# Unit Testing with Fake Models — LangChain / LlamaIndex

Source: https://www.geekswithgeeks.com/en/langchain-llamaindex/p-test

> Test your chain logic without calling a real LLM.

## Deterministic tests for deterministic code

Most of an LLM app is ordinary code: formatting, routing, parsing, validation, tool functions, retrieval wiring. Test it normally with **fake models** (`FakeListChatModel`, `MockLLM`) and fake embeddings that return fixed outputs. This makes tests fast, free and repeatable, and lets you simulate failures (a malformed JSON reply, a timeout, a tool error). Reserve a **separate, smaller set of evaluation runs** against the real model for quality, since real outputs are variable. Do not assert on exact free-text answers from a real model in unit tests.

## Test without the model, measure with it

Fakes make unit tests fast and free; evaluation sets measure real quality.

![Four habits: fake, evaluate, trace, pin.](assets/figures/langchain-llamaindex/section-7-map.svg) — Figure 7.1 — Fake, evaluate, trace and pin.

## A pytest-style test (illustrative)

The chain is built from a prompt, a fake model and a parser, so the test needs no network. The structure matches the chain demonstrated earlier; not run as a test here.

```python
from langchain_core.language_models.fake_chat_models import FakeListChatModel
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate

def build_chain(model):
    prompt = ChatPromptTemplate.from_template("Translate to French: {text}")
    return prompt | model | StrOutputParser()

def test_chain_returns_model_text():
    chain = build_chain(FakeListChatModel(responses=["Bonjour"]))
    assert chain.invoke({"text": "Hello"}) == "Bonjour"

def test_missing_variable_fails_early():
    chain = build_chain(FakeListChatModel(responses=["x"]))
    try:
        chain.invoke({})
        assert False, "expected an error"
    except Exception:
        pass
```

**Quiz:** Why use fake models in unit tests?

- [x] Tests become fast, free and repeatable
- [ ] They improve model quality
- [ ] They remove the need for code
- [ ] They train the embeddings

*Answer:* Tests become fast, free and repeatable. Fixed outputs make assertions on your own logic reliable.