Tracing Haystack

Haystack is an open-source AI orchestration framework developed by deepset, designed to help Python developers build production-ready LLM-powered applications. It features a modular architecture - built around components and pipelines for building everything from retrieval-augmented generation (RAG) workflows to autonomous agentic systems and scalable search engines.

MLflow Tracing provides automatic tracing capability when using Haystack pipelines and components. When Haystack auto-tracing is enabled by calling the mlflow.haystack.autolog() function, usage of Haystack pipelines and components will automatically record generated traces during interactive development.

import mlflow

mlflow.haystack.autolog()

MLflow trace automatically captures the following information

• Pipelines and Components
• 延迟
• Metadata about the different components added, such as tool names
• Token 使用量和成本
• 缓存命中
• 如果抛出任何异常

基本示例

import mlflow

from haystack import Document, Pipeline
from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.dataclasses import ChatMessage
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.utils import Secret

mlflow.haystack.autolog()
mlflow.set_experiment("Haystack Tracing")

# Write documents to InMemoryDocumentStore
document_store = InMemoryDocumentStore()
document_store.write_documents(
    [
        Document(content="My name is Jean and I live in Paris."),
        Document(content="My name is Mark and I live in Berlin."),
        Document(content="My name is Giorgio and I live in Rome."),
    ]
)

# Build a RAG pipeline
prompt_template = [
    ChatMessage.from_system("You are a helpful assistant."),
    ChatMessage.from_user(
        "Given these documents, answer the question.\n"
        "Documents:\n{% for doc in documents %}{{ doc.content }}{% endfor %}\n"
        "Question: {{question}}\n"
        "Answer:"
    ),
]

# Define required variables explicitly
prompt_builder = ChatPromptBuilder(
    template=prompt_template, required_variables={"question", "documents"}
)

retriever = InMemoryBM25Retriever(document_store=document_store)
llm = OpenAIChatGenerator(api_key=Secret.from_env_var("OPENAI_API_KEY"))

rag_pipeline = Pipeline()
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", prompt_builder)
rag_pipeline.add_component("llm", llm)
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm.messages")

# Ask a question
question = "Who lives in Paris?"
results = rag_pipeline.run(
    {
        "retriever": {"query": question},
        "prompt_builder": {"question": question},
    }
)

print(results["llm"]["replies"])

Token 用量

MLflow >= 3.4.0 supports token usage tracking for Haystack. The token usage for each LLM call will be logged in the mlflow.chat.tokenUsage attribute. The total token usage throughout the trace will be available in the token_usage field of the trace info object.

question = "Who lives in Paris?"
results = rag_pipeline.run(
    {
        "retriever": {"query": question},
        "prompt_builder": {"question": question},
    }
)

print(results["llm"]["replies"])

last_trace_id = mlflow.get_last_active_trace_id()
trace = mlflow.get_trace(trace_id=last_trace_id)

# Print the token usage
total_usage = trace.info.token_usage
print("== Total token usage: ==")
print(f"  Input tokens: {total_usage['input_tokens']}")
print(f"  Output tokens: {total_usage['output_tokens']}")
print(f"  Total tokens: {total_usage['total_tokens']}")

# Print the token usage for each LLM call
print("\n== Detailed usage for each LLM call: ==")
for span in trace.data.spans:
    if usage := span.get_attribute("mlflow.chat.tokenUsage"):
        print(f"{span.name}:")
        print(f"  Input tokens: {usage['input_tokens']}")
        print(f"  Output tokens: {usage['output_tokens']}")
        print(f"  Total tokens: {usage['total_tokens']}")

== Total token usage: ==
  Input tokens: 64
  Output tokens: 5
  Total tokens: 69

== Detailed usage for each LLM call: ==
OpenAIChatGenerator:
  Input tokens: 64
  Output tokens: 5

禁用自动跟踪

Auto tracing for Haystack can be disabled globally by calling mlflow.haystack.autolog(disable=True) or mlflow.autolog(disable=True).