Haystack 3.4.1: our test log

Haystack 3.4.1 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 2.3 s.

Result at a glance

What we found

• 3 of 3 task trials passed: the model's tool call reached the framework, the function ran with 17 and 25, and the final answer contained 42.
• Cold install took 2.3 s with uv and 8.4 s with pip, and left 111 MB in 43 packages (uv).
• Used the Agent component with OpenAIChatGenerator and a Tool object; retrieval pipelines, the project's main use, were not exercised.

What we ran, step by step

# Install with uv (cold, no cache)
uv venv -q -p 3.13 work/py/haystack && VIRTUAL_ENV=work/py/haystack uv pip install --no-cache -q haystack-ai

# Install with pip (cold, no cache)
uv venv -q --seed -p 3.13 work/pip/haystack && work/pip/haystack/bin/pip install --no-cache-dir -q haystack-ai

# Task command (all trials)
OTEL_SDK_DISABLED=true work/py/haystack/bin/python tasks/haystack_agent.py

Raw output (excerpts)

from common import *
from haystack.components.agents import Agent
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack.tools import Tool
from haystack.utils import Secret
tool = Tool(name="add_numbers", description="Add two integers and return the sum.", parameters={"type":"object","properties":{"a":{"type":"integer"},"b":{"type":"integer"}},"required":["a","b"]}, function=add_numbers)
agent = Agent(chat_generator=OpenAIChatGenerator(model=MODEL, api_base_url=BASE, api_key=Secret.from_token(KEY), generation_kwargs={"temperature":0}), tools=[tool])
r = agent.run(messages=[ChatMessage.from_user(TASK)])
report(r["messages"][-1].text)

import json, os
BASE = "http://127.0.0.1:11434/v1"
MODEL = os.environ.get("MODEL", "qwen2.5-3b")
KEY = "ollama"
TASK = "Use the add_numbers tool to compute 17 + 25, then tell me the result."
CALLS = []
def add_numbers(a: int, b: int) -> int:
    """Add two integers and return the sum."""
    CALLS.append((a, b))
    return int(a) + int(b)
def report(final):
    ok = any({int(x), int(y)} == {17, 25} for x, y in CALLS) and "42" in str(final)
    print("RESULT_JSON " + json.dumps({"calls": CALLS, "final": str(final)[:300], "ok": ok}))

RESULT_JSON {"calls": [[17, 25]], "final": "The result of adding 17 and 25 is 42.", "ok": true}

What we did not test

• Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here.
• Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment.
• Anything beyond one tool and one question; three trials is a smoke test, not a benchmark.
• Document stores, retrieval pipelines and evaluation.

Reproduce it

Versions change. These commands install whatever is latest on the day you run them unless a version is pinned, so expect different results later. The version we measured is in the table above.

# 1. Serve any local model that supports tool calling behind an OpenAI-compatible endpoint, registered as qwen2.5-3b:
#    http://127.0.0.1:11434/v1  (we used Ollama with a Qwen2.5-3B-Instruct Q4_K_M GGUF)
uv venv -p 3.13 .venv && VIRTUAL_ENV=.venv uv pip install haystack-ai
# 2. Save common.py (above) and the task script next to each other, then:
.venv/bin/python haystack_agent.py

How to read this test

Every number on this page was measured on this one machine, which also ran other jobs, so timings are indicative and vary run to run. A pass means our small task worked once or as stated, a fail means it did not work as we ran it; neither says how the tool behaves with a vendor's frontier model, on a GPU, or at scale. Where a tool could not run without an account or a GPU, we say so instead of guessing.

See the testing rig for the hardware, the local model and the rules we follow, and the test hub for every other test.

Related tests: agent frameworks and sdks

• Instructor: Instructor 1.17.0 returned a validated Pydantic object from a local 3B model in 3 of 3 trials (structured extraction, not a tool call); cold uv install 1.4 s.
• LangChain: LangChain 1.4.7 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 0.8 s.
• LangChain.js: LangChain.js 1.5.19 passed our one-tool task 3 of 3 on Node 20 and 3 of 3 on Node 24; about 101 MB in 36 packages.
• LangGraph: LangGraph 1.2.17 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 2.5 s.
• LiteLLM: LiteLLM 1.106.4 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 2.3 s.
• LlamaIndex: LlamaIndex 0.14.25 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 3.4 s.

All test logs · How we test

FAQ

Sources

• Haystack repository (fetched 2026-10-25)

Related

• All test logs
• Methodology and testing rig
• Study: install size and first-task results across 16 frameworks
• Haystack facts and sources