For New Contributors: Use SecretStr for api_keys

[eyurtsev]

Updated: 20233-12-06

Hello everyone! thank you all for your contributions! We've made a lot of progress with SecretStrs in the code base.

First time contributors -- hope you had fun learning how to work in the code base and thanks for putting in the time. All contributors -- thanks for all your efforts in improving LangChain.

We'll create a new first time issue in a few months.

---

Hello LangChain community,

We're always happy to see more folks getting involved in contributing to the LangChain codebase.

This is a good first issue if you want to learn more about how to set up
for development in the LangChain codebase.

Goal

Your contribution will make it safer to print out a LangChain object
without having any secrets included in raw format in the string representation.

Set up for development

Prior to making any changes in the code:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

Make sure you're able to test, format, lint from langchain/libs/langchain

make test

make format

make lint

Shall you accept

Shall you accept this challenge, please claim one (and only one) of the modules from the list
below as one that you will be working on, and respond to this issue.

Once you've made the required code changes, open a PR and link to this issue.

Acceptance Criteria

• invoking str or repr on the the object does not show the secret key

Integration test for the code updated to include tests that:

• confirms the object can be initialized with an API key provided via the initializer
• confirms the object can be initialized with an API key provided via an env variable

Confirm that it works:

• either re-run notebook for the given object or else add an appropriate test
  that confirms that the actual secret is used appropriately (i.e.,.get_secret_value())

If your code does not use get_secret_value() somewhere, then it probably contains a bug!

Modules

• langchain/chat_models/anyscale.py @aidoskanapyanov
• langchain/chat_models/azure_openai.py @onesolpark
• langchain/chat_models/azureml_endpoint.py @fyasla
• langchain/chat_models/baichuan.py
• langchain/chat_models/everlyai.py @sfreisthler
• langchain/chat_models/fireworks.py @nepalprabin
• langchain/chat_models/google_palm.py @faisalt14
• langchain/chat_models/javelin_ai_gateway.py
• langchain/chat_models/jinachat.py
• langchain/chat_models/konko.py
• langchain/chat_models/litellm.py
• langchain/chat_models/openai.py @AnasKhan0607
• langchain/chat_models/tongyi.py
• langchain/llms/ai21.py
• langchain/llms/aleph_alpha.py @slangenbach
• langchain/llms/anthropic.py
• langchain/llms/anyscale.py @aidoskanapyanov
• langchain/llms/arcee.py
• langchain/llms/azureml_endpoint.py
• langchain/llms/bananadev.py
• langchain/llms/cerebriumai.py
• langchain/llms/cohere.py @arunsathiya
• langchain/llms/edenai.py @kristinspenc
• langchain/llms/fireworks.py
• langchain/llms/forefrontai.py
• langchain/llms/google_palm.py @Harshil-Patel28
• langchain/llms/gooseai.py
• langchain/llms/javelin_ai_gateway.py
• langchain/llms/minimax.py
• langchain/llms/nlpcloud.py
• langchain/llms/openai.py @HassanA01
• langchain/llms/petals.py @akshatvishu
• langchain/llms/pipelineai.py
• langchain/llms/predibase.py
• langchain/llms/stochasticai.py
• langchain/llms/symblai_nebula.py @praveenv
• langchain/llms/together.py
• langchain/llms/tongyi.py
• langchain/llms/writer.py @ommirzaei
• langchain/llms/yandex.py

Motivation

Prevent secrets from being printed out when printing the given langchain object.

Your contribution

Please sign up by responding to this issue and including the name of the module.

[HassanA01]

Hey @eyurtsev ! I am working with a group of 4 and would like to tackle this issue for my project at my course. Do you think completing these modules would be feasible in a month?

[eyurtsev]

@HassanA01 yes definitely. But the work is very similar across all the modules -- I would suggest selecting a single module per individual and should be just a few lines of code. This is a good entry point to set up for development w/ langchain and learn a little bit about the code structure

[HassanA01]

@eyurtsev Sounds good! Also, could you recommend an issue that might be a little bit more complex but doesn't require too much knowledge about the in-depths of langchain which we can also tackle and would be feasible to complete in 2-3 weeks

[eyurtsev]

Not of the top of my head, but I'll think some -- in the meantime feel free to scan through the list of issues or feature requests to see if something stands out.

[faisalt14]

Hey, I’m also part of @HassanA01’s group and am planning to work on the langchain/chat_models/google_palm.py module. 😁

[HassanA01]

No worries! My group and I will get started to tackle this issue. I'll work on the langchain/llms/openai.py module!

[HassanA01]

@eyurtsev Is it fine if as a group of 5, we make one PR to the upstream main with 5 module fixes (1 per team member)?

[AnasKhan0607]

Another member of the team 🫡. Will be tackling the langchain/chat_models/openai.py module.

[eyurtsev]

@HassanA01 totally fine -- claim the modules that you want :)