VCR LangChain

Patches VCR.py to include non-network tooling for use with LangChain. Refactor with confidence as you record and replay all your LLM logic in a contained environment, free from any and all side effects.

Quickstart

pip install vcr-langchain

Use it with pytest:

import vcr_langchain as vcr
from langchain.llms import OpenAI

@vcr.use_cassette()
def test_use_as_test_decorator():
    llm = OpenAI(model_name="text-ada-001")
    assert llm("Tell me a surreal joke") == "<put the output here>"

The next time you run it:

the output is now deterministic
it executes a lot faster by replaying from cache
no command executions or other side effects actually happen
you no longer need to have real API keys defined for test execution in CI environments

For more examples, see the usages test file.

If you're using the Langchain Playwright browser tools, you can also use get_sync_test_browser and get_async_test_browser to automatically get real browsers during recording but fake browsers on replay. This allows you to skip downloading and installing Playwright browsers on your remote CI server, while still being able to re-record sessions in a real browser when developing locally.

Pitfalls

Note that tools, if initialized outside of the vcr_langchain decorator, will not have recording capabilities patched in. This is true even if an agent using those tools is initialized within the decorator.

Documentation

For more information on how VCR works and what other options there are, please see the VCR docs.

For more information on how to use langchain, please see the langchain docs.

Please note that there is a lot of langchain functionality that I haven't gotten around to hijacking for recording. If there's anything you need to record in a cassette, please open a PR or issue.

Projects that use this

LangChain Visualizer

Release files for vcr-langchain 0.0.31

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for vcr-langchain 0.0.31
File	Size	Uploaded
vcr_langchain-0.0.31.tar.gz	8.7 kB	Jan 9, 2024	Details

Built distribution (wheel)

Table of built distributions (wheels) for vcr-langchain 0.0.31
File	Interpreter	ABI	Platform	Reset
vcr_langchain-0.0.31-py3-none-any.whl 9.0 kB Jan 9, 2024	Python 3	none	any	Details

Total release size: 17.7 kB

Release files / vcr_langchain-0.0.31.tar.gz

Download URL	vcr_langchain-0.0.31.tar.gz
Size	8.7 kB
Tags	Source
SHA-256 checksum How to use checksums	`fc7131fb66b4e09885fd6d50b37c72542e57aae113b5e303b8ff5d649307b7d2`
BLAKE2b-256 checksum How to use checksums	`aeecf5cfc468a7e8699d9056f7d8408e7464a3f397a99bf0c7949af7228dabcd`
Upload date	Jan 9, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.5.1 CPython/3.11.4 Linux/5.15.0-91-generic`

Release files / vcr_langchain-0.0.31-py3-none-any.whl

Download URL	vcr_langchain-0.0.31-py3-none-any.whl
Size	9.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`65f4dea747c568181943c31e7c9436bb389ec26d10591e15b8a582ff12c2bdcd`
BLAKE2b-256 checksum How to use checksums	`c108f814c49f291f6560bd77717ba8d4717b9df987c54e0219ed97dfd13f173b`
Upload date	Jan 9, 2024
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`poetry/1.5.1 CPython/3.11.4 Linux/5.15.0-91-generic`