Eugene Yurtsev comments

Results 457 comments of


                                            Eugene Yurtsev

Docs: Concise intro

Looks great!

Add Spark DataFrame as a Document Loader

Thanks for the contribution! Here is a reference for how to add tests with optional dependencies: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md#working-with-optional-dependencies

Change methodology for scraping

Would it be better to use the tags if they exist and if not then fall back to a different strategy of using the body tag ?

Change methodology for scraping

@Haste171 let us know if you're interested in implementing the fallback strategy

Change methodology for scraping

Feel free to re-open if you end up doing any work on this! Thanks @Haste171

RFC: Flag to pass openai creds at invocation

@dev2049 This works, we'll need to figure out how to handle things for serialization.

handle single arg to and/or

@dev2049 yeah that works -- if it gets complex in the future we can separate out to another post-processing step, but looks good where it is now

feat: interfaces for async embeddings, implement async openai

Hi @tyree731 , code looks good -- let's remove the abstractmethod to reduce scope and avoid breaking changes and then code is good to merge.

Updated notebook openai_functions_agent.ipynb

@sumanthdonthula thanks for the contribution! Looking good! I'm wondering if we could paraphrase the "train" word in this sentence: "The agent will be trained to perform 3 search functionalities with...

Getting NameError: name 'partition_pdf' is not defined when running "documents = loader.load()"

Hi @botchagalupe, If you have a full stack trace that would be more helpful (the one included in your previous response is abbreviated). Based on that stack trace I'd check...