-
Notifications
You must be signed in to change notification settings - Fork 42
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update agent eval tutorial #582
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
_set_env("LANGCHAIN_API_KEY") | ||
_set_env("OPENAI_API_KEY") | ||
#endregion | ||
``` | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
While we're using OpenAI for this example, you can use any [LangChain supported chat model](https://python.langchain.com/docs/integrations/chat/#all-chat-models). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nothing looks openai dependent from a quick skim but need to confirm if true
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
i dont know if we should even say that you need to use langchain. yes this code is langchain-based but you could apply all the same techniques without it, from langsmith perspective it doesn't matter if you use langchain
Co-authored-by: Tanushree <[email protected]>
Co-authored-by: Tanushree <[email protected]>
|
||
# Grade prompt | ||
grade_prompt_answer_accuracy = prompt = hub.pull("langchain-ai/rag-answer-vs-reference") | ||
You can see what these results look like here: [LangSmith link](https://smith.langchain.com/public/708d08f4-300e-4c75-9677-c6b71b0d28c9/d). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think embedding the link on the word "here" makes more sense to me
…/langsmith-docs into bagatur/eval_agent_tutorial
No description provided.