai

Cohere

LangChain

Chroma